How to recognize intents with custom entity pattern matching

Article
03/18/2025

The Azure AI services Speech SDK has a built-in feature to provide intent recognition with simple language pattern matching. An intent is something the user wants to do: close a window, mark a checkbox, insert some text, etc.

In this guide, you use the Speech SDK to develop a console application that derives intents from speech utterances spoken through your device's microphone. You learn how to:

Create a Visual Studio project referencing the Speech SDK NuGet package
Create a speech configuration and get an intent recognizer
Add intents and patterns via the Speech SDK API
Add custom entities via the Speech SDK API
Use asynchronous, event-driven continuous recognition

When to use pattern matching

Use pattern matching if:

You're only interested in matching strictly what the user said. These patterns match more aggressively than conversational language understanding (CLU).
You don't have access to a CLU model, but still want intents.

For more information, see the pattern matching overview.

Prerequisites

Be sure you have the following items before you begin this guide:

An Azure AI services resource or a Unified Speech resource
Visual Studio 2019 (any edition).

Create a project

Create a new C# console application project in Visual Studio 2019 and install the Speech SDK.

Start with some boilerplate code

Let's open Program.cs and add some code that works as a skeleton for our project.

using System;
using System.Threading.Tasks;
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Intent;

namespace helloworld
{
    class Program
    {
        static void Main(string[] args)
        {
            IntentPatternMatchingWithMicrophoneAsync().Wait();
        }

        private static async Task IntentPatternMatchingWithMicrophoneAsync()
        {
            var config = SpeechConfig.FromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");
        }
    }
}

Create a Speech configuration

Before you can initialize an IntentRecognizer object, you need to create a configuration that uses the key and Azure region for your Azure AI services prediction resource.

Replace "YOUR_SUBSCRIPTION_KEY" with your Azure AI services prediction key.
Replace "YOUR_SUBSCRIPTION_REGION" with your Azure AI services resource region.

This sample uses the FromSubscription() method to build the SpeechConfig. For a full list of available methods, see SpeechConfig Class.

Initialize an IntentRecognizer

Now create an IntentRecognizer. Insert this code right below your Speech configuration.

using (var recognizer = new IntentRecognizer(config))
{
    
}

Add some intents

You need to associate some patterns with a PatternMatchingModel and apply it to the IntentRecognizer. We'll start by creating a PatternMatchingModel and adding a few intents to it.

Note

We can add multiple patterns to a PatternMatchingIntent.

Insert this code inside the using block:

// Creates a Pattern Matching model and adds specific intents from your model. The
// Id is used to identify this model from others in the collection.
var model = new PatternMatchingModel("YourPatternMatchingModelId");

// Creates a pattern that uses groups of optional words. "[Go | Take me]" will match either "Go", "Take me", or "".
var patternWithOptionalWords = "[Go | Take me] to [floor|level] {floorName}";

// Creates a pattern that uses an optional entity and group that could be used to tie commands together.
var patternWithOptionalEntity = "Go to parking [{parkingLevel}]";

// You can also have multiple entities of the same name in a single pattern by adding appending a unique identifier
// to distinguish between the instances. For example:
var patternWithTwoOfTheSameEntity = "Go to floor {floorName:1} [and then go to floor {floorName:2}]";
// NOTE: Both floorName:1 and floorName:2 are tied to the same list of entries. The identifier can be a string
//       and is separated from the entity name by a ':'

// Creates the pattern matching intents and adds them to the model
model.Intents.Add(new PatternMatchingIntent("ChangeFloors", patternWithOptionalWords, patternWithOptionalEntity, patternWithTwoOfTheSameEntity));
model.Intents.Add(new PatternMatchingIntent("DoorControl", "{action} the doors", "{action} doors", "{action} the door", "{action} door"));

Add some custom entities

To take full advantage of the pattern matcher, you can customize your entities. We'll make "floorName" a list of the available floors. We'll also make "parkingLevel" an integer entity.

Insert this code below your intents:

// Creates the "floorName" entity and set it to type list.
// Adds acceptable values. NOTE the default entity type is Any and so we do not need
// to declare the "action" entity.
model.Entities.Add(PatternMatchingEntity.CreateListEntity("floorName", EntityMatchMode.Strict, "ground floor", "lobby", "1st", "first", "one", "1", "2nd", "second", "two", "2"));

// Creates the "parkingLevel" entity as a pre-built integer
model.Entities.Add(PatternMatchingEntity.CreateIntegerEntity("parkingLevel"));

Apply our model to the Recognizer

Now it's necessary to apply the model to the IntentRecognizer. It's possible to use multiple models at once so the API takes a collection of models.

Insert this code below your entities:

var modelCollection = new LanguageUnderstandingModelCollection();
modelCollection.Add(model);

recognizer.ApplyLanguageModels(modelCollection);

Recognize an intent

From the IntentRecognizer object, you're going to call the RecognizeOnceAsync() method. This method asks the Speech service to recognize speech in a single phrase, and stop recognizing speech once the phrase is identified.

