转录多通道音频

本页面介绍了如何使用 Speech-to-Text 转录包含多个通道的音频文件。多通道识别适用于 Speech-to-Text 支持的大多数(但不是全部)音频编码。如需了解每种编码类型的音频文件中识别出的通道数量,请参阅 audioChannelCount

通常情况下,对于录音中出现的每名讲话人,音频数据都会包含一个对应的通道。例如,通过电话交谈的两个人的音频可能包含两个通道,分别记录通话双方的线路。

要转录包含多个通道的音频数据,您必须在发送给 Speech-to-Text API 的请求中提供通道数量。在您的请求中,将 audioChannelCount 字段设置为音频中的通道数量即可。

在您发送包含多个通道的请求后,Speech-to-Text 会向您返回标识音频中不同通道的结果,并使用 channelTag 字段标记每个结果的替代项。

以下代码示例展示了如何转录包含多个通道的音频。

协议

如需了解完整的详细信息,请参阅 speech:recognize API 端点。

如需执行同步语音识别,请发出 POST 请求并提供相应的请求正文。以下示例展示了一个使用 curl 发出的 POST 请求。该示例使用通过 Google Cloud Cloud SDK 为项目设置的服务帐号的访问令牌。如需了解有关安装 Cloud SDK、建立项目和服务帐号以及获取访问令牌的说明,请参阅快速入门

以下示例展示了如何使用 curl 发送 POST 请求,其中请求正文指定了音频样本上存在的通道数量。

curl -X POST -H "Authorization: Bearer $(gcloud auth application-default print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     --data '{
    "config": {
        "encoding": "LINEAR16",
        "languageCode": "en-US",
        "audioChannelCount": 2,
        "enableSeparateRecognitionPerChannel": true
    },
    "audio": {
        "uri": "gs://cloud-samples-tests/speech/commercial_stereo.wav"
    }
}' "https://speech.googleapis.com/v1/speech:recognize" > multi-channel.txt

如果请求成功,服务器将返回一个 200 OK HTTP 状态代码以及 JSON 格式的响应(该响应会保存到名为 multi-channel.txt 的文件中)。

{
  "results": [
    {
      "alternatives": [
        {
          "transcript": "hi I'd like to buy a Chromecast I'm always wondering whether you could help me with that",
          "confidence": 0.8991147
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": "certainly which color would you like we have blue black and red",
          "confidence": 0.9408236
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " let's go with the black one",
          "confidence": 0.98783094
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " would you like the new Chromecast Ultra model or the regular Chromecast",
          "confidence": 0.9573053
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " regular Chromecast is fine thank you",
          "confidence": 0.9671048
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " okay sure would you like to ship it regular or Express",
          "confidence": 0.9544821
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " express please",
          "confidence": 0.9487205
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " terrific it's on the way thank you",
          "confidence": 0.97655964
        }
      ],
      "channelTag": 2,
      "languageCode": "en-us"
    },
    {
      "alternatives": [
        {
          "transcript": " thank you very much bye",
          "confidence": 0.9735077
        }
      ],
      "channelTag": 1,
      "languageCode": "en-us"
    }
  ]
}

Go


// transcribeMultichannel generates a transcript from a multichannel speech file and tags the speech from each channel.
func transcribeMultichannel(w io.Writer, path string) error {
	ctx := context.Background()

	client, err := speech.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %v", err)
	}
	defer client.Close()

	data, err := ioutil.ReadFile(path)
	if err != nil {
		return fmt.Errorf("ReadFile: %v", err)
	}

	resp, err := client.Recognize(ctx, &speechpb.RecognizeRequest{
		Config: &speechpb.RecognitionConfig{
			Encoding:                            speechpb.RecognitionConfig_LINEAR16,
			SampleRateHertz:                     44100,
			LanguageCode:                        "en-US",
			AudioChannelCount:                   2,
			EnableSeparateRecognitionPerChannel: true,
		},
		Audio: &speechpb.RecognitionAudio{
			AudioSource: &speechpb.RecognitionAudio_Content{Content: data},
		},
	})
	if err != nil {
		return fmt.Errorf("Recognize: %v", err)
	}

	// Print the results.
	for _, result := range resp.Results {
		for _, alt := range result.Alternatives {
			fmt.Fprintf(w, "Channel %v: %v\n", result.ChannelTag, alt.Transcript)
		}
	}
	return nil
}

Java

/**
 * Transcribe a remote audio file with multi-channel recognition
 *
 * @param gcsUri the path to the audio file
 */
public static void transcribeMultiChannelGcs(String gcsUri) throws Exception {

  try (SpeechClient speechClient = SpeechClient.create()) {

    // Configure request to enable multiple channels
    RecognitionConfig config =
        RecognitionConfig.newBuilder()
            .setEncoding(AudioEncoding.LINEAR16)
            .setLanguageCode("en-US")
            .setSampleRateHertz(44100)
            .setAudioChannelCount(2)
            .setEnableSeparateRecognitionPerChannel(true)
            .build();

    // Set the remote path for the audio file
    RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(gcsUri).build();

    // Use non-blocking call for getting file transcription
    OperationFuture<LongRunningRecognizeResponse, LongRunningRecognizeMetadata> response =
        speechClient.longRunningRecognizeAsync(config, audio);

    while (!response.isDone()) {
      System.out.println("Waiting for response...");
      Thread.sleep(10000);
    }
    // Just print the first result here.
    for (SpeechRecognitionResult result : response.get().getResultsList()) {

      // There can be several alternative transcripts for a given chunk of speech. Just use the
      // first (most likely) one here.
      SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);

      // Print out the result
      System.out.printf("Transcript : %s\n", alternative.getTranscript());
      System.out.printf("Channel Tag : %s\n", result.getChannelTag());
    }
  }
}

Node.js

const speech = require('@google-cloud/speech').v1;

// Creates a client
const client = new speech.SpeechClient();

const config = {
  encoding: 'LINEAR16',
  languageCode: 'en-US',
  audioChannelCount: 2,
  enableSeparateRecognitionPerChannel: true,
};

const audio = {
  uri: gcsUri,
};

const request = {
  config: config,
  audio: audio,
};

const [response] = await client.recognize(request);
const transcription = response.results
  .map(
    result =>
      ` Channel Tag: ${result.channelTag} ${result.alternatives[0].transcript}`
  )
  .join('\n');
console.log(`Transcription: \n${transcription}`);

Python

from google.cloud import speech

client = speech.SpeechClient()

with open(speech_file, "rb") as audio_file:
    content = audio_file.read()

audio = speech.RecognitionAudio(content=content)

config = speech.RecognitionConfig(
    encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
    sample_rate_hertz=44100,
    language_code="en-US",
    audio_channel_count=2,
    enable_separate_recognition_per_channel=True,
)

response = client.recognize(config=config, audio=audio)

for i, result in enumerate(response.results):
    alternative = result.alternatives[0]
    print("-" * 20)
    print("First alternative of result {}".format(i))
    print(u"Transcript: {}".format(alternative.transcript))
    print(u"Channel Tag: {}".format(result.channel_tag))

其他语言

C#:请按照客户端库页面上的 C# 设置说明操作,然后访问 .NET 的 Speech-to-Text 参考文档

PHP:请按照客户端库页面上的 PHP 设置说明 操作,然后访问 PHP 的 Speech-to-Text 参考文档

Ruby:请按照客户端库页面上的 Ruby 设置说明操作,然后访问 Ruby 的 Speech-to-Text 参考文档