Speech endpoint detection method, device and equipment and storage medium

Abstract

The invention provides a speech endpoint detection method, device and equipment and a storage medium. The speech endpoint detection method comprises the steps of extracting audio features used for determining the dynamic detection interval from audio data to be detected to serve as dynamic detection interval features; determining attributes of the audio data to be detected through a pre-established audio attribute determination model according to the dynamic detection interval features, and determining the dynamic detection interval of the audio data to be detected through a pre-established dynamic detection interval model according to the dynamic detection interval features; and determining the speech endpoint of the audio data to be detected based on the attributes and the dynamic detection interval of the audio data to be detected. The speech endpoint detection method provided by the invention realizes speech endpoint detection based on the dynamic detection interval, has a good detection effect and is excellent in user experience.

Description

technical field [0001] The present application relates to the technical field of speech recognition, and in particular to a speech endpoint detection method, device, equipment and storage medium. Background technique [0002] Speech recognition is an important part of human-computer interaction. Speech recognition refers to the automatic conversion of speech into corresponding text through methods such as machine learning. [0003] With the advancement of artificial intelligence wave after wave, speech recognition, as an important field of artificial intelligence, is developing by leaps and bounds. Although speech recognition technology has reached the commercial stage, its recognition effect is still not satisfactory. One of the important reasons for this is that the detection effect of the current speech endpoint detection scheme is not good. [0004] Since speech endpoint detection is the front-end processing process of speech recognition, if the effect of speech endpoin...

AI Technical Summary

Problems solved by technology

Although speech recognition technology has reached the commercial stage, its recognition effect is still not ideal. One of the important reasons is that the detection effect of the current speech endpoint detection scheme is not good.

[0004] Since speech endpoint detection is the front-end processing process of speech recognition, if the effect of speech endpoint detection is not good, it will inevitably lead to poor effect of subsequent speech recognition. Therefore, it is urgent to provide a speech endpoint detection solution with better detection effect

Images