Join Us
Sign In
My Subscriptions
Magazines
Journals
Video Library
Conference Proceedings
Individual CSDL Subscriptions
Institutional CSDL Subscriptions
Resources
Career Center
Tech News
Resource Center
Press Room
Advertising
Librarian Resources
IEEE.org
Help
About Us
Career Center
Cart
Create Account
Sign In
Toggle navigation
My Subscriptions
Browse Content
Resources
All
Home
Proceedings
ICASSP
ICASSP 2004
Generate Citations
2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
May 17 2004 to May 21 2004
Montreal, Que.
Volume:
1
2
3
4
5
Table of Contents
2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
Freely available from IEEE.
pp. i
Copyright page
Freely available from IEEE.
pp. ii
IEEE Signal Processing Society 2004 Board of Governors
Freely available from IEEE.
pp. iii
ICASSP 2004 Conference Committee
Freely available from IEEE.
pp. iv
Technical Program Committee
Freely available from IEEE.
pp. v,vi,vii,viii,ix,x,xi
Future ICASSP conferences
Freely available from IEEE.
pp. xii
ICASSP 2004 Philadelphia
Freely available from IEEE.
pp. xiii
Conference proceedings overview
Freely available from IEEE.
pp. xiv
Table of contents
Freely available from IEEE.
pp. xv,xvi,xvii,xviii
ICASSP 2004 technical program
Freely available from IEEE.
pp. XIX
Non-parallel training for voice conversion by maximum likelihood constrained adaptation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-1-4 vol.1
by
A. Mouchtaris
,
J. Van der Spiegel
,
P. Mueller
Speaking style adaptation using context clustering decision tree for HMM-based speech synthesis
Full-text access may be available. Sign in or learn about subscription options.
pp. I-5-8 vol.1
by
J. Yamagishi
,
M. Tachibana
,
T. Masuko
,
T. Kobayashi
High quality voice morphing
Full-text access may be available. Sign in or learn about subscription options.
pp. I-9-12 vol.1
by
Hui Ye
,
S. Young
Algorithm amalgam: morphing waveform based methods, sinusoidal models and STRAIGHT
Full-text access may be available. Sign in or learn about subscription options.
pp. I-13-16 vol.1
by
H. Kawahara
,
H. Banno
,
T. Irino
,
P. Zolfaghari
Voice characteristics conversion for TTS using reverse VTLN
Full-text access may be available. Sign in or learn about subscription options.
pp. I-17-20 vol.1
by
M. Eichner
,
M. Wolff
,
R. Hoffmann
Voice conversion through transformation of spectral and intonation features
Full-text access may be available. Sign in or learn about subscription options.
pp. I-21-4 vol.1
by
D. Rentzos
,
S. Vaseghi
,
Qin Yan
,
Ching-Hsiang Ho
Discriminative training for speaker identification based on maximum model distance algorithm
Full-text access may be available. Sign in or learn about subscription options.
pp. I-25-8 vol.1
by
Q.Y. Hong
,
S. Kwong
Parameter sharing and minimum classification error training of mixtures of factor analyzers for speaker identification
Full-text access may be available. Sign in or learn about subscription options.
pp. I-29-32 vol.1
by
H. Yamamoto
,
Y. Nankaku
,
C. Miyajima
,
K. Tokuda
,
T. Kitamura
Discovering relations among discriminative training objectives [speak recognition applications]
Full-text access may be available. Sign in or learn about subscription options.
pp. I-33-6 vol.1
by
Qi Li
Disentangling speaker and channel effects in speaker verification
Full-text access may be available. Sign in or learn about subscription options.
pp. I-37-40 vol.1
by
P. Kenny
,
P. Dumouchel
Generalized locally recurrent probabilistic neural networks for text-independent speaker verification
Full-text access may be available. Sign in or learn about subscription options.
pp. I-41-4 vol.1
by
T. Ganchev
,
N. Fakotakis
,
D.K. Tasoulis
,
M.N. Vrahatis
Discrimination power weighted subword-based speaker verification
Full-text access may be available. Sign in or learn about subscription options.
