Language depth neural network-based language recognition method

Abstract

The invention relates to a language depth neural network-based language recognition method. The method includes the following steps that: S11, biorthogonal wavelet transformation is adopted to filterinputted speech information; S12, the Mel frequency cepstrum coefficient is adopted to extract to a feature sequence formed by key feature parameters reflecting speech signal features; S13, the feature parameters of a training speech library are adopted to train an acoustic model; S14, the feature parameters of a text database are adopted to a train language model; S15, a decoder is established, as for inputted speech signals, a recognition network is established according to the trained HMM acoustic model, the language model, and a dictionary; and S16, the decoder retrieves words matched withto-be-recognized speech feature parameters in the text library according to the step S15, and judges front and behind commonly used words corresponding to the words, and sorting is performed according to grammars and speech recognized in the step S14, and finally the speech signals are converted into text information. The method of the invention has the advantages of high recognition efficiency and accurate voice conversion.

Description

technical field [0001] The invention belongs to the technical field of language recognition methods, and in particular relates to a language recognition method based on a language deep neural network. Background technique [0002] Over the past few years, with the continuous development and progress of science and technology, when people take notes, they have evolved from the initial paper records to the current use of electronic products for recording, and most of the recording methods using list products are recorded by typing or recording method, and then it is the method of recording in time, and the recording needs to be converted into text form for storage in the future. This recording method undoubtedly creates a workload for the recorder. Therefore, there has been a recording method that directly converts speech into text at present, and its specific method is to directly convert speech into textual information, and then store the textual information. However, when p...

AI Technical Summary

Problems solved by technology

[0002] Over the past few years, with the continuous development and progress of science and technology, when people take notes, they have evolved from the initial paper records to the current use of electronic products for recording, and most of the recording methods using list products are recorded by typing or recording method, and then it is the way of recording in time, and the recording needs to be converted into text form for storage in the future. This recording method undoubtedly creates a workload for the recorder

Therefore, there has been a recording method that directly converts speech into text at present, and its specific method is to directly convert speech into textual information, and then store the textual information. However, when performing speech conversion at present, when carrying out speech information input, Due to the influence of factors such as the speaker's surrounding environment, the input voice information is often noisy, which leads to inaccurate conversion when converting the recognized voice to text information

Images