← Authors

Titouan Parcollet

24 papers · 2017–2024 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (8) πŸ—ΊοΈ Taxonomy Completionist (17) 🏠 Conference Loyalist (20) πŸ‘₯ Mega-Team (33) πŸ† Keyword Champion (3) 🧬 Topic Evolution πŸ—ƒοΈ Keyword Collector (79) ⚑ Prolific Year (6) πŸ“ˆ Trend Setter πŸ’Ž Century Club (24) πŸ”₯ Unstoppable (8) ❓ The Questioner (2)

Conferences

INTERSPEECH (20) ICLR (2) JMLR (2)

Top co-authors

Mohamed Morchid (6) Salah Zaiem (5) Georges Linarès (5) Mirco Ravanelli (5) Shucong Zhang (5) Xinchi Qiu (4) Renato de Mori (4) Rogier van Dalen (4) Sourav Bhattacharya (4) Slim Essid (4)

Research topics

Privacy (1)

Keywords

self-supervised learning (8) automatic speech recognition (6) speech recognition (4) representation learning (4) quaternion neural network (4) speech enhancement (3) speech processing (3) linear complexity (3) distant speech recognition (2) federated learning (2) multi-channel speech recognition (2) data augmentation (2) speech representation (2) end-to-end speech recognition (2) downstream task (2) inference speed (2) spoken language understanding (2) speaker recognition (2) recurrent neural network (2) energy consumption (2)

Papers

Open-Source Conversational AI with SpeechBrain 1.0 JMLR 2024
Linear-Complexity Self-Supervised Learning for Speech Processing INTERSPEECH 2024
SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding INTERSPEECH 2024
Speech Self-Supervised Representation Benchmarking: Are We Doing it Right? INTERSPEECH 2023
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition INTERSPEECH 2023
On the (In)Efficiency of Acoustic Feature Extractors for Self-Supervised Speech Representation Learning INTERSPEECH 2023
Real-Time Personalised Speech Enhancement Transformers with Dynamic Cross-attended Speaker Representations INTERSPEECH 2023
Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations INTERSPEECH 2023
A First Look into the Carbon Footprint of Federated Learning JMLR 2023
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning INTERSPEECH 2022
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity ICLR 2022
Federated Self-supervised Speech Representations: Are We There Yet? INTERSPEECH 2022
End-to-end model for named entity recognition from speech without paired training data INTERSPEECH 2022
The Energy and Carbon Footprint of Training End-to-End Speech Recognizers INTERSPEECH 2021
Conditional Independence for Pretext Task Selection in Self-Supervised Speech Representation Learning INTERSPEECH 2021
Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation INTERSPEECH 2021
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech INTERSPEECH 2021
Quaternion Neural Networks for Multi-Channel Distant Speech Recognition INTERSPEECH 2020
FusionRNN: Shared Neural Parameters for Multi-Channel Distant Speech Recognition INTERSPEECH 2020
Quaternion Recurrent Neural Networks ICLR 2019
Real to H-Space Encoder for Speech Recognition INTERSPEECH 2019
M2H-GAN: A GAN-Based Mapping from Machine to Human Transcripts for Speech Understanding INTERSPEECH 2019
Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition INTERSPEECH 2018
Quaternion Denoising Encoder-Decoder for Theme Identification of Telephone Conversations INTERSPEECH 2017