Resonance peak automatic matching method for voiceprint identification

Abstract

The invention provides a resonance peak automatic matching method for voiceprint identification. The method comprises the following steps that: phoneme boundary positions in an inspection material and a sample in the voiceprint identification can be automatically marked through using continuous speech recognition-based forced alignment (FA) technology; as for identical vowel phoneme segments of the inspection material and the sample, whether a current phoneme is a valid analysable phoneme is automatically judged through using fundamental frequencies, resonance peaks and power spectrum density parameters; and deviation ratios of corresponding resonance peak time-frequency areas can be automatically rendered through using a dynamic time warping (DTW) algorithm and are adopted as analysis basis of final manual voiceprint identification. With the resonance peak automatic matching method for the voiceprint identification of the invention adopted, the boundaries of phonemes can be automatically marked, and whether the pronunciation of the phonemes is valid is judged, and therefore, processing efficiency can be greatly improved; and at the same time, an automatic resonance peak deviation alignment algorithm is performed on effective phoneme pairs, and therefore, the accuracy of resonance peak alignment can be improved.

Description

technical field [0001] The invention relates to the technical field of voiceprint identification, in particular to an automatic formant matching method for voiceprint identification. Background technique [0002] Voiceprint identification technology (see literature [1] Beigi, Homayoon. Voice: Technologies and Algorithms for Biometrics Applications [M]. http: / / ieee-elearning.org / course.2010) is an application of voice in judicial identification. Texture recognition technology (see literature [2] X.D.Huang, A.Acero and H.Hon, Spoken Language Processing, Prentice Hall, 2000 and literature [3] L.Rabiner and B.H.Juang, Fundamentals of speech recognition, Prentice Hall PTR, 1993), which means that the appraiser uses scientific technology or specialized knowledge to compare the speech of the sample with the speech of the inspection material, and draws an appraisal conclusion on whether the speaker of the sample and the speaker of the building material are the same. At present, voi...

AI Technical Summary

Problems solved by technology

[0012] 3) Since the vocalization of the human vocal tract has a slow-changing characteristic, and the pronunciation of a single phoneme is affected by the front and rear phonemes, the trend of the formant will also change greatly, and the selected materials and samples for manual comparison may be in the same vocalization stage, which affects the accuracy of judgment

[0019] 1) The voiceprint recognition system is greatly affected by the channel, noise and other phonemes. When the channel of the sample and the inspection material are greatly different, the similarity score given by the system will change greatly;

[0020] 2) The voiceprint recognition system can only give a similarity score, and it needs to set a threshold to give a deterministic judgment result of yes or no. It is difficult to set the threshold in actual identification tasks;

[0021] 3) In order to set a more reliable threshold, multiple sample speaker voices that are similar to the channel, noise, and content of the sample voice are required. In practice, it is difficult to obtain multiple sample voices that meet the requirements, making the voiceprint recognition system give The likelihood score is difficult to use as an evaluation reference for identity determination

Images