Insert this code after applying the language models:

Console.WriteLine("Say something...");

var result = await recognizer.RecognizeOnceAsync();

Display the recognition results (or errors)

When the Speech service returns the recognition result, we print the result.

Insert this code below var result = await recognizer.RecognizeOnceAsync();:

if (result.Reason == ResultReason.RecognizedIntent)
{
    Console.WriteLine($"RECOGNIZED: Text={result.Text}");
    Console.WriteLine($"       Intent Id={result.IntentId}.");

    var entities = result.Entities;
    switch (result.IntentId)
    {
        case "ChangeFloors":
            if (entities.TryGetValue("floorName", out string floorName))
            {
                Console.WriteLine($"       FloorName={floorName}");
            }

            if (entities.TryGetValue("floorName:1", out floorName))
            {
                Console.WriteLine($"     FloorName:1={floorName}");
            }

            if (entities.TryGetValue("floorName:2", out floorName))
            {
                Console.WriteLine($"     FloorName:2={floorName}");
            }

            if (entities.TryGetValue("parkingLevel", out string parkingLevel))
            {
                Console.WriteLine($"    ParkingLevel={parkingLevel}");
            }

            break;

        case "DoorControl":
            if (entities.TryGetValue("action", out string action))
            {
                Console.WriteLine($"          Action={action}");
            }
            break;
    }
}
else if (result.Reason == ResultReason.RecognizedSpeech)
{
    Console.WriteLine($"RECOGNIZED: Text={result.Text}");
    Console.WriteLine($"    Intent not recognized.");
}
else if (result.Reason == ResultReason.NoMatch)
{
    Console.WriteLine($"NOMATCH: Speech could not be recognized.");
}
else if (result.Reason == ResultReason.Canceled)
{
    var cancellation = CancellationDetails.FromResult(result);
    Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");

    if (cancellation.Reason == CancellationReason.Error)
    {
        Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
        Console.WriteLine($"CANCELED: ErrorDetails={cancellation.ErrorDetails}");
        Console.WriteLine($"CANCELED: Did you set the speech resource key and region values?");
    }
}

Check your code

At this point, your code should look like this:

using System;
using System.Threading.Tasks;
using Microsoft.CognitiveServices.Speech;
using Microsoft.CognitiveServices.Speech.Intent;

namespace helloworld
{
    class Program
    {
        static void Main(string[] args)
        {
            IntentPatternMatchingWithMicrophoneAsync().Wait();
        }

        private static async Task IntentPatternMatchingWithMicrophoneAsync()
        {
            var config = SpeechConfig.FromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");

            using (var recognizer = new IntentRecognizer(config))
            {
                // Creates a Pattern Matching model and adds specific intents from your model. The
                // Id is used to identify this model from others in the collection.
                var model = new PatternMatchingModel("YourPatternMatchingModelId");

                // Creates a pattern that uses groups of optional words. "[Go | Take me]" will match either "Go", "Take me", or "".
                var patternWithOptionalWords = "[Go | Take me] to [floor|level] {floorName}";

                // Creates a pattern that uses an optional entity and group that could be used to tie commands together.
                var patternWithOptionalEntity = "Go to parking [{parkingLevel}]";

                // You can also have multiple entities of the same name in a single pattern by adding appending a unique identifier
                // to distinguish between the instances. For example:
                var patternWithTwoOfTheSameEntity = "Go to floor {floorName:1} [and then go to floor {floorName:2}]";
                // NOTE: Both floorName:1 and floorName:2 are tied to the same list of entries. The identifier can be a string
                //       and is separated from the entity name by a ':'

                // Adds some intents to look for specific patterns.
                model.Intents.Add(new PatternMatchingIntent("ChangeFloors", patternWithOptionalWords, patternWithOptionalEntity, patternWithTwoOfTheSameEntity));
                model.Intents.Add(new PatternMatchingIntent("DoorControl", "{action} the doors", "{action} doors", "{action} the door", "{action} door"));

                // Creates the "floorName" entity and set it to type list.
                // Adds acceptable values. NOTE the default entity type is Any and so we do not need
                // to declare the "action" entity.
                model.Entities.Add(PatternMatchingEntity.CreateListEntity("floorName", EntityMatchMode.Strict, "ground floor", "lobby", "1st", "first", "one", "1", "2nd", "second", "two", "2"));

                // Creates the "parkingLevel" entity as a pre-built integer
                model.Entities.Add(PatternMatchingEntity.CreateIntegerEntity("parkingLevel"));

                var modelCollection = new LanguageUnderstandingModelCollection();
                modelCollection.Add(model);

                recognizer.ApplyLanguageModels(modelCollection);

                Console.WriteLine("Say something...");

                var result = await recognizer.RecognizeOnceAsync();

                if (result.Reason == ResultReason.RecognizedIntent)
                {
                    Console.WriteLine($"RECOGNIZED: Text={result.Text}");
                    Console.WriteLine($"       Intent Id={result.IntentId}.");

                    var entities = result.Entities;
                    switch (result.IntentId)
                    {
                        case "ChangeFloors":
                            if (entities.TryGetValue("floorName", out string floorName))
                            {
                                Console.WriteLine($"       FloorName={floorName}");
                            }

                            if (entities.TryGetValue("floorName:1", out floorName))
                            {
                                Console.WriteLine($"     FloorName:1={floorName}");
                            }

                            if (entities.TryGetValue("floorName:2", out floorName))
                            {
                                Console.WriteLine($"     FloorName:2={floorName}");
                            }

                            if (entities.TryGetValue("parkingLevel", out string parkingLevel))
                            {
                                Console.WriteLine($"    ParkingLevel={parkingLevel}");
                            }

                            break;

                        case "DoorControl":
                            if (entities.TryGetValue("action", out string action))
                            {
                                Console.WriteLine($"          Action={action}");
                            }
                            break;
                    }
                }
                else if (result.Reason == ResultReason.RecognizedSpeech)
                {
                    Console.WriteLine($"RECOGNIZED: Text={result.Text}");
                    Console.WriteLine($"    Intent not recognized.");
                }
                else if (result.Reason == ResultReason.NoMatch)
                {
                    Console.WriteLine($"NOMATCH: Speech could not be recognized.");
                }
                else if (result.Reason == ResultReason.Canceled)
                {
                    var cancellation = CancellationDetails.FromResult(result);
                    Console.WriteLine($"CANCELED: Reason={cancellation.Reason}");

                    if (cancellation.Reason == CancellationReason.Error)
                    {
                        Console.WriteLine($"CANCELED: ErrorCode={cancellation.ErrorCode}");
                        Console.WriteLine($"CANCELED: ErrorDetails={cancellation.ErrorDetails}");
                        Console.WriteLine($"CANCELED: Did you set the speech resource key and region values?");
                    }
                }
            }
        }
    }
}

Build and run your app

Now you're ready to build your app and test our speech recognition using the Speech service.

Compile the code - From the menu bar of Visual Studio, choose Build > Build Solution.
Start your app - From the menu bar, choose Debug > Start Debugging or press F5.
Start recognition - It prompts you to say something. The default language is English. Your speech is sent to the Speech service, transcribed as text, and rendered in the console.

For example if you say "Take me to floor 2", this should be the output:

Say something...
RECOGNIZED: Text=Take me to floor 2.
       Intent Id=ChangeFloors.
       FloorName=2

As another example if you say "Take me to floor 7", this should be the output:

Say something...
RECOGNIZED: Text=Take me to floor 7.
    Intent not recognized.

No intent was recognized because 7 wasn't in our list of valid values for floorName.

Create a project

Create a new C++ console application project in Visual Studio 2019 and install the Speech SDK.

Start with some boilerplate code

Let's open helloworld.cpp and add some code that works as a skeleton for our project.

#include <iostream>
#include <speechapi_cxx.h>

using namespace Microsoft::CognitiveServices::Speech;
using namespace Microsoft::CognitiveServices::Speech::Intent;

int main()
{
    std::cout << "Hello World!\n";

    auto config = SpeechConfig::FromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");
}

Create a Speech configuration

Before you can initialize an IntentRecognizer object, you need to create a configuration that uses the key and Azure region for your Azure AI services prediction resource.

Replace "YOUR_SUBSCRIPTION_KEY" with your Azure AI services prediction key.
Replace "YOUR_SUBSCRIPTION_REGION" with your Azure AI services resource region.

This sample uses the FromSubscription() method to build the SpeechConfig. For a full list of available methods, see SpeechConfig Class.

Initialize an IntentRecognizer

Now create an IntentRecognizer. Insert this code right below your Speech configuration.

    auto intentRecognizer = IntentRecognizer::FromConfig(config);

Add some intents

You need to associate some patterns with a PatternMatchingModel and apply it to the IntentRecognizer. We'll start by creating a PatternMatchingModel and adding a few intents to it. A PatternMatchingIntent is a struct so we just use the in-line syntax.

