Loading...

i-vector/HMM based text-dependent speaker verification system for RedDots challenge

Zeinali, H ; Sharif University of Technology | 2016

719 Viewed
  1. Type of Document: Article
  2. DOI: 10.21437/Interspeech.2016-1174
  3. Publisher: International Speech and Communication Association , 2016
  4. Abstract:
  5. Recently, a new data collection was initiated within the RedDots project in order to evaluate text-dependent and text-prompted speaker recognition technology on data from a wider speaker population and with more realistic noise, channel and phonetic variability. This paper analyses our systems built for RedDots challenge-the effort to collect and compare the initial results on this new evaluation data set obtained at different sites. We use our recently introduced HMM based i-vector approach, where, instead of the traditional GMM, a set of phone specific HMMs is used to collect the sufficient statistics for i-vector extraction. Our systems are trained in a completely phraseindependent way on the data from RSR2015 and Libri speech databases. We compare systems making use of standard cepstral features and their combination with neural network based bottle-neck features. The best results are obtained with a scorelevel fusion of such systems
  6. Keywords:
  7. HMM ; I-vector ; RedDots challenge ; Text-dependent speaker verification ; Bottles ; Character recognition ; Population statistics ; Speech communication ; Speech processing ; Vectors ; Cepstral features ; RedDots challenge ; Score-level fusion ; Speaker recognition ; Speaker verification ; Speaker verification system ; Sufficient statistics ; Speech recognition
  8. Source: 17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016, 8 September 2016 through 16 September 2016 ; Volume 08-12-September-2016 , 2016 , Pages 440-444 ; 2308457X (ISSN)
  9. URL: http://www.isca-speech.org/archive/Interspeech_2016/abstracts/1174.html