Speech recognition method based on speed difference of voice unit and system thereof

Abstract

The present invention relates to a speech recognition method based on the speed difference of the voice unit, comprising: preprocessing an input voice; extracting acoustics characteristics of the voice; according to the acoustics model trained in advance and the extracted acoustics characteristics, decoding the voice to obtain a plurality of candidate recognition results, wherein, each of the candidate recognition results possesses an acoustics score and a section length of the voice units contained by the voice; based on the section length of the voice units contained by the voice, calculating the speed difference of the voice unit for each of the candidate recognition results; based on the speed difference of the voice unit and the acoustics score, calculating a comprehensive score for the candidate recognition result; and selecting the candidate recognition result with the highest comprehensive score from the plurality of candidate recognition results as the final recognition result of the voice. In addition, the present invention also provides a corresponding speech recognition system.

Description

technical field [0001] The present invention relates to speech recognition technology, in particular, to a speech recognition method and a corresponding speech recognition system based on differences in speech rates of speech units. Background technique [0002] Generally, the speech recognition process may include preprocessing of speech signals, extraction of acoustic features, search and decoding, and so on. When performing speech recognition, the input speech signal is firstly preprocessed, including pre-filtering, sampling and quantization, windowing and framing, endpoint detection, pre-emphasis, etc. Then, feature extraction is performed on the preprocessed speech signal to obtain acoustic features such as linear prediction coefficient LPC, cepstral coefficient CEP, Mel cepstral coefficient MFCC and perceptual linear prediction PLP. According to the obtained acoustic features and the pre-trained acoustic model, a search strategy such as the Viterbi algorithm is used t...

AI Technical Summary

Problems solved by technology

[0009] Another segment length normalization method is to use the segment length of the previous speech unit to normalize the segment length of the current speech unit. However, in this method, it is necessary to pre-calculate and store all possible normalizations of the two context speech units. A long model, so the memory consumption is large

Images