Phoneme Support

Aman Verma 1 Reputation point
2021-11-02T16:38:09.5+00:00

Does Speech to Text Provide Phoneme Support @phoneme
@Speech Totext
eg What is the first sound in CAT (Answer- /k/)
2nd. What is last sound in Bottom (Answer- /tum/)
If yes please share me the resource so i can also check the same.

Thank You

Azure AI Speech
Azure AI Speech
An Azure service that integrates speech processing into apps and services.
1,683 questions

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. romungi-MSFT 45,036 Reputation points Microsoft Employee
    2021-11-03T05:48:21.207+00:00

    @Aman Verma For getting phonemes for speech to text API you need to use the pronunciation assessment feature as part of the speech config. In the config for pronunciation assessment the granularity has to be defined to phoneme level. 

    pronunciation_assessment_config = \  
        speechsdk.PronunciationAssessmentConfig(reference_text='reference text',  
                grading_system=msspeech.PronunciationAssessmentGradingSystem.HundredMark,  
                granularity=msspeech.PronunciationAssessmentGranularity.Phoneme)  
speech_recognizer = speechsdk.SpeechRecognizer(  
        speech_config=speech_config, \  
        audio_config=audio_config)  
  
# apply the pronunciation assessment configuration to the speech recognizer  
pronunciation_assessment_config.apply_to(speech_recognizer)  
result = speech_recognizer.recognize_once()  
pronunciation_assessment_result = speechsdk.PronunciationAssessmentResult(result)  
pronunciation_score = pronunciation_assessment_result.pronunciation_score

    You can lookup this page in documentation for more details on using this functionality.

    If an answer is helpful, please click on 130616-image.png or upvote 130671-image.png which might help other community members reading this thread.

    0 comments

Your answer

Answers can be marked as Accepted Answers by the question author, which helps users to know the answer solved the author's problem.