演讲者对语音的语言化 [英] Speaker Diarization in Speech to Text

问题描述

我正在尝试语音到文本服务，我想分别转录多人说的句子。

I am trying Speech to Text service and I want to transcribe the sentences spoken by multiple people separately. 

Azure Cognitive语音到文本服务是否提供此功能？ ？

Does Azure Cognitive speech to text service offer this feature??

推荐答案

Hello Dheeraj，

Hello Dheeraj,

是的，您可以使用  对话转录服务 结合了实时语音识别，说话人识别和
diarization。 需要具有特定几何配置的圆形七麦克风阵列。有关规格和设计的详细信息，请参阅
Microsoft Speech Device SDK Microphone 。要了解更多信息或购买开发套件，请参阅
获取Microsoft语音设备SDK 。

Yes, you can use conversation transcription service that combines real-time speech recognition, speaker identification, and diarization.  A circular seven microphone array with specific geometry configuration is required. For specification and design details, see Microsoft Speech Device SDK Microphone. To learn more or purchase a development kit, see Get Microsoft Speech Device SDK.

对话转录目前可在"en-US"中找到。和"zh-CN"在以下地区：centralus和eastasia。这是

链接用语音SDK转录多方参与者的对话，供您参考。

Conversation Transcription is currently available in "en-US" and "zh-CN" in the following regions: centralus and eastasia. Here is the link to transcribe multi-participant conversations with speech SDK for your reference.

这篇关于演讲者对语音的语言化的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！