Conference paper

VESELÝ Karel, WATANABE Shinji, ŽMOLÍKOVÁ Kateřina, KARAFIÁT Martin, BURGET Lukáš and ČERNOCKÝ Jan. Sequence Summarizing Neural Network for Speaker Adaptation. In: Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016. Shanghai: IEEE Signal Processing Society, 2016, pp. 5315-5319. ISBN 978-1-4799-9988-0.
Publication language:english
Original title:Sequence Summarizing Neural Network for Speaker Adaptation
Title (cs):Neuronové sítě shrnující sekvence pro adaptaci na mluvčího
Pages:5315-5319
Proceedings:Proceedings of the 41th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), 2016
Conference:41th IEEE International Conference on Acoustics, Speech and Signal Processing
Place:Shanghai, CN
Year:2016
ISBN:978-1-4799-9988-0
Publisher:IEEE Signal Processing Society
URL:http://www.fit.vutbr.cz/research/groups/speech/publi/2016/vesely_icassp2016_0005315.pdf [PDF]
Files: 
+Type Name Title Size Last modified
iconvesely_icassp2016_0005315.pdf178 KB2016-09-29 18:16:17
^ Select all
With selected:
Keywords
DNN, adaptation, i-vector, sequence summary, SSNN
Annotation
In this paper, we proposed an alternative method to produce DNN adaptation vectors similar to i-vectors. The vectors are computed by the Sequence Summarizing Neural Network and characterize the acoustics in an utterance.
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 frameclassification 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{
   author = {Karel Vesel{\'{y}} and Shinji Watanabe and Kate{\v{r}}ina
	{\v{Z}}mol{\'{i}}kov{\'{a}} and Martin Karafi{\'{a}}t and
	Luk{\'{a}}{\v{s}} Burget and Jan {\v{C}}ernock{\'{y}}},
   title = {Sequence Summarizing Neural Network for Speaker Adaptation},
   pages = {5315--5319},
   booktitle = {Proceedings of the 41th IEEE International Conference on
	Acoustics, Speech and Signal Processing (ICASSP 2016), 2016},
   year = {2016},
   location = {Shanghai, CN},
   publisher = {IEEE Signal Processing Society},
   ISBN = {978-1-4799-9988-0},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11145}
}

Your IPv4 address: 54.146.47.178
Switch to IPv6 connection

DNSSEC [dnssec]