Speech recognition method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of speech recognition, in particular to a speech recognition method and device, electronic equipment and a storage medium, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic and auxiliary driving and are used for efficiently and accurately realizing speech recognition of multiple dialect target languages. The method comprises the following steps: acquiring to-be-recognized voice data of a target language; extracting voice acoustic features corresponding to each frame of voice data in the to-be-recognized voice data; performing deep feature extraction on the voice acoustic features to obtain corresponding dialect embedding features; encoding the voice acoustic features to obtain corresponding acoustic encoding features; and based on the dialect embedding feature and the acoustic coding feature, performing dialect speech recognition on the to-be-recognized speech data to obtain target text information and a target dialect category corresponding to the to-be-recognized speech data. According to the method, the dialect embedding feature and the acoustic coding feature are combined for comprehensive learning, so that speech recognition for recognizing various dialects can be efficiently and accurately realized.

Description

technical field [0001] The present application relates to the technical field of voice recognition, and in particular to a voice recognition method, device, electronic equipment and storage medium. Background technique [0002] With the rapid development of science and technology, related services based on speech recognition technology have been widely used in people's daily life and work, such as smart speakers and vehicle systems. [0003] In related technologies, the research work on speech recognition is mainly concentrated on some common languages ​​with relatively rich data resources, and the amount of speech data gradually breaks through tens of thousands or even hundreds of thousands of hours. However, speech recognition for target languages ​​with few data resources (such as Tibetan) is limited by data resources and the scope of language dissemination, and there are few researches on speech recognition for target languages. [0004] In the traditional modeling meth...

AI Technical Summary

Problems solved by technology

However, speech recognition for target languages ​​with few data resources (such as Tibetan) is limited by the scope of data resources and language dissemination, and there are few researches on speech recognition for target languages

[0004] In the traditional modeling method, modules such as acoustic model, pronunciation dictionary, and language model need to be constructed separately. Due to the scarcity of corpus resources in the target language, it is difficult to record a large amount of speech data in the target language, resulting in a small corpus, difficult construction of a pronunciation dictionary, and related research. in a single dialect

In addition, the coverage and balance of pronunciation phenomena are low, which makes the recognition rate of the acoustic model obtained by corpus training also low.

Images