116 citations · 441 across the 62 of their papers we have counts for
71 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…
Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation
Lorenzo Lupo, Marco Dinarelli, Laurent Besacier
Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive i…
Focused Concatenation for Context-Aware Neural Machine Translation
Lorenzo Lupo, Marco Dinarelli, Laurent Besacier
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed…
SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages
Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard +3
In recent years, multilingual machine translation models have achieved promising performance on low-resource language pairs by sharing information between similar languages, thus e…
A Textless Metric for Speech-to-Speech Comparison
Laurent Besacier, Swen Ribeiro, Olivier Galibert +1
In this paper, we introduce a new and simple method for comparing speech utterances without relying on text transcripts. Our speech-to-speech comparison metric utilizes state-of-th…
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…
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
Brooke Stephenson, Laurent Besacier, Laurent Girin +1
Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have exp…
What Do Compressed Multilingual Machine Translation Models Forget?
Alireza Mohammadshahi, Vassilina Nikoulina, Alexandre Berard +3
Recently, very large pre-trained models achieve state-of-the-art results in various natural language processing (NLP) tasks, but their size makes it more challenging to apply them…
A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
Marcely Zanon Boito, Laurent Besacier, Natalia Tomashenko +1
Self-supervised models for speech processing emerged recently as popular foundation blocks in speech processing pipelines. These models are pre-trained on unlabeled audio data and…
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters
Ahmet Üstün, Alexandre Bérard, Laurent Besacier +1
We consider the problem of multilingual unsupervised machine translation, translating to and from languages that only have monolingual data by using auxiliary parallel language pai…
Lightweight Adapter Tuning for Multilingual Speech Translation
Hang Le, Juan Pino, Changhan Wang +3
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pretrained parameters of a model and injecting light…
On the Evaluation of Machine Translation for Terminology Consistency
Md Mahfuz ibn Alam, Antonios Anastasopoulos, Laurent Besacier +4
As neural machine translation (NMT) systems become an important part of professional translator pipelines, a growing body of work focuses on combining NMT with terminologies. In ma…
Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings
Éric Le Ferrand, Steven Bird, Laurent Besacier
We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust ASR system. This wo…
Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings
Marcely Zanon Boito, Bolaji Yusuf, Lucas Ondel +2
Documenting languages helps to prevent the extinction of endangered dialects, many of which are otherwise expected to disappear by the end of the century. When documenting oral lan…
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
Zae Myung Kim, Laurent Besacier, Vassilina Nikoulina +1
Recent studies on the analysis of the multilingual representations focus on identifying whether there is an emergence of language-independent representations, or whether a multilin…
Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation
Ha Nguyen, Yannick Estève, Laurent Besacier
Boosted by the simultaneous translation shared task at IWSLT 2020, promising end-to-end online speech translation approaches were recently proposed. They consist in incrementally e…
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…
Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning
Jama Hussein Mohamud, Lloyd Acquaye Thompson, Aissatou Ndoye +1
This paper describes the results of an informal collaboration launched during the African Master of Machine Intelligence (AMMI) in June 2020. After a series of lectures and labs on…
An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies
Ha Nguyen, Yannick Estève, Laurent Besacier
This paper proposes a decoding strategy for end-to-end simultaneous speech translation. We leverage end-to-end models trained in offline mode and conduct an empirical study for two…
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
Oliver Adams, Benjamin Galliot, Guillaume Wisniewski +11
This paper reports on progress integrating the speech recognition toolkit ESPnet into Elpis, a web front-end originally designed to provide access to the Kaldi automatic speech rec…
Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input
Brooke Stephenson, Thomas Hueber, Laurent Girin +1
The prosody of a spoken word is determined by its surrounding context. In incremental text-to-speech synthesis, where the synthesizer produces an output before it has access to the…
Enabling Interactive Transcription in an Indigenous Community
Éric Le Ferrand, Steven Bird, Laurent Besacier
We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-reso…
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
Hang Le, Juan Pino, Changhan Wang +3
We introduce dual-decoder Transformer, a new model architecture that jointly performs automatic speech recognition (ASR) and multilingual speech translation (ST). Our models are ba…
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…