← Authors

Hervé Bourlard

21 papers · 2016–2022 · 2 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (2) 🏃 Academic Marathon (6) 🧭 Keyword Pioneer 🐝 Cross-Pollinator (14) 🗺️ Taxonomy Completionist (26) 🌉 Interdisciplinary Bridge 🏠 Conference Loyalist (20) 🧬 Topic Evolution 🏆 Keyword Champion (5) 👥 Mega-Team (46) 🗃️ Keyword Collector (92) 🚀 Conference Pioneer 💎 Century Club (21) 🔥 Unstoppable (7) 📈 Trend Setter ⚡ Prolific Year (5)

Conferences

INTERSPEECH (20) EACL (1)

Top co-authors

Afsaneh Asaei (6) Philip N. Garner (5) Sibo Tong (5) Srikanth Madikeri (4) Ina Kodrasi (4) Dhananjay Ram (3) Petr Motlicek (3) Michaela Pernon (2) Pranay Dighe (2) Milos Cernak (2)

Keywords

automatic speech recognition (10) posterior probability (5) deep neural network (5) acoustic model (4) lattice-free maximum mutual information (4) query by example (3) dynamic time warping (2) language adaptation (2) domain adaptation (2) sparse representation (2) speech intelligibility (2) transfer learning (2) principal component analysis (2) connectionist temporal classification (2) spoken term detection (2) semantic parsing (1) named entity recognition (1) subspace analysis (1) speech recognition (1) machine translation (1)

Papers

Comparison of 5 methods for the evaluation of intelligibility in mild to moderate French dysarthric speech INTERSPEECH 2022
From Undercomplete to Sparse Overcomplete Autoencoders to Improve LF-MMI based Speech Recognition INTERSPEECH 2022
Comparing CTC and LFMMI for Out-of-Domain Adaptation of wav2vec 2.0 Acoustic Model INTERSPEECH 2021
Multitask Adaptation with Lattice-Free MMI for Multi-Genre Speech Recognition of Low Resource Languages INTERSPEECH 2021
Automatic Discrimination of Apraxia of Speech and Dysarthria Using a Minimalistic Set of Handcrafted Features INTERSPEECH 2020
Lattice-Free Maximum Mutual Information Training of Multilingual Speech Recognition Systems INTERSPEECH 2020
Unbiased Semi-Supervised LF-MMI Training Using Dropout INTERSPEECH 2019
Spectral Subspace Analysis for Automatic Assessment of Pathological Speech Intelligibility INTERSPEECH 2019
Evolution of Neural Network Architectures for Speech Recognition INTERSPEECH 2018
CNN Based Query by Example Spoken Term Detection INTERSPEECH 2018
Single-channel Late Reverberation Power Spectral Density Estimation Using Denoising Autoencoders INTERSPEECH 2018
Phonological Posterior Hashing for Query by Example Spoken Term Detection INTERSPEECH 2018
Fast Language Adaptation Using Phonological Information INTERSPEECH 2018
The SUMMA Platform Prototype EACL 2017
Exploiting Eigenposteriors for Semi-Supervised Training of DNN Acoustic Models with Sequence Discrimination INTERSPEECH 2017
An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation INTERSPEECH 2017
Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling INTERSPEECH 2016
Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures INTERSPEECH 2016
Inter-Task System Fusion for Speaker Recognition INTERSPEECH 2016
Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection INTERSPEECH 2016
Sound Pattern Matching for Automatic Prosodic Event Detection INTERSPEECH 2016