Search Results for author:
Found 123 papers, 41 papers with code
Phone Based Keyword Spotting for Transcribing Very Low Resource Languages
We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust speech recognition system.
Joint ASR and MT Features for Quality Estimation in Spoken Language Translation
This paper aims to unravel the automatic quality assessment for spoken language translation (SLT).
Fashioning Local Designs from Generic Speech Technologies in an Australian Aboriginal Community
An increasing number of papers have been addressing issues related to low-resource languages and the transcription bottleneck paradigm.
Learning From Failure: Data Capture in an Australian Aboriginal Community
Most low resource language technology development is premised on the need to collect data for training statistical models.
Weakly Supervised Word Segmentation for Computational Language Documentation
Word and morpheme segmentation are fundamental steps of language documentation as they allow to discover lexical units in a language for which the lexicon is unknown.
Visualizing Cross‐Lingual Discourse Relations in Multilingual TED Corpora
This paper presents an interactive data dashboard that provides users with an overview of the preservation of discourse relations among 28 language pairs.
Findings of the WMT Shared Task on Machine Translation Using Terminologies
Language domains that require very careful use of terminology are abundant and reflect a significant part of the translation industry.
Contribution d’informations syntaxiques aux capacités de généralisation compositionelle des modèles seq2seq convolutifs (Assessing the Contribution of Syntactic Information for Compositional Generalization of seq2seq Convolutional Networks)
Le jeu de données SCAN, constitué d’un ensemble de commandes en langage naturel associées à des séquences d’action, a été spécifiquement conçu pour évaluer les capacités des réseaux de neurones à apprendre ce type de généralisation compositionnelle.
Investigating the Impact of Gender Representation in ASR Training Data: a Case Study on Librispeech
In this paper we question the impact of gender representation in training data on the performance of an end-to-end ASR system.
Controlling Prosody in End-to-End TTS: A Case Study on Contrastive Focus Generation
In this paper, we investigate whether we can control prosody directly from the input text, in order to code information related to contrastive focus which emphasizes a specific word that is contrary to the presuppositions of the interlocutor.
Monolingual Adapters for Zero-Shot Neural Machine Translation
We propose a novel adapter layer formalism for adapting multilingual models.
Using ASR-Generated Text for Spoken Language Modeling
This papers aims at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
Speech Foundation Models and Crowdsourcing for Efficient, High-Quality Data Collection
While crowdsourcing is an established solution for facilitating and scaling the collection of speech data, the involvement of non-experts necessitates protocols to ensure final data quality.
Speech-MASSIVE: A Multilingual Speech Dataset for SLU and Beyond
We present Speech-MASSIVE, a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus.
mHuBERT-147: A Compact Multilingual HuBERT Model
We present mHuBERT-147, the first general-purpose massively multilingual HuBERT speech representation model trained on 90K hours of clean, open-license data.
ELITR-Bench: A Meeting Assistant Benchmark for Long-Context Language Models
Research on Large Language Models (LLMs) has recently witnessed an increasing interest in extending the models' context size to better capture dependencies within long documents.
LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech
Self-supervised learning (SSL) is at the origin of unprecedented improvements in many different domains including computer vision and natural language processing.
Encoding Sentence Position in Context-Aware Neural Machine Translation with Concatenation
Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture.
Focused Concatenation for Context-Aware Neural Machine Translation
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its context concatenated to it.
A Textless Metric for Speech-to-Speech Comparison
In this paper, we introduce a new and simple method for comparing speech utterances without relying on text transcripts.
SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languages
In recent years, multilingual machine translation models have achieved promising performance on low-resource language pairs by sharing information between similar languages, thus enabling zero-shot translation.
ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model
We collect a corpus of utterances containing contrastive focus and we evaluate the accuracy of a BERT model, finetuned to predict quantized acoustic prominence features, on these samples.
What Do Compressed Multilingual Machine Translation Models Forget?
In this work, we assess the impact of compression methods on Multilingual Neural Machine Translation models (MNMT) for various language groups, gender, and semantic biases by extensive analysis of compressed models on different machine translation benchmarks, i. e. FLORES-101, MT-Gender, and DiBiMT.
