Keywords:
- acoustic modeling
- Ad hoc array calibration
- Ad hoc microphone array calibration
- Ad-hoc microphone array
- Ad-hoc microphone calibration
- adaptive training
- Adequacy of diffuseness
- AFC
- Afrikaans
- Artificial Neural Networks
- assessment method
- association rules
- audio–visual speech synchrony
- Auto-associative multilayer perceptrons
- autoencoders
- automatic disambiguation
- Automatic prosodic event detection
- Automatic Speech Recognition
- automatic speech recognition (ASR)
- Autoregressive modeling
- Bayesian recognition
- binary masking
- Binary pattern matching
- bottleneck
- Broadband beam-pattern
- Cadzow algorithm
- canonical correlation analysis
- Cerebral Palsy
- chain models
- Channel selection
- clinical application
- Compressive Acoustic Measurements
- Compressive sampling
- Compressive Sensing
- Computer Vision
- connectionist temporal classification (ctc)
- Conversational technologies
- Convex optimization
- Convolutive source separation
- crosslingual adaptation
- ctc
- data analysis
- data utility
- deep MLPs
- Deep neural network
- Deep neural network (DNN)
- Deep neural network posterior features
- Deep neural network posterior probabilities
- deep neural networks
- Delay-and-sum beamformer
- Dictionary learning
- difference features
- Diffuse field coherence model
- Diffuse noise coherence
- Diffuse sound coherence model
- Diffuse sound field
- Digital IIR Filters
- Digital IIR Filters
- Directivity
- discourse connectives
- Distant speech recognition
- Distributed source localization.
- dnn
- dnn-based speech recognition
- duration models
- Dynamic Bayesian Network
- Dysarthria
- e2e-lfmmi
- error correction
- Euclidean distance matrix
- evidence combination
- exemplar-based modeling
- far-field asr
- far-field speech
- Fast $k$NN
- fast adaptation
- fast training
- FC
- floor control
- Fujisaki Model
- full combination
- gaming
- Generalized cross correlation
- Generalized Trust Region Subproblem (GTRS).
- Graphemes
- Grassmannian discriminant analysis
- hidden variable
- high-dimensional sparse representations
- HMM/ANN-Hybrid
- HMMs
- human behaviour analysis
- hybrid system
- Image Model
- information bottleneck
- Information Bottleneck clustering
- Information Retrieval
- intelligibility
- Joint sparse recovery
- k-nearest neighbor (kNN) search
- Keyword Detection
- Keyword spotting detection
- KL-divergence
- KL-HMM
- kNN classifier
- Kullback-Leibler divergence
- Kullback-Leibler divergence based hidden Markov model
- Laplacian speech modeling
- Linguistic parsing
- Low bit rate speech vocoding
- low-rank representation (LRR)
- low-rank sparsity
- Matrix completion
- microphone array
- Microphone array calibration
- missing data
- missing features
- ML-adaptation
- Model-Based Compressive Sensing
- Model-based sparse recovery
- models
- multi-band
- multi-band combination
- Multi-party Speech Recognition
- Multi-speaker Localization
- multi-stream
- multi-stream processing
- multiband
- multilayer perceptron
- multilingual acoustic modeling
- multilingual ASR
- multilingual speech recognition
- Multimodal interaction
- multimodal signal processing
- multimodal speaker diarisation
- Multiparty Conversation
- multiparty meetings
- multiple time scales
- mutual information
- nearest neighbour rule of classification.
