Pronunciation dictionary generation method and word speech recognition method and device

Abstract

The embodiment of the invention provides a pronunciation dictionary generation method, a word speech recognition method, a word speech recognition device, electronic equipment and a storage medium. The pronunciation dictionary generation method comprises the steps: acquiring a training corpus which comprises a first phoneme sequence corresponding to one or more notional words, and a pronunciationrule corresponding to the language to which the notional word belongs; constructing one or more function words according to the pronunciation rule, wherein the function words have corresponding a second phoneme sequence; and generating a pronunciation dictionary by adopting the notional words, the first phoneme sequence, the function words and the second phoneme sequence. According to the method,the data volume of the pronunciation dictionary is ensured, and a pronunciation dictionary with sufficient words can be generated by using training corpora less than that for training a common pronunciation dictionary when facing unknown small languages, so that pronunciation of the to-be-identified words is accurately identified by increasing little corpora with large corpora.

Description

technical field [0001] The invention relates to the field of speech recognition, in particular to a method for generating a pronunciation dictionary and a device for generating a pronunciation dictionary, a method for recognizing a word and a device for recognizing a word, electronic equipment, and a storage medium. Background technique [0002] Pronunciation dictionary is one of the important links of speech recognition and an integral part of it. It represents the pronunciation of a word (generally in units of words) corresponding to a phoneme. It is generally the standard International Phonetic Alphabet, but in fact the phonetic symbol is just a symbol. , is a representation method, in fact, it only needs to ensure that the same pronunciation has the same symbol. For unknown small languages, the construction of pronunciation dictionaries is generally divided into two methods: G2P (grapheme-to-phoneme, grapheme-to-phoneme) and the method of direct construction according to...

AI Technical Summary

Problems solved by technology

However, the training of the neural network requires a large amount of data support, and the effect is not ideal when the amount of data is small.

In addition, the phonetic notation of a large number of pronunciation dictionaries found may not be uniform. Although the notation of pronunciation dictionaries is generally the International Phonetic Alphabet, there may also be other methods of notation. Pronunciation dictionaries obtained from different channels may have different notations. affect the accuracy

Therefore, for small languages, the existing pronunciation dictionaries have a small number of word samples. In this case, it is difficult to realize more and more word recognition, and the limitations of G2P technology are revealed.

Images