514 citations · 918 across the 31 of their papers we have counts for
36 papers
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Titouan Parcollet, Ha Nguyen, Solene Evain +19
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing. Speech processing…
Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads
Salah Zaiem, Youcef Kemiche, Titouan Parcollet +2
Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed appr…
SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding
Titouan Parcollet, Rogier van Dalen, Shucong Zhang +1
Modern speech processing systems rely on self-attention. Unfortunately, token mixing with self-attention takes quadratic time in the length of the speech utterance, slowing down in…
Learning Multilingual Expressive Speech Representation for Prosody Prediction without Parallel Data
Jarod Duret, Titouan Parcollet, Yannick Estève
We propose a method for speech-to-speech emotionpreserving translation that operates at the level of discrete speech units. Our approach relies on the use of multilingual emotion e…
Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations
Salah Zaiem, Titouan Parcollet, Slim Essid
Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datas…
Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?
Salah Zaiem, Youcef Kemiche, Titouan Parcollet +2
Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts o…
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition
Florian Mai, Juan Zuluaga-Gomez, Titouan Parcollet +1
State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions…
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study
Salah Zaiem, Robin Algayres, Titouan Parcollet +2
Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it has been demonstrate…
Stabilising and accelerating light gated recurrent units for automatic speech recognition
Adel Moumen, Titouan Parcollet
The light gated recurrent units (Li-GRU) is well-known for achieving impressive results in automatic speech recognition (ASR) tasks while being lighter and faster to train than a s…
Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio
Yan Gao, Javier Fernandez-Marques, Titouan Parcollet +2
Self-supervised learning (SSL) has proven vital in speech and audio-related applications. The paradigm trains a general model on unlabeled data that can later be used to solve spec…
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity
Xinchi Qiu, Javier Fernandez-Marques, Pedro PB Gusmao +3
When the available hardware cannot meet the memory and compute requirements to efficiently train high performing machine learning models, a compromise in either the training qualit…
Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning
Salah Zaiem, Titouan Parcollet, Slim Essid
Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar sig…
End-to-end model for named entity recognition from speech without paired training data
Salima Mdhaffar, Jarod Duret, Titouan Parcollet +1
Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU). Through the term end-to-end, one considers the use of a s…
Federated Self-supervised Speech Representations: Are We There Yet?
Yan Gao, Javier Fernandez-Marques, Titouan Parcollet +2
The ubiquity of microphone-enabled devices has lead to large amounts of unlabelled audio data being produced at the edge. The integration of self-supervised learning (SSL) and fede…
Pretext Tasks selection for multitask self-supervised speech representation learning
Salah Zaiem, Titouan Parcollet, Slim Essid +1
Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream tas…
SpeechBrain: A General-Purpose Speech Toolkit
Mirco Ravanelli, Titouan Parcollet, Peter Plantinga +18
SpeechBrain is an open-source and all-in-one speech toolkit. It is designed to facilitate the research and development of neural speech processing technologies by being simple, fle…
On-device Federated Learning with Flower
Akhil Mathur, Daniel J. Beutel, Pedro Porto Buarque de Gusmão +6
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do…
End-to-End Speech Recognition from Federated Acoustic Models
Yan Gao, Titouan Parcollet, Salah Zaiem +4
Training Automatic Speech Recognition (ASR) models under federated learning (FL) settings has attracted a lot of attention recently. However, the FL scenarios often presented in th…
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
Solene Evain, Ha Nguyen, Hang Le +15
Self-Supervised Learning (SSL) using huge unlabeled data has been successfully explored for image and natural language processing. Recent works also investigated SSL from speech. T…
Conditional independence for pretext task selection in Self-supervised speech representation learning
Salah Zaiem, Titouan Parcollet, Slim Essid
Through solving pretext tasks, self-supervised learning (SSL) leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstre…
Timers and Such: A Practical Benchmark for Spoken Language Understanding with Numbers
Loren Lugosch, Piyush Papreja, Mirco Ravanelli +2
This paper introduces Timers and Such, a new open source dataset of spoken English commands for common voice control use cases involving numbers. We describe the gap in existing sp…
A first look into the carbon footprint of federated learning
Xinchi Qiu, Titouan Parcollet, Javier Fernandez-Marques +6
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers.…
Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation
Paul-Gauthier Noé, Mohammad Mohammadamini, Driss Matrouf +3
In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authenticati…
Can Federated Learning Save The Planet?
Xinchi Qiu, Titouan Parcollet, Daniel J. Beutel +3
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers.…