- neural network
- neural network features
- neural networks
- Noise
- noise adaptation
- noise annoyance
- noise intrusiveness
- noise reduction
- noise robust ASR
- Noisy Text
- Non-negative matrix factorization
- non-verbal features
- Objective intelligibility
- objective measures
- open-architecture distributed system
- Overlap speech
- Overlapping Speech
- overlapping speech recognition
- P-ESTOI
- Pairwise distance estimation
- PCA
- perceptual quality assessment
- Phase transform
- Phone posterior
- Phoneme classification
- phonemes
- Phonological features
- Phonological posterior
- phonological posteriors
- posterior feature
- Posterior feature space
- Posterior features
- Posterior hashing
- posterior probability
- Posterior probability structures
- Posterior representatives
- posterior space properties
- posterior-based metrics
- Principle component analysis
- Pronunciation dewarping
- Prosody Modelling
- Psychoacoustics
- Quantized posterior hashing
- query by example
- real-time processing
- reliability
- representation learning
- Reverberant enclosure
- Reverberation
- robust ASR
- Robust microphone placement
- robust recognition
- Room acoustic characterization
- Room acoustic estimation
- Room Geometry
- Room geometry estima- tion
- S-stress
- Semidefinite programming
- sensor fusion
- Single-channel source localization
- Singular value decomposition
- Social Behaviour Analysis
- Social Interactions
- Social Signal Processing
- Social signals
- soft targets
- sound source localization
- Source localization
- sparse autoencoder
- sparse coding
- Sparse Component Analysis
- Sparse modeling
- sparse overcomplete autoencoder
- Sparse Recovery
- sparse representation
- Sparse Signal Recovery
- Sparse word posterior probabilities
- sparsity
- Speaker Diarization
- Speaker localization
- speaker turn
- spectral amplitude estimation
- Spectral subspace
- Speech
- Speech Analysis
- Speech dereverberation
- Speech enhancement
- Speech intelligibility
- speech modeling
- speech processing
- speech quality
- speech recognition
- speech separation
- Speech source localization
- speech sparsity
- Speech spectral structures
- speech synthesis
- Spoken Documents Retrieval
- spoken term detection
- spontaneous meeting recordings
- Statistical Machine Translation
- Structural similarity measure
- Structured Sparse Coding
- Structured sparse representation
- Structured sparsity
- structured sparsity models
- subbands
- subjective evaluation
- subjective testing
- Subspace detection
- Superdirective beamformer
- SVD
- synchronisation
- synthetic reference templates.
- Tandem
- template-based approach
- temporal modulations
- temporal subspace
- text-to-speech synthesis
- triphone mapping
- TTS
- un- derdetermined convolutive speech separation
- under-resourced languages
- under-resourced speech recognition
- universal phoneme set
- utterance verification
- verb tense
- wav2vec 2.0
- weighting
- word emphasis
Publications of Hervé Bourlard
2023
| Idiap Scientific Report 2022, , , , , , , , , , , , , , , , , and , Idiap-RR-05-2023 |
|
2022
| Autoencoders Reloaded, and , in: Springer Biological Cybernetics, 2022 |
[DOI] [URL] |
| Comparison of 5 methods for the evaluation of intelligibility in mild to moderate French dysarthric speech, , , , , , , , , and , in: Annual Conference of the International Speech Communication Association, pages 2188-2192, 2022 |
[DOI] |
| From Undercomplete to Sparse Overcomplete Autoencoders to Improve LF-MMI Speech Recognition, and , in: Proceedings of Interspeech Conference, 2022 |
|
| SPARSE AUTOENCODERS TO ENHANCE SPEECH RECOGNITION, and , Idiap-RR-10-2022 |
|
| SPEECH MODELING USING SPARSE AUTOENCODERS, and , Idiap-RR-11-2022 |
|
2021
| Automatic and perceptual discrimination between dysarthria, apraxia of speech, and neurotypical speech, , , and , in: IEEE International Conference on Acoustics, Speech and Signal Processing, 2021 |
|
| AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS, , and , in: 45th International Conference on Acoustics, Speech, and Signal Processing, Toronto, Canada, pages 7328–7332, 2021 |
|
| Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model, , and , Idiap-RR-04-2021 |
|
| Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model, , and , in: Proceedings of Interspeech, 2021 |
[URL] |
| LATTICE-FREE MMI ADAPTATION OF SELF-SUPERVISED PRETRAINED ACOUSTIC MODELS, , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2021 |
[URL] |
| Multitask adaptation with Lattice-Free MMI for multi-genre speech recognition of low resource languages, , and , in: Proceedings of Interspeech 2021, 2021 |
|
2020
| Automatic Discrimination of Apraxia of Speech and Dysarthria using a Minimalistic Set of Handcrafted Features, , , and , in: Interspeech, 2020 |
|
| AUTOMATIC DYSARTHRIC SPEECH DETECTION EXPLOITING PAIRWISE DISTANCE-BASED CONVOLUTIONAL NEURAL NETWORKS, , and , Idiap-RR-32-2020 |
|
| Automatic pathological speech intelligibility assessment exploiting subspace-based analyses, , and , in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28:1717 - 1728, 2020 |
[DOI] |
| INCREMENTAL SEMI-SUPERVISED LEARNING FOR MULTI-GENRE SPEECH RECOGNITION, , , , , and , in: Proceedings of ICASSP 2020, 2020 |
|
| Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition System, , , , , and , Idiap-RR-28-2020 |
|
| Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition System, , , , , and , in: In Proceedings of Interspeech 2020, pages 4746--4750, ISCA, 2020 |
|
| LATTICE-FREE MMI ADAPTATION OF SELF-SUPERVISED PRETRAINED ACOUSTIC MODELS, , and , Idiap-RR-40-2020 |
[URL] |
| Neural Network based End-to-End Query by Example Spoken Term Detection, , and , in: IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH, AND LANGUAGE PROCESSING, 2020 |
|
| On quantifying the quality of acoustic models in hybrid DNN-HMM ASR, , and , in: Speech Communication, 119:24-35, 2020 |
[DOI] |
| Spectro-temporal sparsity characterization for dysarthric speech detection, and , in: IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28:1210-1222, 2020 |
|
| Subspace-based Learning for Automatic Dysarthric Speech Detection, , and , in: IEEE Signal Processing Letters, 2020 |
| SYNTHETIC SPEECH REFERENCES FOR AUTOMATIC PATHOLOGICAL SPEECH INTELLIGIBILITY ASSESSMENT, , and , in: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Barcelona, Spain, 2020 |
|
2019
| AN END-TO-END NETWORK TO SYNTHESIZE INTONATION USING A GENERALIZED COMMAND RESPONSE MODEL, , , , and , Idiap-RR-05-2019 |
|
| An End-to-end Network to Synthesize Intonation Using a Generalized Command Response Model, , , , and , in: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, United Kingdom, pages 7040-7044, IEEE, 2019 |
[DOI] [URL] |
| AN INVESTIGATION OF MULTILINGUAL ASR USING END-TO-END LF-MMI, , and , in: International Conference on Acoustics, Speech and Signal Processing, 2019 |
|
| ANALYZING UNCERTAINTIES IN SPEECH RECOGNITION USING DROPOUT, , , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019 |
| INVESTIGATING TIME DELAY NEURAL NETWORK (TDNN) FOR LANGUAGE MODELING IN LOW RESOURCE AUTOMATIC SPEECH RECOGNITION, , , and , Idiap-RR-13-2019 |
|
| Multilingual Bottleneck Features for Query by Example Spoken Term Detection, , and , in: IEEE Automatic Speech Recognition and Understanding Workshop, 2019 |
|
| PATHOLOGICAL SPEECH INTELLIGIBILITY ASSESSMENT BASED ON THE SHORT-TIME OBJECTIVE INTELLIGIBILITY MEASURE, , and , in: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Brighton, UK, pages 6405--6409, 2019 |
|
| Spectral Subspace Analysis for Automatic Assessment of Pathological Speech Intelligibility, , and , in: Proceedings of Interspeech, Graz, Austria, pages 3038--3042, 2019 |
|
| STACKED NEURAL NETWORKS WITH PARAMETER SHARING FOR MULTILINGUAL LANGUAGE MODELING, , , , , and , Idiap-RR-12-2019 |
|
| Super-gaussianity of Speech Spectral Coefficients as a Potential Biomarker for Dysarthric Speech Detection, and , in: IEEE International Conference on Acoustics, Speech and Signal Processing, 2019 |