Note

We can add multiple patterns to a PatternMatchingIntent.

auto model = PatternMatchingModel::FromId("myNewModel");

model->Intents.push_back({"Take me to floor {floorName}.", "Go to floor {floorName}."} , "ChangeFloors");
model->Intents.push_back({"{action} the door."}, "OpenCloseDoor");

Add some custom entities

To take full advantage of the pattern matcher, you can customize your entities. We'll make "floorName" a list of the available floors.

model->Entities.push_back({ "floorName" , Intent::EntityType::List, Intent::EntityMatchMode::Strict, {"one", "1", "two", "2", "lobby", "ground floor"} });

Apply our model to the Recognizer

Now it's necessary to apply the model to the IntentRecognizer. It's possible to use multiple models at once so the API takes a collection of models.

std::vector<std::shared_ptr<LanguageUnderstandingModel>> collection;

collection.push_back(model);
intentRecognizer->ApplyLanguageModels(collection);

Recognize an intent

Insert this code below your intents:

std::cout << "Say something ..." << std::endl;
auto result = intentRecognizer->RecognizeOnceAsync().get();

Display the recognition results (or errors)

When the Speech service returns the recognition result, we print the result.

Insert this code below auto result = intentRecognizer->RecognizeOnceAsync().get();:

switch (result->Reason)
{
case ResultReason::RecognizedSpeech:
        std::cout << "RECOGNIZED: Text = " << result->Text.c_str() << std::endl;
        std::cout << "NO INTENT RECOGNIZED!" << std::endl;
        break;
case ResultReason::RecognizedIntent:
    std::cout << "RECOGNIZED: Text = " << result->Text.c_str() << std::endl;
    std::cout << "  Intent Id = " << result->IntentId.c_str() << std::endl;
    auto entities = result->GetEntities();
    if (entities.find("floorName") != entities.end())
    {
        std::cout << "  Floor name: = " << entities["floorName"].c_str() << std::endl;
    }

    if (entities.find("action") != entities.end())
    {
        std::cout << "  Action: = " << entities["action"].c_str() << std::endl;
    }

    break;
case ResultReason::NoMatch:
{
    auto noMatch = NoMatchDetails::FromResult(result);
    switch (noMatch->Reason)
    {
    case NoMatchReason::NotRecognized:
        std::cout << "NOMATCH: Speech was detected, but not recognized." << std::endl;
        break;
    case NoMatchReason::InitialSilenceTimeout:
        std::cout << "NOMATCH: The start of the audio stream contains only silence, and the service timed out waiting for speech." << std::endl;
        break;
    case NoMatchReason::InitialBabbleTimeout:
        std::cout << "NOMATCH: The start of the audio stream contains only noise, and the service timed out waiting for speech." << std::endl;
        break;
    case NoMatchReason::KeywordNotRecognized:
        std::cout << "NOMATCH: Keyword not recognized" << std::endl;
        break;
    }
    break;
}
case ResultReason::Canceled:
{
    auto cancellation = CancellationDetails::FromResult(result);

    if (!cancellation->ErrorDetails.empty())
    {
        std::cout << "CANCELED: ErrorDetails=" << cancellation->ErrorDetails.c_str() << std::endl;
        std::cout << "CANCELED: Did you set the speech resource key and region values?" << std::endl;
    }
}
default:
    break;
}

Check your code

At this point, your code should look like this:

#include <iostream>
#include <speechapi_cxx.h>

using namespace Microsoft::CognitiveServices::Speech;
using namespace Microsoft::CognitiveServices::Speech::Intent;

int main()
{
    auto config = SpeechConfig::FromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");
    auto intentRecognizer = IntentRecognizer::FromConfig(config);

    auto model = PatternMatchingModel::FromId("myNewModel");

    model->Intents.push_back({"Take me to floor {floorName}.", "Go to floor {floorName}."} , "ChangeFloors");
    model->Intents.push_back({"{action} the door."}, "OpenCloseDoor");

    model->Entities.push_back({ "floorName" , Intent::EntityType::List, Intent::EntityMatchMode::Strict, {"one", "1", "two", "2", "lobby", "ground floor"} });

    std::vector<std::shared_ptr<LanguageUnderstandingModel>> collection;

    collection.push_back(model);
    intentRecognizer->ApplyLanguageModels(collection);

    std::cout << "Say something ..." << std::endl;

    auto result = intentRecognizer->RecognizeOnceAsync().get();

    switch (result->Reason)
    {
    case ResultReason::RecognizedSpeech:
        std::cout << "RECOGNIZED: Text = " << result->Text.c_str() << std::endl;
        std::cout << "NO INTENT RECOGNIZED!" << std::endl;
        break;
    case ResultReason::RecognizedIntent:
        std::cout << "RECOGNIZED: Text = " << result->Text.c_str() << std::endl;
        std::cout << "  Intent Id = " << result->IntentId.c_str() << std::endl;
        auto entities = result->GetEntities();
        if (entities.find("floorName") != entities.end())
        {
            std::cout << "  Floor name: = " << entities["floorName"].c_str() << std::endl;
        }

        if (entities.find("action") != entities.end())
        {
            std::cout << "  Action: = " << entities["action"].c_str() << std::endl;
        }

