Blogs by Ashwin

  Introduction The TranslationRecognizer provides transcriptions of spoken input that have been translated, effectively converting spoken language into text. Additionally, you can produce the translation as speech, enabling speech-to-speech translation options. There are two methods available to achieve this. Event-based Synthesis When you aim to conduct a 1:1 translation (translating from one source language directly into a single target language), you can utilize event-driven synthesis to capture the translation as an audio stream. To accomplish this, you must indicate the preferred voice for the translated speech in the TranslationConfig. Develop an event handler for the Synthesizing event of the TranslationRecognizer object. Within the event handler, employ the GetAudio() method from the Result parameter to obtain the byte stream of the translated audio. The exact code for creating an event handler differs depending on the programming language you are using. Manual Synthesis Ma...

  Introduction By identifying and recording spoken input in a designated language and providing translations of the transcription in one or more other languages, translation of speech expands upon speech recognition. Provision an Azure Resource For Speech Translation The Azure AI Speech service offers comprehensive speech translation capabilities powered by machine learning and artificial intelligence, allowing developers to integrate real-time, end-to-end speech translation into their applications or services. You have the option to utilize either a dedicated Azure AI Speech resource or a multi-service Azure AI Services resource. Before you can use the service, you need to create an Azure AI Speech resource in your Azure subscription. After creating your Azure resource, you will need the following information to use it from a client application through one of the supported SDKs: The location in which the resource is deployed One of the keys assigned to your resource. You can view ...

  Configure Audio Format and Voices When generating speech, a SpeechConfig object can be utilized to tailor the audio provided by the Azure AI Speech service. Audio Format The Azure AI Speech service offers various output formats for the audio stream produced by speech synthesis. You can select a format that aligns with your specific requirements: Audio file type Sample-rate Bit-depth The supported formats are indicated in the SDK using the SpeechSynthesisOutputFormat enumeration. Voices The Azure AI Speech service offers a variety of voices that can be utilized to customize your speech-enabled applications. There are two kinds of voice that you can use: Standard voices - synthetic voices created from audio samples. Neural voices - more natural sounding voices created using deep neural networks. Voices are identified by names that indicate a locale and a person's name Use Speech Synthesis Markup Language While the Azure AI Speech SDK enables you to submit plain text to be synthes...

  Use the Text to Speech API The Azure AI Speech service provides additional REST APIs for speech synthesis, much like its Speech to Text APIs: The Text to speech API, which is the primary way to perform speech synthesis. The Batch synthesis API, which is designed to support batch operations that convert large volumes of text to audio, for example to generate an audio-book from the source text. Using the Azure AI Speech SDK Similar to voice recognition, the Azure AI voice SDK is actually used to create the majority of interactive speech-enabled applications. The pattern for implementing speech synthesis is similar to that of speech recognition: Use a SpeechConfig object to encapsulate the information required to connect to your Azure AI Speech resource. Specifically, its location and key. Optionally, use an AudioConfig to define the output device for the speech to be synthesized. By default, this is the default system speaker, but you can also specify an audio file, or by explic...

  Use the Azure AI Speech to Text API The Azure AI Speech service supports speech recognition through two REST APIs: The Speech to text API, which is the primary way to perform speech recognition. The Speech to text Short Audio API, which is optimized for short streams of audio (up to 60 seconds). Depending on how long the spoken input is expected to be, you can use either API for interactive voice recognition. Additionally, you can batch transcribe several audio recordings to text using the Speech to Text API. Using the Azure AI Speech SDK There is a standard procedure for utilizing the Speech to Text API, even though the specifics differ based on the SDK being used (Python, C#, etc.) : Use a SpeechConfig object to encapsulate the information required to connect to your Azure AI Speech resource. Specifically, its location and key. Optionally, use an AudioConfig to define the input source for the audio to be transcribed. By default, this is the default system microp...

  Introduction You may create speech-enabled apps with the Azure AI Speech service. You can create speech-enabled applications using the APIs provided by Azure AI Speech. This includes: Speech to text - An API that enables speech recognition in which your application can accept spoken input. Text to speech - An API that enables speech synthesis in which your application can provide spoken output. Speech Translation - An API that you can use to translate spoken input into multiple languages. Speaker Recognition - An API that enables your application to recognize individual speakers based on their voice. Intent Recognition - An API that uses conversational language understanding to determine the semantic meaning of spoken input. Provision An Azure Resource For Speech You must first build an Azure AI Speech resource in your Azure subscription in order to use Azure AI Speech. Either a multi-service Azure AI Services resource or a single Azure AI Speech resource are available. Afte...