Detail publikace

i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge

ZEINALI, H. SAMETI, H. BURGET, L. ČERNOCKÝ, J. MAGHSOODI, N. MATĚJKA, P.

Originální název

i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge

Anglický název

i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

Dokumenty

BibTex


@inproceedings{BUT131018,
  author="Hossein {Zeinali} and Hossein {Sameti} and Lukáš {Burget} and Jan {Černocký} and Nooshin {Maghsoodi} and Pavel {Matějka}",
  title="i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge",
  annote="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.",
  address="International Speech Communication Association",
  booktitle="Proceedings of Interspeech 2016",
  chapter="131018",
  doi="10.21437/Interspeech.2016-1174",
  edition="NEUVEDEN",
  howpublished="online",
  institution="International Speech Communication Association",
  year="2016",
  month="september",
  pages="440--444",
  publisher="International Speech Communication Association",
  type="conference paper"
}