        break;
    case ResultReason::NoMatch:
    {
        auto noMatch = NoMatchDetails::FromResult(result);
        switch (noMatch->Reason)
        {
        case NoMatchReason::NotRecognized:
            std::cout << "NOMATCH: Speech was detected, but not recognized." << std::endl;
            break;
        case NoMatchReason::InitialSilenceTimeout:
            std::cout << "NOMATCH: The start of the audio stream contains only silence, and the service timed out waiting for speech." << std::endl;
            break;
        case NoMatchReason::InitialBabbleTimeout:
            std::cout << "NOMATCH: The start of the audio stream contains only noise, and the service timed out waiting for speech." << std::endl;
            break;
        case NoMatchReason::KeywordNotRecognized:
            std::cout << "NOMATCH: Keyword not recognized." << std::endl;
            break;
        }
        break;
    }
    case ResultReason::Canceled:
    {
        auto cancellation = CancellationDetails::FromResult(result);

        if (!cancellation->ErrorDetails.empty())
        {
            std::cout << "CANCELED: ErrorDetails=" << cancellation->ErrorDetails.c_str() << std::endl;
            std::cout << "CANCELED: Did you set the speech resource key and region values?" << std::endl;
        }
    }
    default:
        break;
    }
}

Build and run your app

Now you're ready to build your app and test our speech recognition using the Speech service.

Compile the code - From the menu bar of Visual Studio, choose Build > Build Solution.
Start your app - From the menu bar, choose Debug > Start Debugging or press F5.
Start recognition - It prompts you to say something. The default language is English. Your speech is sent to the Speech service, transcribed as text, and rendered in the console.

For example if you say "Take me to floor 2", this should be the output:

Say something ...
RECOGNIZED: Text = Take me to floor 2.
  Intent Id = ChangeFloors
  Floor name: = 2

Another example if you say "Take me to floor 7", this should be the output:

Say something ...
RECOGNIZED: Text = Take me to floor 7.
NO INTENT RECOGNIZED!

The Intent ID is empty because 7 wasn't in our list.

Reference documentation | Additional samples on GitHub

In this quickstart, you install the Speech SDK for Java.

Platform requirements

Choose your target environment:

Java Runtime
Android

The Speech SDK for Java is compatible with Windows, Linux, and macOS.

The Speech SDK for Java supports the following distributions on the x64, ARM32, and ARM64 architectures:

Ubuntu 20.04/22.04/24.04
Debian 11/12
Amazon Linux 2023
Azure Linux 3.0

Important

Use the most recent LTS release of the Linux distribution. For example, if you are using Ubuntu 20.04 LTS, use the latest release of Ubuntu 20.04.X.

The Speech SDK depends on the following Linux system libraries:

The shared libraries of the GNU C library, including the POSIX Threads Programming library, libpthreads.
The OpenSSL library, version 1.x (libssl1) or 3.x (libssl3), and certificates (ca-certificates).
The shared library for ALSA applications (libasound2).

Ubuntu 20.04/22.04/24.04
Debian 11/12

Run these commands:

sudo apt-get update
sudo apt-get install build-essential ca-certificates libasound2-dev libssl-dev wget

Run these commands:

sudo apt-get update
sudo apt-get install build-essential ca-certificates libasound2-dev libssl-dev wget

Install a Java Development Kit such as Azul Zulu OpenJDK. The Microsoft Build of OpenJDK or your preferred JDK should also work.

Install the Speech SDK for Java

Some of the instructions use a specific SDK version such as 1.43.0. To check the latest version, search our GitHub repository.

Choose your target environment:

Java Runtime
Android

This guide shows how to install the Speech SDK for Java on the Java Runtime.

Supported operating systems

The Speech SDK for Java package is available for these operating systems:

Windows: 64-bit only.
Mac: macOS X version 10.14 or later.
Linux: See the supported Linux distributions and target architectures.

Follow these steps to install the Speech SDK for Java using Apache Maven:

Install Apache Maven.
Open a command prompt where you want the new project, and create a new pom.xml file.

Copy the following XML content into pom.xml:

<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>com.microsoft.cognitiveservices.speech.samples</groupId>
    <artifactId>quickstart-eclipse</artifactId>
    <version>1.0.0-SNAPSHOT</version>
    <build>
        <sourceDirectory>src</sourceDirectory>
        <plugins>
        <plugin>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>3.7.0</version>
            <configuration>
            <source>1.8</source>
            <target>1.8</target>
            </configuration>
        </plugin>
        </plugins>
    </build>
    <dependencies>
        <dependency>
        <groupId>com.microsoft.cognitiveservices.speech</groupId>
        <artifactId>client-sdk</artifactId>
        <version>1.43.0</version>
        </dependency>
    </dependencies>
</project>

Run the following Maven command to install the Speech SDK and dependencies.
```
mvn clean dependency:copy-dependencies
```

