|
Conference Papers
- V. Digalakis, V. Doumpiotis, S. Tsakalidis.
"On the integration of dialect and speaker adaptation in a multi-dialect
speech recognition system,"
EUSIPCO, Rhodes, Greece, September 1998.
- V. Digalakis, S. Tsakalidis, L. Neumeyer.
"Reviving discrete HMMs: the myth about the superiority of continuous HMMs,"
Eurospeech, Budapest, Hungary, September 1999.
- S. Tsakalidis, V. Digalakis, L. Neumeyer.
"Efficient Speech Recognition Using Subvector Quantization and Discrete-mixture
HMMs,"
ICASSP, Phoenix, Arizona, March 1999. ( ps )
- D. Vergyri, S. Tsakalidis and W. Byrne.
"Minimum Risk Acoustic Clustering for Multilingual Acoustic Model Combination,"
ICSLP, Beijing, 2000. ( ps , pdf )
- S. Tsakalidis, V. Doumpiotis and W. Byrne.
"Dicriminative Linear Transforms for Feature Normalization and Speaker
Adaptation in HMM Estimation,"
ICSLP, Denver, 2002. ( ps , pdf )
- V. Doumpiotis, S. Tsakalidis and W. Byrne.
"Discriminative Training for Segmental Minimum Bayes Risk Decoding,"
ICASSP,
Hong Kong, 2003. ( ps , pdf )
- V. Doumpiotis, S. Tsakalidis and W.
Byrne.
"Lattice Segmentation and Minimum Bayes Risk
Discriminative Training,"
EUROSPEECH, Geneva, 2003. ( ps, pdf )
- S. Tsakalidis and W. Byrne.
"Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription,"
ICASSP, 2005. (pdf)
Journal Papers
- V. Digalakis, S. Tsakalidis, C. Harizakis, L. Neumeyer.
"Efficient Speech Recognition Using Subvector Quantization
and Discrete-mixture HMMs,"
Computer Speech and Language (2000) 14, 33-46. ( ps, pdf )
- S. Tsakalidis, V. Doumpiotis and W.
Byrne.
"Discriminative Linear Transforms for Feature
Normalization and Speaker Adaptation in HMM Estimation,"
IEEE Transactions on Speech and Audio
Processing, 13(3), May 2005.
- S. Tsakalidis, V. Doumpiotis and W. Byrne.
"Discriminative Linear Transforms for Feature
Normalization and Speaker Adaptation in HMM Estimation,"
CLSP Technical Report, No.47 ( ps, pdf )
Patents
- "Method and apparatus for automatic recognition using features encoded with product-space vector
quantization"
U.S. Patent No. 6,256,607
|
