DocumentCode :
3166101
Title :
Artificial stereo data generation for speech feature mapping
Author :
Han, Chang Woo ; Kang, Tae Gyoon ; Kang, Shin Jae ; Sung, June Sig ; Kim, Nam Soo
Author_Institution :
Sch. of Electr. Eng., Seoul Nat. Univ., Seoul, South Korea
fYear :
2012
fDate :
25-30 March 2012
Firstpage :
4897
Lastpage :
4900
Abstract :
Feature mapping technique is widely used to eliminate the mismatch between the training and test conditions of speech recognition. In the feature mapping, a target (mismatched) feature vector sequence is mapped closer to the corresponding reference (matched) feature vector stream. The training of the mapping system is usually carried out based on a set of stereo data which consists of simultaneous recordings obtained in both the reference and target conditions. In this paper, we propose a novel approach to blind parameter estimation which does not require the reference feature vectors. The proposed approach is motivated by the hidden Markov model (HMM)-based speech synthesis algorithm.
Keywords :
hidden Markov models; speech synthesis; HMM-based speech synthesis algorithm; artificial stereo data generation; feature mapping technique; hidden Markov model; reference feature vector stream; speech feature mapping; stereo data; target conditions; Estimation; Hidden Markov models; Speech; Speech processing; Speech recognition; Superluminescent diodes; Vectors; Robust speech recognition; blind estimation; feature mapping;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
ISSN :
1520-6149
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
Type :
conf
DOI :
10.1109/ICASSP.2012.6289017
Filename :
6289017
Link To Document :
بازگشت