A method and device for language recognition and classification based on denoising autoencoder

Abstract

The present invention provides a method for language recognition and classification based on a noise-reducing automatic encoder, which includes: step 1) extracting the speech signal to be recognized from the speech segment to be recognized, and obtaining the underlying acoustic features; step 2) obtaining from step 1) Extract the original i‑vector of the underlying acoustic features; step 3) calculate and obtain the phoneme vector p c (u); step 4) combine the original i‑vector with the phoneme vector p c (u) splicing, and inputting it into the DAE-based i-vector compensation network to obtain the compensated i-vector; step 5) the original i-vector obtained in step 2) and the compensated i-vector obtained in step 4) respectively Input the i‑vector to the pre-trained logistic regression classifier to obtain the corresponding score vector; step 6) perform score fusion on the corresponding score vector obtained in step 5) to obtain the final score vector, and then obtain the probability of each language category , and determine the language category it belongs to.

Description

technical field [0001] The invention belongs to the technical field of language recognition, and in particular relates to a method and device for language recognition and classification based on a noise reduction automatic encoder. Background technique [0002] Language Identification (LID) refers to the process of automatically determining a given speech segment, extracting the difference information of each language from the speech signal of the speech segment, and judging the language type. Language recognition technology has important applications in multilingual speech processing, such as spoken language translation systems, multilingual speech recognition systems, speech and text processing, etc. [0003] At present, the traditional language recognition technology includes two methods: the first method is the language recognition technology based on the features of the phoneme layer; among them, the language recognition technology based on the features of the phoneme l...

AI Technical Summary

Problems solved by technology

At present, the existing language recognition system has a high recognition rate when the length of the training speech and the test speech match; however, when the length of the training speech and the test speech do not match, its performance also decreases

The existing language recognition system, for the length mismatch problem, trains the matching models for different lengths of test speech, which greatly increases the complexity of the model

Images