461 citations · 1.1k across the 30 of their papers we have counts for
41 papers
Introducing topography in convolutional neural networks
Maxime Poli, Emmanuel Dupoux, Rachid Riad
Parts of the brain that carry sensory tasks are organized topographically: nearby neurons are responsive to the same properties of input signals. Thus, in this work, inspired by th…
Emergent Communication: Generalization and Overfitting in Lewis Games
Mathieu Rita, Corentin Tallec, Paul Michel +4
Lewis signaling games are a class of simple communication games for simulating the emergence of language. In these games, two agents must agree on a communication protocol in order…
Is the Language Familiarity Effect gradual? A computational modelling approach
Maureen de Seyssel, Guillaume Wisniewski, Emmanuel Dupoux
According to the Language Familiarity Effect (LFE), people are better at discriminating between speakers of their native language. Although this cognitive effect was largely studie…
On the role of population heterogeneity in emergent communication
Mathieu Rita, Florian Strub, Jean-Bastien Grill +2
Populations have often been perceived as a structuring component for language to emerge and evolve: the larger the population, the more structured the language. While this observat…
Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
Adam Polyak, Yossi Adi, Jade Copet +5
We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representat…
Learning spectro-temporal representations of complex sounds with parameterized neural networks
Rachid Riad, Julien Karadayi, Anne-Catherine Bachoud-Lévi +1
Deep Learning models have become potential candidates for auditory neuroscience research, thanks to their recent successes on a variety of auditory tasks. Yet, these models often l…
Generative Spoken Language Modeling from Raw Audio
Kushal Lakhotia, Evgeny Kharitonov, Wei-Ning Hsu +8
We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of m…
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
Changhan Wang, Morgane Rivière, Ann Lee +6
We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised repre…
The Zero Resource Speech Benchmark 2021: Metrics and baselines for unsupervised spoken language modeling
Tu Anh Nguyen, Maureen de Seyssel, Patricia Rozé +5
We introduce a new unsupervised task, spoken language modeling: the learning of linguistic representations from raw audio signals without any labels, along with the Zero Resource S…
Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews
Rachid Riad, Hadrien Titeux, Laurie Lemoine +6
Conversations between a clinician and a patient, in natural conditions, are valuable sources of information for medical follow-up. The automatic analysis of these dialogues could h…
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
Ewan Dunbar, Julien Karadayi, Mathieu Bernard +6
We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels. It combines the data sets and metrics f…
Analogies minus analogy test: measuring regularities in word embeddings
Louis Fournier, Emmanuel Dupoux, Ewan Dunbar
Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose an…
"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently
Mathieu Rita, Rahma Chaabouni, Emmanuel Dupoux
Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a spe…
Vocal markers from sustained phonation in Huntington's Disease
Rachid Riad, Hadrien Titeux, Laurie Lemoine +5
Disease-modifying treatments are currently assessed in neurodegenerative diseases. Huntington's Disease represents a unique opportunity to design automatic sub-clinical markers, ev…
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve +4
Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech…
Evaluating the reliability of acoustic speech embeddings
Robin Algayres, Mohamed Salah Zaiem, Benoit Sagot +1
Speech embeddings are fixed-size acoustic representations of variable-length speech sequences. They are increasingly used for a variety of tasks ranging from information retrieval…
An open-source voice type classifier for child-centered daylong recordings
Marvin Lavechin, Ruben Bousbib, Hervé Bredin +2
Spontaneous conversations in real-world settings such as those found in child-centered recordings have been shown to be amongst the most challenging audio files to process. Neverth…
Occlusion resistant learning of intuitive physics from videos
Ronan Riochet, Josef Sivic, Ivan Laptev +1
To reach human performance on complex tasks, a key ability for artificial systems is to understand physical interactions between objects, and predict future outcomes of a situation…
Compositionality and Generalization in Emergent Languages
Rahma Chaabouni, Eugene Kharitonov, Diane Bouchacourt +2
Natural language allows us to refer to novel composite concepts by combining expressions denoting their parts according to systematic rules, a property known as \emph{compositional…
Identification of primary and collateral tracks in stuttered speech
Rachid Riad, Anne-Catherine Bachoud-Lévi, Frank Rudzicz +1
Disfluent speech has been previously addressed from two main perspectives: the clinical perspective focusing on diagnostic, and the Natural Language Processing (NLP) perspective ai…
Seshat: A tool for managing and verifying annotation campaigns of audio data
Hadrien Titeux, Rachid Riad, Xuan-Nga Cao +5
We introduce Seshat, a new, simple and open-source software to efficiently manage annotations of speech corpora. The Seshat software allows users to easily customise and manage ann…
Unsupervised pretraining transfers well across languages
Morgane Rivière, Armand Joulin, Pierre-Emmanuel Mazaré +1
Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel…
Libri-Light: A Benchmark for ASR with Limited or No Supervision
Jacob Kahn, Morgane Rivière, Weiyi Zheng +12
We introduce a new collection of spoken English audio suitable for training speech recognition systems under limited or no supervision. It is derived from open-source audio books f…
Speaker detection in the wild: Lessons learned from JSALT 2019
Paola Garcia, Jesus Villalba, Herve Bredin +21
This paper presents the problems and solutions addressed at the JSALT workshop when using a single microphone for speaker detection in adverse scenarios. The main focus was to tack…