End-to-end speech recognition method, electronic device and computer readable storage medium

Abstract

The invention relates to the technical field of speech recognition and discloses an end-to-end speech recognition method. The method includes acquiring a first mixed speech signal of a plurality of speakers and tag sequences as training samples; building an Encoder-Decoder Architecture based neural network model; training the neural network model; acquiring a second mixed speech signal including aplurality of speakers to be recognized; inputting the second mixed speech signal into the trained neural network model to output text information corresponding to each speaker respectively. The invention outputs the pronunciation content corresponding to each speaker respectively for the mixed speech source input formed by the simultaneous vocalization of a plurality of speakers, and does not need to include an obvious speech segmentation stage to generate a plurality of independent outputs from the mono-channel mixed speech, thereby simplifying the speech recognition process and reducing thecomputational load. The invention also discloses an electronic device and a computer-readable storage medium.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to an end-to-end voice recognition method, an electronic device and a computer-readable storage medium. Background technique [0002] Speech recognition, also known as Automatic Speech Recognition (ASR), can convert input speech signals into corresponding text or command output through recognition and understanding, and is an important branch of the development of modern artificial intelligence. With the rapid improvement of computer processing capabilities, speech recognition technology has also been greatly developed. Speech recognition technology can effectively promote the development of voice-activated interaction related fields and greatly facilitate people's lives. It is also increasingly changing human production and life. Way. With the development of voice interaction methods, the requirements for voice recognition technology are getting higher and higher...

AI Technical Summary

Problems solved by technology

[0003] The present invention provides an end-to-end speech recognition method, an electronic device, and a computer-readable storage medium to solve the problem that the existing speech recognition method and system have a large amount of processing for multi-speaker mixed speech input, the process is complicated, and it cannot target Mixing speech source input for direct recognition and outputting multiple independent pronunciation content questions

Images