Title :
A deep neural network based approach to mandarin consonant/vowel separation
Author :
Yen-Teh Liu ; Yu Tsao ; Chang, Ronald Y.
Author_Institution :
Res. Center for Inf. Technol. Innovation, Taipei, Taiwan
Abstract :
In this paper, we study the problem of Mandarin consonant/vowel separation which is an integral part of many Mandarin speech applications. We propose a deep neural network (DNN) based approach and compare its performance with the support vector machine (SVM) method. Our results demonstrate an improved separation performance yielded by the proposed method, especially on consonant identification.
Keywords :
neural nets; speech processing; support vector machines; DNN based approach; Mandarin consonant separation; Mandarin speech applications; SVM method; consonant identification; deep neural network based approach; support vector machine method; vowel separation; Auditory system; Feature extraction; Neural networks; Speech; Speech processing; Support vector machines; Training;
Conference_Titel :
Consumer Electronics - Taiwan (ICCE-TW), 2015 IEEE International Conference on
Conference_Location :
Taipei
DOI :
10.1109/ICCE-TW.2015.7216923
