Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Petr Fousek"'
Autor:
Dimitrios Dimitriadis, Petr Fousek
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d0acfbfe85c4b62f83803124c40d2a20
https://doi.org/10.21437/interspeech.2017-166
https://doi.org/10.21437/interspeech.2017-166
Autor:
Jason W. Pelecanos, Dimitrios Dimitriadis, Kenneth Church, Weizhong Zhu, Josef Vopicka, Petr Fousek
Publikováno v:
ICASSP
This paper discusses some challenges and opportunities in developing a speaker diarization system for operation on real world call center telephony data. We contrast some of the differences between a standard data set akin to NIST evaluations and tho
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8bd503bd47dab1ae5d644793dd8315dd
https://doi.org/10.1109/icassp.2017.7953098
https://doi.org/10.1109/icassp.2017.7953098
Publikováno v:
ICASSP
Deep Scattering Network features introduced for image processing have recently proved useful in speech recognition as an alternative to log-mel features for Deep Neural Network (DNN) acoustic models. Scattering features use wavelet decomposition dire
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dc1d9fab1eadcb4aa35679f5289581bc
https://doi.org/10.1109/icassp.2015.7178832
https://doi.org/10.1109/icassp.2015.7178832
Autor:
David Nahamoo, Vijayaditya Peddinti, Petr Fousek, Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran
Publikováno v:
INTERSPEECH
Log-mel filterbank features, which are commonly used features for CNNs, can remove higher-resolution information from the speech signal. A novel technique, known as Deep Scattering Spectrum (DSS), addresses this issue and looks to preserve this infor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f8e0d0685744c65bddafbce169282955
https://doi.org/10.21437/interspeech.2014-225
https://doi.org/10.21437/interspeech.2014-225
Publikováno v:
ICASSP
In this paper, we present new methods for parameterizing the connections of neural networks using sums of direct products. We show that low rank parameterizations of weight matrices are a subset of this set, and explore the theoretical and practical
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0dcafc71bce5c7730967c4eb40f81d31
https://doi.org/10.1109/icassp.2013.6638238
https://doi.org/10.1109/icassp.2013.6638238
Publikováno v:
ICASSP
We present the Factorial Hidden Restricted Boltzmann Machine (FHRBM) for robust speech recognition. Speech and noise are modeled as independent RBMs, and the interaction between them is explicitly modeled to capture how speech and noise combine to ge
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b52954753ebf6434f64f70478c5fbfab
https://doi.org/10.1109/icassp.2012.6288869
https://doi.org/10.1109/icassp.2012.6288869
Publikováno v:
ASRU
In this paper we describe how the model-based noise robustness algorithm for previously unseen noise conditions, Dynamic Noise Adaptation (DNA), can be made robust to matched data, without the need to do any system re-training. The approach is to do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::26e9af76eb96b3ce6f8a8c7b35c37c7a
https://doi.org/10.1109/asru.2011.6163919
https://doi.org/10.1109/asru.2011.6163919
Autor:
Tara N. Sainath, Bhuvana Ramabhadran, Petr Fousek, Petr Novak, Brian Kingsbury, Abdelrahman Mohamed
Publikováno v:
ASRU
To date, there has been limited work in applying Deep Belief Networks (DBNs) for acoustic modeling in LVCSR tasks, with past work using standard speech features. However, a typical LVCSR system makes use of both feature and model-space speaker adapta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6d61db1c764a3a36dab9720cb065a552
https://doi.org/10.1109/asru.2011.6163900
https://doi.org/10.1109/asru.2011.6163900
Publikováno v:
ICASSP
Dynamic noise adaptation (DNA) [1, 2] is a model-based technique for improving automatic speech recognition (ASR) performance in noise. DNA has shown promise on artificially mixed data such as the Aurora II and DNA+Aurora II tasks [1]—significantly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::15264d9e1251b79a991e92a7fc31afa6
https://doi.org/10.1109/icassp.2011.5947377
https://doi.org/10.1109/icassp.2011.5947377