Continuous speech recognition from microphone on MS Azure

Question

I want to use the Azure Speech service for speech recognition from the microphone. I have a program running smoothly in Python with recognize_once_async(), this recognizes only the first utterance with a 15-second audio limit though. I did some research on this topic and went over sample code from MS (https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/python/console/speech_sample.py) and couldn't find anything that enables continuous speech recognition from microphone... Any tips?

Answer 1

You could try the below code :

import azure.cognitiveservices.speech as speechsdk
import os
import time

 
path = os.getcwd()
# Creates an instance of a speech config with specified subscription key and service region.
# Replace with your own subscription key and region identifier from here: https://aka.ms/speech/sdkregion
speech_key, service_region = "6.....9", "eastus"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)

# Creates a recognizer with the given settings
speech_config.speech_recognition_language="en-US"
#source_language_config = speechsdk.languageconfig.SourceLanguageConfig("en-US", "The Endpoint ID for your custom model.")
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

done = False 
def stop_cb(evt):
    print('CLOSING on {}'.format(evt))
    speech_recognizer.stop_continuous_recognition()
    global done
    done= True
    

#Connect callbacks to the events fired by the speech recognizer    
speech_recognizer.recognizing.connect(lambda evt: print('RECOGNIZING: {}'.format(evt)))
speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
# stop continuous recognition on either session stopped or canceled events
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)

speech_recognizer.start_continuous_recognition()

while not done:
    time.sleep(.5)

Explanation : By default, when you don't provide the audioconfig - the default input source is microphone.

If you would like configure/customize - you could use audioconfig class

In continous recognition there are various callback for events like - Recognizing,Recognized, cancelled.

Output :