DocumentCode
478485
Title
Non-Native Speaker Identity Verification Based on Speech
Author
Wei, Hong ; Yang, Jian
Author_Institution
Sch. of Inf. Sci. & Technol., Yunnan Univ., Kunming
Volume
6
fYear
2008
fDate
18-20 Oct. 2008
Firstpage
59
Lastpage
62
Abstract
Speaker identity verification is an useful biometric recognition approach. Native speaker verification has achieved some better effects. But non-native speaker verification remains a challenging task because of wide varieties of non-native accents. Based on two speech corpus, one native speech corpus and one non-native corpus, by means of speaker adaptation. Combined with traditional speaker verification and connected digits continuous speech recognition techniques, non-native speaker identity verification experiments are performed. The combined judging strategy is proved to be more effective by the final experimental results.
Keywords
biometrics (access control); speaker recognition; speech processing; biometric recognition approach; connected digits continuous speech recognition techniques; nonnative speaker identity verification; speaker adaptation; Biometrics; Fingerprint recognition; Hidden Markov models; Information science; Iris; National security; Natural languages; Speaker recognition; Speech recognition; Stability; Connected Digits Speech Recognition; HMM; Non-native Speaker; Speaker Adaptation; Speaker Verification;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Computation, 2008. ICNC '08. Fourth International Conference on
Conference_Location
Jinan
Print_ISBN
978-0-7695-3304-9
Type
conf
DOI
10.1109/ICNC.2008.574
Filename
4667803
Link To Document