Keywords:
- Bayesian recognition
- classifier correction
- combination of experts
- confidence measures
- confusion matrix
- contingency tables
- data uncertainty
- data utility
- duration models
- EEG
- evidence combination
- full combination
- HMM/ANN-Hybrid
- HMMs
- likelihood decomposition
- likelihood ratio
- missing data
- missing features
- ML-adaptation
- MLP classifier
- multi-band
- multi-band and multi-stream processing
- multi-band combination
- multi-stream
- multi-stream classification
- multi-stream hybrid
- multi-stream processing
- multiband
- multiband ASR
- mutual information
- neural networks
- Noise
- noise adaptation
- noise masking
- noise robust ASR
- non-linear phonology
- pdf transformation
- posteriors decomposition
- robust ASR
- robust recognition
- soft missing data
- subbands
- tandem hybrid
- weighting
- word error rate
Publications of Andrew Morris sorted by title
A
| A comparison of two strategies for ASR in additive noise : Missing Data and Spectral Subtraction, and , Idiap-RR-17-1999 |
|
| A comparison of two strategies for ASR in additive noise : Missing Data and Spectral Subtraction, and , in: 6th European Conference on Speech Communication and Technology --- Eurospeech'99, 1999 |
|
| A neural network for classification with incomplete data, , Idiap-RR-23-2000 |
|
| A neural network for classification with incomplete data: application to robust ASR, , , , and , in: Proc. ICSLP, 2000 |
|
| Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR, , and , in: ICASSP, 2001 |
|
| Adaptive ML-Weighting in Multi-Band Recombination of Gaussian Mixture ASR, , and , Idiap-RR-05-2001 |
|
| An information theoretic measure of sequence recognition performance, , Idiap-Com-03-2002 |
|
| Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Variables, , , and , in: 6th International Conference on Spoken Language Processing: ICSLP~2000 (Interspeech~2000), 2000 |
|
| Automatic Speech Recognition using Dynamic Bayesian Networks with both Acoustic and Articulatory Variables, , , and , Idiap-RR-19-2000 |
|
C
| Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR, and , in: ICSLP, 2000 |
|
| Comparison of HMM experts with MLP experts in the Full Combination Multi-Band Approach to Robust ASR, and , Idiap-RR-21-2000 |
|
| Confusion Matrix Based Entropy Correction in Multi-stream Combination, and , in: Proceedings of ISCA European Conference on Speech Communication and Technology (Eurospeech), 2003 |
|
| Confusion matrix based posterior probabilities correction, and , Idiap-RR-53-2002 |
|
D
| Data utility modelling for mismatch reduction, , in: Proc. CRAC (workshop on Consistent & Reliable Acoustic Cues for sound analysis), 2001 |
|
| Data utility modelling for mismatch reduction, , Idiap-RR-30-2001 |
|
| Different Weighting Schemes in the Full Combination Subbands Approach for Noise Robust ASR, , and , in: Robust Methods for Speech Recognition in Adverse Conditions, 1999 |
|
E
| EEG pattern recognition through multi-stream evidence combination, , and , in: Proc. World Congress on Neuroinformatics, 2001 |
|
| EEG pattern recognition through multi-stream evidence combination, , and , Idiap-RR-31-2001 |
|
| Extended BIC Criterion for Model Selection, and , Idiap-RR-42-2002 |
|
F
| From missing data to maybe useful data: soft data modelling for noise robust ASR, , and , in: Proc. WISP, 2001 |
|
| From missing data to maybe useful data: soft data modelling for noise robust ASR, , and , Idiap-RR-06-2001 |
|
| From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR, , and , in: ISCA ITRW ASR2000, 2000 |
|
| From Multi-Band Full Combination to Multi-Stream Full Combination Processing in Robust ASR, , and , Idiap-RR-20-2000 |
|
L
| Latent variable decomposition for posteriors or likelihood based subband ASR, , Idiap-Com-04-1999 |
|
| Low cost duration modelling for noise robust speech recognition, , and , in: Proc. ICSLP, 2002 |
|
| Low cost duration modelling for noise robust speech recognition, , and , Idiap-RR-08-2002 |
|
M
| MAP Combination of Multi-Stream HMM or HMM/ANN Experts, , and , in: Proc. Eurospeech, 2001 |
|
| MAP Combination of Multi-Stream HMM or HMM/ANN Experts, , and , Idiap-RR-14-2001 |
|
| Multi-stream adaptive evidence combination for noise robust ASR, , , and , in: Speech Communication, 2001 |
| Multi-stream adaptive evidence combination for noise robust ASR, , , and , Idiap-RR-26-1999 |
|
N
| Noise PDF transformation in secondary feature processing, , Idiap-RR-29-2002 |
|
R
| Recent advances in the multi-stream HMM/ANN hybrid approach to noise robust ASR, and , Idiap-RR-57-2002 |
|
| Robust Speech Recognition with Small Microphone Arrays using the Missing Data Approach, , and , in: Proceedings of International Conference on Speech and Language Processing (ICSLP), 2002 |
|
| Robust Speech Recognition with Small Microphone Arrays using the Missing Data Approach, , and , Idiap-RR-09-2002 |
|
S
| Some applications of a priori knowledge in multi-stream HMM and HMM/ANN based ASR, , in: Phonus No.5,Dec.2000, ISSN 0949-1791, Proc. Workshop on Phonetics and Phonology in ASR, 2000 |
|
| Subband-Based Speech Recognition in Noisy Conditions: The Full Combination Approach, , and , Idiap-RR-15-1998 |
|
T
| The full combination sub-bands approach to noise robust HMM/ANN based ASR, , and , in: 6th European Conference on Speech Communication and Technology --- Eurospeech'99, 1999 |
|