Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Time-Contrastive Learning Based Deep Bottleneck Features for Text-Dependent Speaker Verification

By: 
Achintya Kumar Sarkar; Zheng-Hua Tan; Hao Tang; Suwon Shon; James Glass

There are a number of studies about extraction of bottleneck (BN) features from deep neural networks (DNNs) trained to discriminate speakers, pass-phrases, and triphone states for improving the performance of text-dependent speaker verification (TD-SV). However, a moderate success has been achieved. A recent study presented a time contrastive learning (TCL) concept to explore the non-stationarity of brain signals for classification of brain states. Speech signals have similar non-stationarity property, and TCL further has the advantage of having no need for labeled data. We therefore present a TCL based BN feature extraction method. The method uniformly partitions each speech utterance in a training dataset into a predefined number of multi-frame segments. Each segment in an utterance corresponds to one class, and class labels are shared across utterances. DNNs are then trained to discriminate all speech frames among the classes to exploit the temporal structure of speech. In addition, we propose a segment-based unsupervised clustering algorithm to re-assign class labels to the segments. TD-SV experiments were conducted on the RedDots challenge database. The TCL-DNNs were trained using speech data of fixed pass-phrases that were excluded from the TD-SV evaluation set, so the learned features can be considered phrase-independent. We compare the performance of the proposed TCL BN feature with those of short-time cepstral features and BN features extracted from DNNs discriminating speakers, pass-phrases, speaker+pass-phrase, as well as monophones whose labels and boundaries are generated by three different automatic speech recognition (ASR) systems. Experimental results show that the proposed TCL-BN outperforms cepstral features and speaker+pass-phrase discriminant BN features, and its performance is on par with those of ASR derived BN features. Moreover, the clustering method improves the TD-SV performance of TCL-BN and ASR derived BN features with respect to their st...

SPS on Twitter

  • We are happy to welcome Prof. Jiebo Luo as the new Editor-in-Chief of IEEE Transactions on Multimedia beginning in… https://t.co/9ZgBrgkFXv
  • wants your talents! Our tenure-track position in engineering applications of information and data science a… https://t.co/QrqTAFGlyM
  • If you’re missing out on , don’t worry - we’ll be tweeting all week long. Follow along with us to see the action!

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar