Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Astrid Hagen"'
Autor:
Andrew C. Morris, Astrid Hagen
Publikováno v:
Computer Speech & Language. 19:3-30
In this article we review several successful extensions to the standard hidden-Markov-model/artificial neural network (HMM/ANN) hybrid, which have recently made important contributions to the field of noise robust automatic speech recognition. The fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::65d73d3e6e34a8aa61cbb593af204390
https://doi.org/10.1016/j.csl.2003.12.002
https://doi.org/10.1016/j.csl.2003.12.002
Publikováno v:
Speech Communication. 34:25-40
In this paper we develop different mathematical models in the framework of the multi-stream paradigm for noise robust ASR, and discuss their close relationship with human speech perception. Largely inspired by Fletcher's "product-of-errors" rule in p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5accd5358ee761b8d038eb8be7be83d2
https://doi.org/10.1016/s0167-6393(00)00044-3
https://doi.org/10.1016/s0167-6393(00)00044-3
Autor:
João Neto, Astrid Hagen
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783540404361
PROPOR
PROPOR
In this article, we describe an automatic speech recognizer developed for Portuguese telephone speech. For this, we employed the Portuguese SpeechDat database which will be described in detail, giving its recording conditions, speaker characteristics
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::25efb27784ec7adaab15c6e67c1c4c4e
https://doi.org/10.1007/3-540-45011-4_19
https://doi.org/10.1007/3-540-45011-4_19
Publikováno v:
7th International Conference on Spoken Language Processing (ICSLP 2002).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eb35a946f3745886550142cd5662c868
https://doi.org/10.21437/icslp.2002-36
https://doi.org/10.21437/icslp.2002-36
Autor:
Astrid Hagen
Publikováno v:
Advances in Natural Language Processing ISBN: 9783540438298
PorTAL
PorTAL
This paper summarizes our work carried out over the last four years on multi-band and multi-stream processing as means to achieve robust automatic speech recognition (ASR). Main focused is laid on the "full combination" approach which integrates over
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8993297215da509b1adfbcc2cd8fb22f
https://doi.org/10.1007/3-540-45433-0_27
https://doi.org/10.1007/3-540-45433-0_27
Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR
Autor:
Astrid Hagen, Andrew Morris
In this paper we apply the Full Combination (FC) multi-band approach, which has originally been introduced in the framework of posterior-based HMM/ANN (Hidden Markov Model/Artificial Neural Network) hybrid systems, to systems in which the ANN (or Mul
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3cbb740564638f9e12f7f6b94a6795a6
https://infoscience.epfl.ch/record/82608
https://infoscience.epfl.ch/record/82608
Recently, the advantages of the spectral parameters obtained by frequency filtering (FF) of the logarithmic filter-bank energies (logFBEs) have been reported. These parameters, which are frequency derivatives of the logFBEs, lie in the frequency doma
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::896807cdbda8aab6f545deb54fdfff3c
https://infoscience.epfl.ch/record/82955
https://infoscience.epfl.ch/record/82955
Publikováno v:
2003 IEEE International Conference on Acoustics, Speech & Signal Processing, 2003. Proceedings (ICASSP '03); 2003, pi-xcviii, 98p
Publikováno v:
2003 IEEE Workshop on Automatic Speech Recognition & Understanding (IEEE Cat. No.03EX721); 2003, p94-98, 5p
Publikováno v:
2003 IEEE International Conference on Acoustics, Speech & Signal Processing, 2003. Proceedings (ICASSP '03); 2003, pi-xcviii, 98p