pp. I-45-8 vol.1
by
Siu-Man Chan
,
Man-Hung Siu
Soft decoding strategies for distributed speech recognition over IP networks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-49-52 vol.1
by
A. Cardenal-Lopez
,
L. Docio-Fernandez
,
C. Garcia-Mateo
The ETSI extended distributed speech recognition (DSR) standards: server-side speech reconstruction
Full-text access may be available. Sign in or learn about subscription options.
pp. I-53-6 vol.1
by
T. Ramabadran
,
A. Sorin
,
M. McLaughlin
,
D. Chazan
,
D. Pearce
,
R. Hoory
A subvector-based error concealment algorithm for speech recognition over mobile networks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-57-60 vol.1
by
Zheng-Hua Tan
,
P. Daisgaard
,
B. Lindberg
A complexity reduction of ETSI advanced front-end for DSR
Full-text access may be available. Sign in or learn about subscription options.
pp. I-61-4 vol.1
by
Jin-Yu Li
,
Bo Liu
,
Ren-Hua Wang
,
Li-Rong Dai
Robust speech recognition techniques evaluation for telephony server based in-car applications
Full-text access may be available. Sign in or learn about subscription options.
pp. I-65-8 vol.1
by
L. Delphin-Poulat
Efficient and robust distributed speech recognition (DSR) over wireless fading channels: 2D-DCT compression, iterative bit allocation, short BCH code and interleaving
Full-text access may be available. Sign in or learn about subscription options.
pp. I-69-72 vol.1
by
Wei-hao Hsu
,
Lin-shan Lee
High-level speaker verification with support vector machines
Full-text access may be available. Sign in or learn about subscription options.
pp. I-73-6 vol.1
by
W.M. Campbell
,
J.R. Campbell
,
D.A. Reynolds
,
D.A. Jones
,
T.R. Leek
Using Haar transformed vocal source information for automatic speaker recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-77-80 vol.1
by
Nengheng Zheng
,
P.C. Ching
Text-independent speaker recognition by combining speaker-specific GMM with speaker adapted syllable-based HMM
Full-text access may be available. Sign in or learn about subscription options.
pp. I-81-4 vol.1
by
S. Nakagawa
,
W. Zhang
,
M. Takahashi
Applying articulatory features to telephone-based speaker verification
Full-text access may be available. Sign in or learn about subscription options.
pp. I-85-8 vol.1
by
Ka-Yee Leung
,
Man-Wai Mak
,
Sun-Yuan Kung
Speaker identification using supra-segmental pitch pattern dynamics
Full-text access may be available. Sign in or learn about subscription options.
pp. I-89-92 vol.1
by
F. Farahani
,
P.G. Georgiou
,
S.S. Narayanan
Improvement of speaker recognition by combining residual and prosodic features with acoustic features
Full-text access may be available. Sign in or learn about subscription options.
pp. I-93-6 vol.1
by
Shi-Han Chen
,
Hsiao-Chuan Wang
Pitch prediction from MFCC vectors for speech reconstruction
Full-text access may be available. Sign in or learn about subscription options.
pp. I-97-100 vol.1
by
Xu Shao
,
B. Milner
Algorithm for automatic glottal waveform estimation without the reliance on precise glottal closure information
Full-text access may be available. Sign in or learn about subscription options.
pp. I-101-4 vol.1
by
E. Moore
,
M. Clements
Tone recognition with fractionized models and outlined features
Full-text access may be available. Sign in or learn about subscription options.
pp. I-105-8 vol.1
by
Ye Tian
,
Jian-Lai Zhou
,
Min Chu
,
E. Chang
Extraction of pitch in adverse conditions
Full-text access may be available. Sign in or learn about subscription options.
pp. I-109-12 vol.1
by
S.R.M. Prasanna
,
B. Yegnanarayana
Weighted autocorrelation-based F0 estimation for distant-talking interaction with a distributed microphone network
Full-text access may be available. Sign in or learn about subscription options.
pp. I-113-16 vol.1
by
L. Armani
,
M. Omologo
A novel method for computation of periodicity, aperiodicity and pitch of speech signals
Full-text access may be available. Sign in or learn about subscription options.
pp. I-117-20 vol.1
by
O. Deshmukh
,
J. Singh
,
C. Espy-Wilson
Non-uniform speaker normalization using affine-transformation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-121-4 vol.1
by
S.V.B. Kumar
,
S. Umesh
,
R. Sinha
Product of power spectrum and group delay function for speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-125-8 vol.1
by
Donglai Zhu
,
K.K. Paliwal
The ETSI extended distributed speech recognition (DSR) standards: client side processing and tonal language recognition evaluation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-129-32 vol.1
by
A. Sorin
,
T. Ramabadran
,
D. Chazan
,
R. Hoory
,
M. Mclaughlin
,
D. Pearce
,
F.C. Wang
,
Yaxin Zhang
Robust speech feature extraction by growth transformation in reproducing kernel Hilbert space
Full-text access may be available. Sign in or learn about subscription options.
pp. I-133-6 vol.1
by
S. Chakrabartty
,
Yunbin Deng
,
G. Cauwenberghs
Dimensionality reduction using MCE-optimized LDA transformation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-137-40 vol.1
by
Xiao-Bing Li
,
Jin-Yu Li
,
Ren-Hua Wang
Speech feature extraction method representing periodicity and aperiodicity in sub bands for robust speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-141-4 vol.1
by
K. Ishizuka
,
N. Miyazaki
Low-complexity predictive trellis coded quantization of wideband speech LSF parameters
Full-text access may be available. Sign in or learn about subscription options.
pp. I-145-8 vol.1
by
Yongwon Shin
,
Sangwon Kang
,
T.R. Fischer
,
Changyong Son
,
Yongbeom Lee
Multiple frame block quantisation of line spectral frequencies using Gaussian mixture models
Full-text access may be available. Sign in or learn about subscription options.
pp. I-149-52 vol.1
by
K.K. Paliwal
,
S. So
Variable-dimension quantization of sinusoidal amplitudes using Gaussian mixture models
Full-text access may be available. Sign in or learn about subscription options.
pp. I-153-6 vol.1
by
J. Lindblom
,
P. Hedelin
On split quantization of LSF parameters
Full-text access may be available. Sign in or learn about subscription options.
pp. I-157-60 vol.1
by
F. Nordin
,
T. Eriksson
Improved quantization structures using generalized HMM modelling with application to wideband speech coding
Full-text access may be available. Sign in or learn about subscription options.
pp. I-161-4 vol.1
by
E.R. Duni
,
A.D. Subramaniam
,
B.D. Rao
Waveform quantization of speech using Gaussian mixture models
Full-text access may be available. Sign in or learn about subscription options.
pp. I-165-8 vol.1
by
J. Samuelsson
Effects on transcription errors on supervised learning in speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-169-72 vol.1
by
R. Sundaram
,
J. Picone
Combination of hidden Markov models with dynamic time warping for speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-173-6 vol.1
by
S. Axelrod
,
B. Maison
Joint decoding for phoneme-grapheme continuous speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-177-80 vol.1
by
M. Magimai-Doss
,
S. Bengio
,
H. Bourlard
A locally weighted distance measure for example based speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-181-4 vol.1
by
M. De Wachter
,
K. Demuynck
,
P. Wambacq
,
D. Van Compernolle
Light supervision in acoustic model training
Full-text access may be available. Sign in or learn about subscription options.
pp. I-185-8 vol.1
by
Long Nguyen
,
Bing Xiang
Lightly supervised acoustic model training using consensus networks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-189-92 vol.1
by
Langzhou Chen
,
L. Lamel
,
J.L. Gauvain
Spectral entropy based feature for robust ASR
Full-text access may be available. Sign in or learn about subscription options.
pp. I-193-6 vol.1
by
H. Misra
,
S. Ikbal
,
H. Bourlard
,
H. Hermansky
Higher order cepstral moment normalization (HOCMN) for robust speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-197-200 vol.1
by
Chang-wen Hsu
,
Lin-shan Lee
Robustness of speech recognition using genetic algorithms and a Mel-cepstral subspace approach
Full-text access may be available. Sign in or learn about subscription options.