Create an Eclipse project and install the Speech SDK

Install the Eclipse Java IDE. This IDE requires Java to already be installed.
Start Eclipse.
In Eclipse Launcher, in the Workspace box, enter the name of a new workspace directory. Then select Launch.
In a moment, the main window of the Eclipse IDE appears. Close the Welcome screen if one is present.
From the Eclipse menu, select File > New > Project.
The New Project dialog box appears. Select Java Project, and then select Next.
The New Java Project wizard starts. In the Project name field, enter quickstart. Choose JavaSE-1.8 as the execution environment. Select Finish.
If the Open Associated Perspective? window appears, select Open Perspective.
In Package Explorer, right-click the quickstart project. Select Configure > Convert to Maven Project from the context menu.
The Create new POM window appears. In the Group Id field, enter com.microsoft.cognitiveservices.speech.samples. In the Artifact Id field, enter quickstart. Then select Finish.

Open the pom.xml file and edit it:

Add a dependencies element at the end of the file, before the closing tag </project>, with the Speech SDK as a dependency:

<dependencies>
  <dependency>
    <groupId>com.microsoft.cognitiveservices.speech</groupId>
    <artifactId>client-sdk</artifactId>
    <version>1.43.0</version>
  </dependency>
</dependencies>

Save the changes.

Gradle configurations

Gradle configurations require an explicit reference to the .jar dependency extension:

// build.gradle

dependencies {
    implementation group: 'com.microsoft.cognitiveservices.speech', name: 'client-sdk', version: "1.43.0", ext: "jar"
}

Start with some boilerplate code

Open Main.java from the src dir.
Replace the contents of the file with following:

import java.util.ArrayList;
import java.util.Dictionary;
import java.util.concurrent.ExecutionException;


import com.microsoft.cognitiveservices.speech.*;
import com.microsoft.cognitiveservices.speech.intent.*;

public class Main {
    public static void main(String[] args) throws InterruptedException, ExecutionException {
        IntentPatternMatchingWithMicrophone();
    }

    public static void IntentPatternMatchingWithMicrophone() throws InterruptedException, ExecutionException {
        SpeechConfig config = SpeechConfig.fromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");
    }
}

Create a Speech configuration

Before you can initialize an IntentRecognizer object, you need to create a configuration that uses the key and Azure region for your Azure AI services prediction resource.

Replace "YOUR_SUBSCRIPTION_KEY" with your Azure AI services prediction key.
Replace "YOUR_SUBSCRIPTION_REGION" with your Azure AI services resource region.

This sample uses the fromSubscription() method to build the SpeechConfig. For a full list of available methods, see SpeechConfig Class.

Initialize an IntentRecognizer

Now create an IntentRecognizer. Insert this code right below your Speech configuration. We do this in a try so that we take advantage of the autoclosable interface.

try (IntentRecognizer recognizer = new IntentRecognizer(config)) {

}

Add some intents

You need to associate some patterns with a PatternMatchingModel and apply it to the IntentRecognizer. We will start by creating a PatternMatchingModel and adding a few intents to it.

Note

We can add multiple patterns to a PatternMatchingIntent.

Insert this code inside the try block:

// Creates a Pattern Matching model and adds specific intents from your model. The
// Id is used to identify this model from others in the collection.
PatternMatchingModel model = new PatternMatchingModel("YourPatternMatchingModelId");

// Creates a pattern that uses groups of optional words. "[Go | Take me]" will match either "Go", "Take me", or "".
String patternWithOptionalWords = "[Go | Take me] to [floor|level] {floorName}";

// Creates a pattern that uses an optional entity and group that could be used to tie commands together.
String patternWithOptionalEntity = "Go to parking [{parkingLevel}]";

// You can also have multiple entities of the same name in a single pattern by adding appending a unique identifier
// to distinguish between the instances. For example:
String patternWithTwoOfTheSameEntity = "Go to floor {floorName:1} [and then go to floor {floorName:2}]";
// NOTE: Both floorName:1 and floorName:2 are tied to the same list of entries. The identifier can be a string
//       and is separated from the entity name by a ':'

// Creates the pattern matching intents and adds them to the model
model.getIntents().put(new PatternMatchingIntent("ChangeFloors", patternWithOptionalWords, patternWithOptionalEntity, patternWithTwoOfTheSameEntity));
model.getIntents().put(new PatternMatchingIntent("DoorControl", "{action} the doors", "{action} doors", "{action} the door", "{action} door"));

Add some custom entities

To take full advantage of the pattern matcher you can customize your entities. We will make "floorName" a list of the available floors. We will also make "parkingLevel" an integer entity.

