Azure Cognitive Services- Speech To Text

Speech 服務是認知服務的一種，提供了語音轉文本，文本轉語音, 語音翻譯等，今天咱們實戰的是語音轉文本（Speech To Text）。

STT支持兩種訪問方式，1.是SDK，2.是REST API。

其中:

SDK方式支持 識別麥克風的語音流 和 語音文件；

REST API方式僅支持語音文件；

準備工做：建立 認知服務之Speech服務：

建立完成後，兩個重要的參數能夠在頁面查看：

一. REST API方式將語音文件轉換成文本：

Azure global的 Speech API 終結點請參考：

https://docs.microsoft.com/zh-cn/azure/cognitive-services/speech-service/rest-speech-to-text#regions-and-endpoints

Azure 中國區 的 Speech API 終結點：

截至到2020.2月，僅中國東部2區域已開通Speech服務，服務終結點爲：

https://chinaeast2.stt.speech.azure.cn/speech/recognition/conversation/cognitiveservices/v1

對於Speech To Text來講，有兩種身份驗證方式：

其中Authorization  Token有效期爲10分鐘。

爲了簡便，本文使用了Ocp-Apim-Subscription-Key的方式。

注意：若是要實現文本轉語音，按照上表，則必須使用 Authorization Token形式進行身份驗證。

構建請求的其餘注意事項：

1. 文件格式：
   
   
   

2. 請求頭：
   
   
   須要注意的是，Key或者Authorization是二選一的關係。
   

3. 請求參數：
   
   
   

在Postman中的示例以下：

若是要在REST API中使用 Authorization Token，則須要先得到Token：

Global 獲取Token的終結點：

https://docs.microsoft.com/zh-cn/azure/cognitive-services/speech-service/rest-speech-to-text#authentication

中國區獲取Token的終結點：

截至2020.02，只有中國東部2有Speech服務，其Token終結點爲：

https://chinaeast2.api.cognitive.azure.cn/sts/v1.0/issuetoken

Postman獲取Token 參考以下：

二. SDK方式將語音文件轉換成文本（Python示例）：

在官網能夠看到相似的代碼，但須要注意的是，該代碼僅在Azure Global的Speech服務中正常工做，針對中國區，須要作特定的修改（見下文）。

import azure.cognitiveservices.speech as speechsdk # Creates an instance of a speech config with specified subscription key and service region. # Replace with your own subscription key and service region (e.g., "chinaeast2"). speech_key, service_region = "YourSubscriptionKey", "YourServiceRegion" speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region) # Creates an audio configuration that points to an audio file. # Replace with your own audio filename. audio_filename = "whatstheweatherlike.wav" audio_input = speechsdk.AudioConfig(filename=audio_filename) # Creates a recognizer with the given settings speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_input) print("Recognizing first result...") # Starts speech recognition, and returns after a single utterance is recognized. The end of a # single utterance is determined by listening for silence at the end or until a maximum of 15 # seconds of audio is processed.  The task returns the recognition text as result. # Note: Since recognize_once() returns only a single utterance, it is suitable only for single # shot recognition like command or query. # For long-running multi-utterance recognition, use start_continuous_recognition() instead. result = speech_recognizer.recognize_once() # Checks result. if result.reason == speechsdk.ResultReason.RecognizedSpeech:    print("Recognized: {}".format(result.text)) elif result.reason == speechsdk.ResultReason.NoMatch:    print("No speech could be recognized: {}".format(result.no_match_details)) elif result.reason == speechsdk.ResultReason.Canceled:    cancellation_details = result.cancellation_details    print("Speech Recognition canceled: {}".format(cancellation_details.reason))    if cancellation_details.reason == speechsdk.CancellationReason.Error:        print("Error details: {}".format(cancellation_details.error_details))

代碼提供頁面：

https://docs.azure.cn/zh-cn/cognitive-services/speech-service/quickstarts/speech-to-text-from-file?tabs=linux&pivots=programming-language-python#create-a-python-application-that-uses-the-speech-sdk

針對中國區，須要使用自定義終結點的方式，才能正常使用SDK：

speech_key, service_region = "Your Key", "chinaeast2"
template = "wss://{}.stt.speech.azure.cn/speech/recognition" \
               "/conversation/cognitiveservices/v1?initialSilenceTimeoutMs={:d}&language=zh-CN"
speech_config = speechsdk.SpeechConfig(subscription=speech_key,
endpoint=template.format(service_region, int(initial_silence_timeout_ms)))

中國區完整代碼爲：

#!/usr/bin/env python
# coding: utf-8

# Copyright (c) Microsoft. All rights reserved.
# Licensed under the MIT license. See LICENSE.md file in the project root for full license information.
"""
Speech recognition samples for the Microsoft Cognitive Services Speech SDK
"""

import time
import wave

try:
    import azure.cognitiveservices.speech as speechsdk
except ImportError:
    print("""
    Importing the Speech SDK for Python failed.
    Refer to
    https://docs.microsoft.com/azure/cognitive-services/speech-service/quickstart-python for
    installation instructions.
    """)
    import sys
    sys.exit(1)


# Set up the subscription info for the Speech Service:
# Replace with your own subscription key and service region (e.g., "westus").
speech_key, service_region = "your key", "chinaeast2"

# Specify the path to an audio file containing speech (mono WAV / PCM with a sampling rate of 16
# kHz).
filename = "D:\FFOutput\speechtotext.wav"

def speech_recognize_once_from_file_with_custom_endpoint_parameters():
    """performs one-shot speech recognition with input from an audio file, specifying an
    endpoint with custom parameters"""
    initial_silence_timeout_ms = 15 * 1e3
    template = "wss://{}.stt.speech.azure.cn/speech/recognition/conversation/cognitiveservices/v1?initialSilenceTimeoutMs={:d}&language=zh-CN"
    speech_config = speechsdk.SpeechConfig(subscription=speech_key,
            endpoint=template.format(service_region, int(initial_silence_timeout_ms)))
    print("Using endpoint", speech_config.get_property(speechsdk.PropertyId.SpeechServiceConnection_Endpoint))
    audio_config = speechsdk.audio.AudioConfig(filename=filename)
    # Creates a speech recognizer using a file as audio input.
    # The default language is "en-us".
    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
    
    result = speech_recognizer.recognize_once()

    # Check the result
    if result.reason == speechsdk.ResultReason.RecognizedSpeech:
        print("Recognized: {}".format(result.text))
    elif result.reason == speechsdk.ResultReason.NoMatch:
        print("No speech could be recognized: {}".format(result.no_match_details))
    elif result.reason == speechsdk.ResultReason.Canceled:
        cancellation_details = result.cancellation_details
        print("Speech Recognition canceled: {}".format(cancellation_details.reason))
        if cancellation_details.reason == speechsdk.CancellationReason.Error:
            print("Error details: {}".format(cancellation_details.error_details))


speech_recognize_once_from_file_with_custom_endpoint_parameters()

須要注意的是，若是咱們使用SDK識別麥克風中的語音，則將

speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)

修改成以下便可（去掉audio_config參數）：

speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

公衆號連接：https://mp.weixin.qq.com/s/NA9kQsVDfzTXEqHMTdDExA

語雀地址：https://www.yuque.com/seanyu/azure/blwb5i