pp. I-201-4 vol.1
by
S.A. Selouani
,
D. O'Shaughnessy
Phase autocorrelation (PAC) features in entropy based multi-stream for robust speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-205-8 vol.1
by
S. Ikbal
,
H. Misra
,
H. Bourlard
,
H. Hermansky
Cepstral gain normalization for noise robust speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-209-12 vol.1
by
S. Yoshizawa
,
N. Hayasaka
,
N. Wada
,
Y. Miyanaga
Robust speech recognition using cepstral domain missing data techniques and noisy masks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-213-16 vol.1
by
H. Van Hamme
Optimal blind separation of convolutive audio mixtures without temporal constraints
Full-text access may be available. Sign in or learn about subscription options.
pp. I-217-20 vol.1
by
K. Kokkinakis
,
A.K. Nandi
Microphone array post-filter for separation of simultaneous non-stationary sources
Full-text access may be available. Sign in or learn about subscription options.
pp. I-221-4 vol.1
by
J.M. Valin
,
J. Rouat
,
F. Michaud
Overdetermined blind separation for convolutive mixtures of speech based on multistage ICA using subarray processing
Full-text access may be available. Sign in or learn about subscription options.
pp. I-225-8 vol.1
by
T. Nishikawa
,
H. Abe
,
H. Saruwatari
,
K. Shikano
Speech enhancement based on a combined multi-channel array with constrained iterative and auditory masked processing
Full-text access may be available. Sign in or learn about subscription options.
pp. I-229-32 vol.1
by
Xianxian Zhang
,
J.H.L. Hansen
,
K.A. Rehar
Multiple-microphone time-varying filters for robust speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-233-6 vol.1
by
Calvin Yiu-Kit Lai
,
P. Aarabi
Noise suppression for automotive applications based on directional information
Full-text access may be available. Sign in or learn about subscription options.
pp. I-237-40 vol.1
by
M. Fuchs
,
T. Haulick
,
G. Schmidt
Meta-data conditional language modeling
Full-text access may be available. Sign in or learn about subscription options.
pp. I-241-4 vol.1
by
M. Bacchiani
,
B. Roark
Exact training of a neural syntactic language model
Full-text access may be available. Sign in or learn about subscription options.
pp. I-245-8 vol.1
by
A. Emami
,
F. Jelinek
Development of the 2003 CU-HTK conversational telephone speech transcription system
Full-text access may be available. Sign in or learn about subscription options.
pp. I-249-52 vol.1
by
G. Evermann
,
H.Y. Chan
,
M.J.F. Gales
,
T. Hain
,
X. Liu
,
D. Mrva
,
L. Wang
,
P.C. Woodland
Vocabulary-independent search in spontaneous speech
Full-text access may be available. Sign in or learn about subscription options.
pp. I-253-6 vol.1
by
F. Seide
,
Peng Yu
,
Chengyuan Ma
,
E. Chang
Cross-lingual latent semantic analysis for language modeling
Full-text access may be available. Sign in or learn about subscription options.
pp. I-257-60 vol.1
by
Woosung Kim
,
S. Khudanpur
The use of a linguistically motivated language model in conversational speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-261-4 vol.1
by
Wen Wang
,
A. Stolcke
,
M.P. Harper
A study of design compromises for speech coders in packet networks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-265-8 vol.1
by
R. Lefebvre
,
Philippe Gournay
,
R. Salami
Improvement issues on transcoding algorithms: for the flexible usage to the various pairs of speech codec
Full-text access may be available. Sign in or learn about subscription options.
pp. I-269-72 vol.1
by
Jin-Kyu Choi
,
Chang-Heon Lee
,
K. Hong-Goo
,
Young-Cheol Park
,
Dae Hee Youn
A scalable speech and audio coding scheme with continuous bitrate flexibility
Full-text access may be available. Sign in or learn about subscription options.
pp. I-273-6 vol.1
by
B. Kovesi
,
D. Massaloux
,
A. Sollaud
A multiple description speech coder based on AMR-WB for mobile ad hoc networks
Full-text access may be available. Sign in or learn about subscription options.
