Microsoft 认知服务 - 说话人识别 API - 识别 - 错误答案

【问题标题】：Microsoft Cognitive Services - Speaker Recognition API - Identification - errorMicrosoft 认知服务 - 说话人识别 API - 识别 - 错误
【发布时间】：2020-06-16 21:57:06
【问题描述】：

在这个API中我已经成功创建了Identification Profile，也成功创建了注册并检查了操作状态，收到成功注册。

现在我正在尝试识别说话者，但我得到了一个错误： b'{"error":{"code":"BadRequest","message":"Audio too long"}}' b'{"error":{"code":"BadRequest","message":"音频太短"}}'

我尝试了各种不同大小的语音样本，例如 5-Second、10-Second、15-Second、30-Second、40-Second、80-Second。 还提到了 IdentificationProfileIds 应该是字符串（如何做）

对于录音，我使用的是 $rec -c 1 -r 16000 -b 16 xa.wav

但仍然出现相同的错误，我希望我的代码中可能存在一些问题。请帮我如果您能提供演讲者 - 识别代码，那将非常有帮助

import http.client, urllib.request, urllib.parse, urllib.error, base64
subscription_key = 'XXXXXXXXXXXXXXXXXXXX'

headers = {
    # Request headers
    'Content-Type': 'multipart/form-data',
    'Ocp-Apim-Subscription-Key': subscription_key,
}

params = urllib.parse.urlencode({
    # Request parameters
    # 'shortAudio': 'false',
    "identificationProfileIds":"080d22d6-917e-487f-a553-fb13a0575067",
 })


try:
    conn = http.client.HTTPSConnection('speaker-recognition-api.cognitiveservices.azure.com')
    body = open('xa.wav','rb')
    #aud = base64.b64encode(body.read())
    print(body)
    conn.request("POST", "/spid/v1.0/identify?identificationProfileIds=080d22d6-917e-487f-a553-fb13a0575067&%s" % params, body, headers)
    response = conn.getresponse()
    print(response)
    data = response.read()
    print(data)
    conn.close()
except Exception as e:
    print("[Errno {0}] {1}".format(e.errno, e.strerror))

【问题讨论】：

标签： python microsoft-cognitive voice-recognition azure-cognitive-services

【解决方案1】：

您可以尝试使用 Speaker Recognition Python 示例应用程序作为开始并从那里开始工作，您可以在 GitHub 上通过 Microsoft here 公开获取该应用程序

你必须在各自的文件中设置你的值，特别是寻找IdentifyFile.py

import IdentificationServiceHttpClientHelper
import sys

def identify_file(subscription_key, file_path, force_short_audio, profile_ids):
    """Identify an audio file on the server.

    Arguments:
    subscription_key -- the subscription key string
    file_path -- the audio file path for identification
    profile_ids -- an array of test profile IDs strings
    force_short_audio -- waive the recommended minimum audio limit needed for enrollment
    """
    helper = IdentificationServiceHttpClientHelper.IdentificationServiceHttpClientHelper(
        subscription_key)

    identification_response = helper.identify_file(
        file_path, profile_ids,
        force_short_audio.lower() == "true")

    print('Identified Speaker = {0}'.format(identification_response.get_identified_profile_id()))
    print('Confidence = {0}'.format(identification_response.get_confidence()))

if __name__ == "__main__":
    if len(sys.argv) < 5:
        print('Usage: python IdentifyFile.py <subscription_key> <identification_file_path>'
              ' <profile_ids>...')
        print('\t<subscription_key> is the subscription key for the service')
        print('\t<identification_file_path> is the audio file path for identification')
        print('\t<force_short_audio> True/False waives the recommended minimum audio limit needed '
              'for enrollment')
        print('\t<profile_ids> the profile IDs for the profiles to identify the audio from.')
        sys.exit('Error: Incorrect Usage.')

    identify_file(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4:])

【讨论】：