Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Carl Quillen"'
Publikováno v:
EUSIPCO
We present a novel, non-intrusive method that jointly estimates acoustic signal properties associated with the perceptual speech quality, level of reverberation and noise in a speech signal. We explore various machine learning frameworks, consisting
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e9eab1cc574318368ead28b3ced5f436
https://doi.org/10.23919/eusipco47968.2020.9287785
https://doi.org/10.23919/eusipco47968.2020.9287785
When a sufficiently large far-field training data is presented, jointly optimizing a multichannel frontend and an end-to-end (E2E) Automatic Speech Recognition (ASR) backend shows promising results. Recent literature has shown traditional beamformer
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::60c8efbe738419d55ab97cad279d2712
Autor:
Carl Quillen
Publikováno v:
ICASSP
Autoregressive HMM modeling of spectral features has been proposed as a replacement for standard HMM speech synthesis. The merits of the approach are explored, and methods for enforcing stability of the estimated predictor coefficients are presented.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::265ed87b50c1298e26d0f4500780c3c4
https://doi.org/10.1109/icassp.2012.6288800
https://doi.org/10.1109/icassp.2012.6288800
Autor:
Carl Quillen
Publikováno v:
ICASSP
Preliminary results are reported from a very simple speech-synthesis system based on clustered-diphone Kalman Filter based modeling of line-spectral frequency based features. Parameters were estimated using maximum-likelihood EM training, with a cons
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e58820ca8d355291bea296769a5092e3
https://doi.org/10.1109/icassp.2010.5495547
https://doi.org/10.1109/icassp.2010.5495547
Autor:
Douglas A. Reynolds, Pedro A. Torres-Carrasquillo, Carl Quillen, William M. Campbell, Terry P. Gleason, Douglas E. Sturim, André Gustavo Adami
Publikováno v:
ICASSP (1)
The MIT Lincoln Laboratory submission for the 2004 NIST speaker recognition evaluation (SRE) was built upon seven core systems using speaker information from short-term acoustics, pitch and duration prosodic behavior, and phoneme and word usage. Thes
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5379f7e090c312c1f9fe60d2f4bb9c7
https://doi.org/10.1109/icassp.2005.1415079
https://doi.org/10.1109/icassp.2005.1415079
Autor:
Pierre L. Dognin, Herbert Gish, Carl Quillen, Fred Richardson, Thomas Colthurst, Spyros Matsoukas, Alex Solomonoff, Owen Kimball
Publikováno v:
ICASSP
This paper describes the BYBLOS system that BBN used to participate in the 2001 NIST Hub-5 evaluation benchmark. We outline the procedure used for training and decoding, and present the algorithmic improvements made to the system, along with experime
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9e03cdb117e4de6c5958d110e3d611aa
https://doi.org/10.1109/icassp.2002.5743819
https://doi.org/10.1109/icassp.2002.5743819
Autor:
Carl Quillen
Publikováno v:
6th International Conference on Spoken Language Processing (ICSLP 2000).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cef6b4bb9f479916d0e5c1233b3f8f3c
https://doi.org/10.21437/icslp.2000-105
https://doi.org/10.21437/icslp.2000-105
Autor:
S. Marsoukas, Fred Richardson, Herbert Gish, Man-Hung Siu, Carl Quillen, Rukmini Iyer, G. Zavaliagkos, Jayadev Billa, Kristine W. Ma, A. El-Jaroudi, T. Colhurst
Publikováno v:
ICASSP
This paper describes the improvements that resulted in the 1998 Byblos large vocabulary conversational speech recognition (LVCSR) system. Salient among these improvements are: improved signal processing, improved hidden Markov model (HMM) topology, u
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::70723a025a808a88edb1a0e5e9fbd3bc
https://doi.org/10.1109/icassp.1999.758057
https://doi.org/10.1109/icassp.1999.758057
Publikováno v:
5th International Conference on Spoken Language Processing (ICSLP 1998).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3e264b7ea96a032b75f255b9bcee6940
https://doi.org/10.21437/icslp.1998-685
https://doi.org/10.21437/icslp.1998-685