pp. I-277-80 vol.1
by
H. Dong
,
A. Gersho
,
J.D. Gibson
,
V. Cuperman
On the architecture of the cdma2000/spl reg/ variable-rate multimode wideband (VMR-WB) speech coding standard
Full-text access may be available. Sign in or learn about subscription options.
pp. I-281-4 vol.1
by
M. Jelinek
,
R. Salami
,
S. Ahmadi
,
B. Bessetle
,
P. Gournay
,
C. Laflamme
A bit-rate/bandwidth scalable speech coder based on ITU-T G.723.1 standard
Full-text access may be available. Sign in or learn about subscription options.
pp. I-285-8 vol.1
by
Sung-Kyo Jung
,
Kyung-Tae Kini
,
Hong-Goo Kang
A two-step noise reduction technique
Full-text access may be available. Sign in or learn about subscription options.
pp. I-289-92 vol.1
by
C. Plapous
,
C. Marro
,
L. Mauuary
,
P. Scalart
On the decision-directed estimation approach of Ephraim and Malah
Full-text access may be available. Sign in or learn about subscription options.
pp. I-293-6 vol.1
by
I. Cohen
Employing Laplacian-Gaussian densities for speech enhancement
Full-text access may be available. Sign in or learn about subscription options.
pp. I-297-300 vol.1
by
S. Gazor
Robust adaptive Kalman filtering-based speech enhancement algorithm
Full-text access may be available. Sign in or learn about subscription options.
pp. I-301-4 vol.1
by
M. Gabrea
A noise estimation algorithm with rapid adaptation for highly nonstationary environments
Full-text access may be available. Sign in or learn about subscription options.
pp. I-305-8 vol.1
by
S. Rangachari
,
P.C. Loizou
,
Yi Hu
Low distortion speech denoising using an adaptive parametric Wiener filter
Full-text access may be available. Sign in or learn about subscription options.
pp. I-309-12 vol.1
by
Ningping Fan
Performance comparisons of all-pass transform adaptation with maximum likelihood linear regression
Full-text access may be available. Sign in or learn about subscription options.
pp. I-313-16 vol.1
by
J. McDonough
,
A. Waibel
Adaptive training using structured transforms
Full-text access may be available. Sign in or learn about subscription options.
pp. I-317-20 vol.1
by
K. Yu
,
M.J.F. Gales
MPE-based discriminative linear transform for speaker adaptation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-321-4 vol.1
by
L. Wang
,
P. Woodland
A study of various composite kernels for kernel eigenvoice speaker adaptation
Full-text access may be available. Sign in or learn about subscription options.
pp. I-325-8 vol.1
by
B. Mak
,
J.T. Kwok
,
S. Ho
Feature space Gaussianization
Full-text access may be available. Sign in or learn about subscription options.
pp. I-329-32 vol.1
by
G. Saon
,
S. Dharanipragada
,
D. Povey
Online speaker clustering
Full-text access may be available. Sign in or learn about subscription options.
pp. I-333-6 vol.1
by
D. Lilt
,
F. Kubala
Prior knowledge guided MEL based model selection and adaptation for nonnative speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-337-40 vol.1
by
Xiaodong He
,
Yunxin Zhao
Enrollment in low-resource speech recognition systems
Full-text access may be available. Sign in or learn about subscription options.
pp. I-341-4 vol.1
by
S. Deligne
,
S. Dharanipragada
An investigation into front-end signal processing for speaker normalization
Full-text access may be available. Sign in or learn about subscription options.
pp. I-345-8 vol.1
by
S. Umesh
,
R. Sinha
,
S.V.B. Kumar
Eigen-MLLRs applied to unsupervised speaker enrollment for large vocabulary continuous speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-349-52 vol.1
by
X.L. Aubert
Speaker indexing and adaptation using speaker clustering based on statistical model selection
Full-text access may be available. Sign in or learn about subscription options.
pp. I-353-6 vol.1
by
M. Nishida
,
T. Kawahara
Eigenspace-based MLLR with speaker adaptive training in large vocabulary conversational speech recognition
Full-text access may be available. Sign in or learn about subscription options.
pp. I-357-60 vol.1
by
V. Dounipiotis
,
Yonggang Deng
Showing 100 out of 271
Load More
Load All