41 citations · 134 across the 14 of their papers we have counts for
17 papers
A Semi-Automatic Approach to Create Large Gender- and Age-Balanced Speaker Corpora: Usefulness of Speaker Diarization & Identification
Rémi Uro, David Doukhan, Albert Rilliard +4
This paper presents a semi-automatic approach to create a diachronic corpus of voices balanced for speaker's age, gender, and recording period, according to 32 categories (2 gender…
Joint speech and overlap detection: a benchmark over multiple audio setup and speech domains
Martin Lebourdais, Théo Mariotte, Marie Tahon +5
Voice activity and overlapped speech detection (respectively VAD and OSD) are key pre-processing tasks for speaker diarization. The final segmentation performance highly relies on…
Improved Cross-Lingual Transfer Learning For Automatic Speech Translation
Sameer Khurana, Nauman Dawalatabad, Antoine Laurent +4
Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cro…
On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration
Nauman Dawalatabad, Sameer Khurana, Antoine Laurent +1
Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST) methods for unsupervised domain adaptation. Dropout-based Uncertainty-driven Self-Training (DUST) proceeds by…
Overlapped speech and gender detection with WavLM pre-trained features
Martin Lebourdais, Marie Tahon, Antoine Laurent +1
This article focuses on overlapped speech and gender detection in order to study interactions between women and men in French audiovisual media (Gender Equality Monitoring project)…
ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks
Valentin Pelloin, Franck Dary, Nicolas Herve +4
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech. We leverage the INA (French National Audiovisual Institute) collectio…
SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation
Sameer Khurana, Antoine Laurent, James Glass
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-level Cross-Lingual Speech Representation learning framework. Unlike previous works on speech representation lea…
ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks
Marcely Zanon Boito, John Ortega, Hugo Riguidel +8
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speec…
Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0
Sameer Khurana, Antoine Laurent, James Glass
We propose a simple and effective cross-lingual transfer learning method to adapt monolingual wav2vec-2.0 models for Automatic Speech Recognition (ASR) in resource-scarce languages…
End-to-end speaker segmentation for overlap-aware resegmentation
Hervé Bredin, Antoine Laurent
Speaker segmentation consists in partitioning a conversation between one or more speakers into speaker turns. Usually addressed as the late combination of three sub-tasks (voice ac…
End2End Acoustic to Semantic Transduction
Valentin Pelloin, Nathalie Camelin, Antoine Laurent +4
In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features…
CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learning
Sameer Khurana, Antoine Laurent, James Glass
More than half of the 7,000 languages in the world are in imminent danger of going extinct. Traditional methods of documenting language proceed by collecting audio data followed by…
A Convolutional Deep Markov Model for Unsupervised Speech Representation Learning
Sameer Khurana, Antoine Laurent, Wei-Ning Hsu +4
Probabilistic Latent Variable Models (LVMs) provide an alternative to self-supervised learning approaches for linguistic representation learning from speech. LVMs admit an intuitiv…
Robust Training of Vector Quantized Bottleneck Models
Adrian Łańcucki, Jan Chorowski, Guillaume Sanchez +6
In this paper we demonstrate methods for reliable and efficient training of discrete representation using Vector-Quantized Variational Auto-Encoder models (VQ-VAEs). Discrete laten…
Recent Advances in End-to-End Spoken Language Understanding
Natalia Tomashenko, Antoine Caubriere, Yannick Esteve +2
This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single e…
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability
Antoine Caubrière, Natalia Tomashenko, Antoine Laurent +3
We present an end-to-end approach to extract semantic concepts directly from the speech audio signal. To overcome the lack of data available for this spoken language understanding…
End-to-end named entity extraction from speech
Sahar Ghannay, Antoine Caubrière, Yannick Estève +2
Named entity recognition (NER) is among SLU tasks that usually extract semantic information from textual documents. Until now, NER from speech is made through a pipeline process th…