Android音频文件中的扬声器二分法

时间:2019-12-21 14:56:29

标签: android google-cloud-platform google-cloud-functions speech-recognition google-speech-api

如何在Android中将不同的扬声器与音频文件分开? Google Cloud Speech API? (https://cloud.google.com/speech-to-text/docs/multiple-voices#speech-diarization-java

可能的复本 Speaker Diarization support in Google Speech API

我已经尝试过将Google云语音演示程序转换为文本api,但无法成功进行演示,请从logcat中检查以下错误日志。

代码:

    ALTER PROCEDURE [dbo].[CreateTask]
    @Name        NVARCHAR(50),
    @IsGate   BIT,
    @Condition Varchar(450),
    @Precondition       Varchar(450),
    @Comments       Varchar(450),
    @StartDate       DateTime,
    @EndDate       DateTime,
    @AssignedTo    Nvarchar(450),
    @PhaseId int 
AS
BEGIN
    Insert Into dbo.Tasks (Name, IsGate, Condition, Precondition, Comments, StartDate, EndDate, AssignedTo, PhaseId, InProgress, Finished, Aborted) Values (@Name, @IsGate, @Condition, @Precondition, @Comments, @StartDate, @EndDate, @AssignedTo, @PhaseId, '0', '0', '0')
END

错误日志: https://justpaste.it/1xgz4

接受不同方式实现说话人差异化的帮助和建议。

0 个答案:

没有答案