Robust Hearing-Impaired Speaker Recognition from Speech using Deep Learning Networks in Native

[摘要] Several research works in speaker recognition have grown recently due to its tremendous applications in security,criminal investigations and in other major fields. Identification of a speaker is represented by the way they speak, and not on thespoken words. Hence the identification of hearing-impaired speakers from their speech is a challenging task since their speech ishighly distorted. In this paper, a new task has been introduced in recognizing Hearing Impaired (HI) speakers using speech as abiometric in native language Tamil. Though their speech is very hard to get recognized even by their parents and teachers, ourproposed system accurately identifies them by adapting enhancement of their speeches. Due to the huge variety in their utterances,instead of applying the spectrogram of raw speech, Mel Frequency Cepstral Coefficient features are derived from speech and it isapplied as spectrogram to Convolutional Neural Network (CNN), which is not necessary for ordinary speakers. In the proposedsystem of recognizing HI speakers, is used as a modelling technique to assess the performance of the system and this deep learningnetwork provides 80% accuracy and the system is less complex. Auto Associative Neural Network (AANN) is used as a modellingtechnique and performance of AANN is only 9% accurate and it is found that CNN performs better than AANN for recognizing HIspeakers. Hence this system is very much useful for the biometric system and other security related applications for hearing impairedspeakers.

[学科分类] 计算机科学（综合）

[关键词] Speaker recognition;voice impaired;energy;deep learning based convolutional neural network;mel frequency cepstralcoefficient;Auto associative neural network;back propagation algorithm