Zobrazeno 1 - 8 of 8 pro vyhledávání: '"Alexey Prudnikov"'
2
Acoustic Modeling in the STC Keyword Search System for OpenKWS 2016 Evaluation
Autor: Ivan Medennikov, Natalia A. Tomashenko, Valentin Mendelev, Yuri Y. Khokhlov, Alexey Prudnikov, Alexander Zatvornitskiy, Aleksei Romanenko, Maxim Korenevsky
Publikováno v: Speech and Computer ISBN: 9783319664286
SPECOM
This paper describes in detail the acoustic modeling part of the keyword search system developed in the Speech Technology Center (STC) for the OpenKWS 2016 evaluation. The key idea was to utilize diversity of both sound representations and acoustic m
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::69237f28e8ac6b08f3c4094a5ee9a72c
https://doi.org/10.1007/978-3-319-66429-3_7
Zobrazit plný text záznamu
4
Advances in STC Russian Spontaneous Speech Recognition System
Autor: Alexey Prudnikov, Ivan Medennikov
Publikováno v: Speech and Computer ISBN: 9783319439570
SPECOM
In this paper we present the latest improvements to the Russian spontaneous speech recognition system developed in Speech Technology Center (STC). Significant word error rate (WER) reduction was obtained by applying hypothesis rescoring with sophisti
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b975bdc70c6fa27b4b64df4c4c554fbc
https://doi.org/10.1007/978-3-319-43958-7_13
Zobrazit plný text záznamu
5
Training Maxout Neural Networks for Speech Recognition Tasks
Autor: Maxim Korenevsky, Alexey Prudnikov
Publikováno v: Text, Speech, and Dialogue ISBN: 9783319455099
TSD
The topic of the paper is the training of deep neural networks which use tunable piecewise-linear activation functions called “maxout” for speech recognition tasks. Maxout networks are compared to the conventional fully-connected DNNs in case of
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::19147a2b4184ad6ef1f316b050190fa8
https://doi.org/10.1007/978-3-319-45510-5_51
Zobrazit plný text záznamu
6
Adaptive beamforming and adaptive training of DNN acoustic models for enhanced multichannel noisy speech recognition
Autor: Alexey Prudnikov, Maxim Korenevsky, Sergei Aleinik
Publikováno v: ASRU
This paper describes our contribution to the development of an ASR system for the CHiME 2015 Challenge. We applied a new adaptive beamforming method of multichannel alignment for enhancing speech recorded with six microphones. Then we trained an effe
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9e38a71cd1d9b98378ea943a075ed27a
https://doi.org/10.1109/asru.2015.7404823
Zobrazit plný text záznamu
7
Improving Acoustic Models for Russian Spontaneous Speech Recognition
Autor: Alexey Prudnikov, Maxim Korenevsky, Valentin Mendelev, Ivan Medennikov, Yuri Y. Khokhlov
Publikováno v: Speech and Computer ISBN: 9783319231310
SPECOM
The aim of the paper is to investigate the ways to improve acoustic models for Russian spontaneous speech recognition. We applied the main steps of the Kaldi Switchboard recipe to a Russian dataset but obtained low accuracy with respect to the result
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::fab883437735db2b5238236f6dde0c9e
https://doi.org/10.1007/978-3-319-23132-7_29
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje