Sequence summarizing neural network for speaker adaptation

Karel Veselý; Shinji Watanabe; Katerina Zmolíková; Martin Karafiát; Lukás Burget; Jan Honza Cernocký

ICASSP 2016accepted0 citations

Sequence summarizing neural network for speaker adaptation

Karel Veselý, Shinji Watanabe, Katerina Zmolíková, Martin Karafiát, Lukás Burget, Jan Honza Cernocký

Abstract

In this paper, we propose a DNN adaptation technique, where the i-vector extractor is replaced by a Sequence Summarizing Neural Network (SSNN). Similarly to i-vector extractor, the SSNN produces a "summary vector", representing an acoustic summary of an utterance. Such vector is then appended to the input of main network, while both networks are trained together optimizing single loss function. Both the i-vector and SSNN speaker adaptation methods are compared on AMI meeting data. The results show comparable performance of both techniques on FBANK system with frame-classification training. Moreover, appending both the i-vector and "summary vector" to the FBANK features leads to additional improvement comparable to the performance of FMLLR adapted DNN system.

BibTeX

@inproceedings{icassp2016_sequencesummariz,
  title = {Sequence summarizing neural network for speaker adaptation},
  author = {Karel Veselý and Shinji Watanabe and Katerina Zmolíková and Martin Karafiát and Lukás Burget and Jan Honza Cernocký},
  booktitle = {ICASSP 2016},
  year = {2016}
}