Insert this code below your intents:

// Creates the "floorName" entity and set it to type list.
// Adds acceptable values. NOTE the default entity type is Any and so we do not need
// to declare the "action" entity.
model.getEntities().put(PatternMatchingEntity.CreateListEntity("floorName", PatternMatchingEntity.EntityMatchMode.Strict, "ground floor", "lobby", "1st", "first", "one", "1", "2nd", "second", "two", "2"));

// Creates the "parkingLevel" entity as a pre-built integer
model.getEntities().put(PatternMatchingEntity.CreateIntegerEntity("parkingLevel"));

Apply our model to the Recognizer

Now it is necessary to apply the model to the IntentRecognizer. It is possible to use multiple models at once so the API takes a collection of models.

Insert this code below your entities:

ArrayList<LanguageUnderstandingModel> modelCollection = new ArrayList<LanguageUnderstandingModel>();
modelCollection.add(model);

recognizer.applyLanguageModels(modelCollection);

Recognize an intent

Insert this code after applying the language models:

System.out.println("Say something...");

IntentRecognitionResult result = recognizer.recognizeOnceAsync().get();

Display the recognition results (or errors)

When the recognition result is returned by the Speech service, we will print the result.

Insert this code below IntentRecognitionResult result = recognizer.recognizeOnceAsync.get();:

if (result.getReason() == ResultReason.RecognizedSpeech) {
    System.out.println("RECOGNIZED: Text= " + result.getText());
    System.out.println(String.format("%17s", "Intent not recognized."));
}
else if (result.getReason() == ResultReason.RecognizedIntent)
{
    System.out.println("RECOGNIZED: Text= " + result.getText());
    System.out.println(String.format("%17s %s", "Intent Id=", result.getIntentId() + "."));
    Dictionary<String, String> entities = result.getEntities();

    switch (result.getIntentId())
    {
        case "ChangeFloors":
            if (entities.get("floorName") != null) {
                System.out.println(String.format("%17s %s", "FloorName=", entities.get("floorName")));
            }
            if (entities.get("floorName:1") != null) {
                System.out.println(String.format("%17s %s", "FloorName:1=", entities.get("floorName:1")));
            }
            if (entities.get("floorName:2") != null) {
                System.out.println(String.format("%17s %s", "FloorName:2=", entities.get("floorName:2")));
            }
            if (entities.get("parkingLevel") != null) {
                System.out.println(String.format("%17s %s", "ParkingLevel=", entities.get("parkingLevel")));
            }
            break;
        case "DoorControl":
            if (entities.get("action") != null) {
                System.out.println(String.format("%17s %s", "Action=", entities.get("action")));
            }
            break;
    }
}
else if (result.getReason() == ResultReason.NoMatch) {
    System.out.println("NOMATCH: Speech could not be recognized.");
}
else if (result.getReason() == ResultReason.Canceled) {
    CancellationDetails cancellation = CancellationDetails.fromResult(result);
    System.out.println("CANCELED: Reason=" + cancellation.getReason());

    if (cancellation.getReason() == CancellationReason.Error)
    {
        System.out.println("CANCELED: ErrorCode=" + cancellation.getErrorCode());
        System.out.println("CANCELED: ErrorDetails=" + cancellation.getErrorDetails());
        System.out.println("CANCELED: Did you update the subscription info?");
    }
}

Check your code

At this point, your code should look like this:

package quickstart;
import java.util.ArrayList;
import java.util.concurrent.ExecutionException;
import java.util.Dictionary;

import com.microsoft.cognitiveservices.speech.*;
import com.microsoft.cognitiveservices.speech.intent.*;

public class Main {
    public static void main(String[] args) throws InterruptedException, ExecutionException {
        IntentPatternMatchingWithMicrophone();
    }

    public static void IntentPatternMatchingWithMicrophone() throws InterruptedException, ExecutionException {
        SpeechConfig config = SpeechConfig.fromSubscription("YOUR_SUBSCRIPTION_KEY", "YOUR_SUBSCRIPTION_REGION");
        try (IntentRecognizer recognizer = new IntentRecognizer(config)) {
            // Creates a Pattern Matching model and adds specific intents from your model. The
            // Id is used to identify this model from others in the collection.
            PatternMatchingModel model = new PatternMatchingModel("YourPatternMatchingModelId");

            // Creates a pattern that uses groups of optional words. "[Go | Take me]" will match either "Go", "Take me", or "".
            String patternWithOptionalWords = "[Go | Take me] to [floor|level] {floorName}";

            // Creates a pattern that uses an optional entity and group that could be used to tie commands together.
            String patternWithOptionalEntity = "Go to parking [{parkingLevel}]";

            // You can also have multiple entities of the same name in a single pattern by adding appending a unique identifier
            // to distinguish between the instances. For example:
            String patternWithTwoOfTheSameEntity = "Go to floor {floorName:1} [and then go to floor {floorName:2}]";
            // NOTE: Both floorName:1 and floorName:2 are tied to the same list of entries. The identifier can be a string
            // and is separated from the entity name by a ':'

            // Creates the pattern matching intents and adds them to the model
            model.getIntents().put(new PatternMatchingIntent("ChangeFloors", patternWithOptionalWords, patternWithOptionalEntity, patternWithTwoOfTheSameEntity));
            model.getIntents().put(new PatternMatchingIntent("DoorControl", "{action} the doors", "{action} doors", "{action} the door", "{action} door"));

            // Creates the "floorName" entity and set it to type list.
            // Adds acceptable values. NOTE the default entity type is Any and so we do not need
            // to declare the "action" entity.
            model.getEntities().put(PatternMatchingEntity.CreateListEntity("floorName", PatternMatchingEntity.EntityMatchMode.Strict, "ground floor", "lobby", "1st", "first", "one", "1", "2nd", "second", "two", "2"));

            // Creates the "parkingLevel" entity as a pre-built integer
            model.getEntities().put(PatternMatchingEntity.CreateIntegerEntity("parkingLevel"));

            ArrayList<LanguageUnderstandingModel> modelCollection = new ArrayList<LanguageUnderstandingModel>();
            modelCollection.add(model);

            recognizer.applyLanguageModels(modelCollection);

            System.out.println("Say something...");

            IntentRecognitionResult result = recognizer.recognizeOnceAsync().get();

            if (result.getReason() == ResultReason.RecognizedSpeech) {
                System.out.println("RECOGNIZED: Text= " + result.getText());
                System.out.println(String.format("%17s", "Intent not recognized."));
            }
            else if (result.getReason() == ResultReason.RecognizedIntent)
            {
                System.out.println("RECOGNIZED: Text= " + result.getText());
                System.out.println(String.format("%17s %s", "Intent Id=", result.getIntentId() + "."));
                Dictionary<String, String> entities = result.getEntities();

                switch (result.getIntentId())
                {
                    case "ChangeFloors":
                        if (entities.get("floorName") != null) {
                            System.out.println(String.format("%17s %s", "FloorName=", entities.get("floorName")));
                        }
                        if (entities.get("floorName:1") != null) {
                            System.out.println(String.format("%17s %s", "FloorName:1=", entities.get("floorName:1")));
                        }
                        if (entities.get("floorName:2") != null) {
                            System.out.println(String.format("%17s %s", "FloorName:2=", entities.get("floorName:2")));
                        }
                        if (entities.get("parkingLevel") != null) {
                            System.out.println(String.format("%17s %s", "ParkingLevel=", entities.get("parkingLevel")));
                        }
                        break;

                    case "DoorControl":
                        if (entities.get("action") != null) {
                            System.out.println(String.format("%17s %s", "Action=", entities.get("action")));
                        }
                        break;
                }
            }
            else if (result.getReason() == ResultReason.NoMatch) {
                System.out.println("NOMATCH: Speech could not be recognized.");
            }
            else if (result.getReason() == ResultReason.Canceled) {
                CancellationDetails cancellation = CancellationDetails.fromResult(result);
                System.out.println("CANCELED: Reason=" + cancellation.getReason());

                if (cancellation.getReason() == CancellationReason.Error)
                {
                    System.out.println("CANCELED: ErrorCode=" + cancellation.getErrorCode());
                    System.out.println("CANCELED: ErrorDetails=" + cancellation.getErrorDetails());
                    System.out.println("CANCELED: Did you update the subscription info?");
                }
            }
        }
    }
}

Build and run your app

Now you're ready to build your app and test our intent recognition using the speech service and the embedded pattern matcher.

Select the run button in Eclipse or press ctrl+F11, then watch the output for the "Say something..." prompt. Once it appears speak your utterance and watch the output.

For example if you say "Take me to floor 2", this should be the output:

Say something...
RECOGNIZED: Text=Take me to floor 2.
       Intent Id=ChangeFloors.
       FloorName=2

As another example if you say "Take me to floor 7", this should be the output:

Say something...
RECOGNIZED: Text=Take me to floor 7.
    Intent not recognized.

No intent was recognized because 7 was not in our list of valid values for floorName.

How to recognize intents with custom entity pattern matching

When to use pattern matching

Prerequisites

Create a project

Start with some boilerplate code

Create a Speech configuration

Initialize an IntentRecognizer

Add some intents

Add some custom entities

Apply our model to the Recognizer

Recognize an intent

Display the recognition results (or errors)

Check your code

Build and run your app

Create a project

Start with some boilerplate code

Create a Speech configuration

Initialize an IntentRecognizer

Add some intents

Add some custom entities

Apply our model to the Recognizer

Recognize an intent

Display the recognition results (or errors)

Check your code

Build and run your app

Platform requirements

Install the Speech SDK for Java

Supported operating systems

Start with some boilerplate code

Create a Speech configuration

Initialize an IntentRecognizer

Add some intents

Add some custom entities

Apply our model to the Recognizer

Recognize an intent

Display the recognition results (or errors)

Check your code

Build and run your app

Additional resources