A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
These models are pre-trained on unlabeled audio data and then used in speech processing downstream tasks such as automatic speech recognition (ASR) or speech translation (ST).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters
We consider the problem of multilingual unsupervised machine translation, translating to and from languages that only have monolingual data by using auxiliary parallel language pairs.
On the Evaluation of Machine Translation for Terminology Consistency
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.
Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings
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.
Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings
Our results suggest that neural models for speech discretization are difficult to exploit in our setting, and that it might be necessary to adapt them to limit sequence length.
Lightweight Adapter Tuning for Multilingual Speech Translation
Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP.
Ranked #1 on
Speech-to-Text Translation
on MuST-C EN->ES
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Do Multilingual Neural Machine Translation Models Contain Language Pair Specific Attention Heads?
Recent studies on the analysis of the multilingual representations focus on identifying whether there is an emergence of language-independent representations, or whether a multilingual model partitions its weights among different languages.
Impact of Encoding and Segmentation Strategies on End-to-End Simultaneous Speech Translation
Boosted by the simultaneous translation shared task at IWSLT 2020, promising end-to-end online speech translation approaches were recently proposed.
LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
In this paper, we propose LeBenchmark: a reproducible framework for assessing SSL from speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Models
Multi-encoder models are a broad family of context-aware neural machine translation systems that aim to improve translation quality by encoding document-level contextual information alongside the current sentence.
Fast Development of ASR in African Languages using Self Supervised Speech Representation Learning
This paper describes the results of an informal collaboration launched during the African Master of Machine Intelligence (AMMI) in June 2020.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
An Empirical Study of End-to-end Simultaneous Speech Translation Decoding Strategies
This paper proposes a decoding strategy for end-to-end simultaneous speech translation.
Alternate Endings: Improving Prosody for Incremental Neural TTS with Predicted Future Text Input
The prosody of a spoken word is determined by its surrounding context.
User-friendly automatic transcription of low-resource languages: Plugging ESPnet into Elpis
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 recognition toolkit.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Enabling Interactive Transcription in an Indigenous Community
We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment.
Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation
We propose two variants of these architectures corresponding to two different levels of dependencies between the decoders, called the parallel and cross dual-decoder Transformers, respectively.
Ranked #1 on
Speech-to-Text Translation
on MuST-C EN->FR
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
We present the Zero Resource Speech Challenge 2020, which aims at learning speech representations from raw audio signals without any labels.
What the Future Brings: Investigating the Impact of Lookahead for Incremental Neural TTS
In this paper, we study the behavior of a neural sequence-to-sequence TTS system when used in an incremental mode, i. e. when generating speech output for token n, the system has access to n + k tokens from the text sequence.
Catplayinginthesnow: Impact of Prior Segmentation on a Model of Visually Grounded Speech
The language acquisition literature shows that children do not build their lexicon by segmenting the spoken input into phonemes and then building up words from them, but rather adopt a top-down approach and start by segmenting word-like units and then break them down into smaller units.
ConfNet2Seq: Full Length Answer Generation from Spoken Questions
This is the first attempt towards generating full-length natural answers from a graph input(confusion network) to the best of our knowledge.
FlauBERT : des mod\`eles de langue contextualis\'es pr\'e-entra\^\in\'es pour le fran\ccais (FlauBERT : Unsupervised Language Model Pre-training for French)
Les mod{\`e}les de langue pr{\'e}-entra{\^\i}n{\'e}s sont d{\'e}sormais indispensables pour obtenir des r{\'e}sultats {\`a} l{'}{\'e}tat-de-l{'}art dans de nombreuses t{\^a}ches du TALN.
Pratiques d'\'evaluation en ASR et biais de performance (Evaluation methodology in ASR and performance bias)
Nous proposons une r{\'e}flexion sur les pratiques d{'}{\'e}valuation des syst{\`e}mes de reconnaissance automatique de la parole (ASR).
Repr\'esentation du genre dans des donn\'ees open source de parole (Gender representation in open source speech resources 1 With the rise of artificial intelligence (AI) and the growing use of deep-learning architectures, the question of ethics and transparency in AI systems has become a central concern within the research community)
Avec l{'}essor de l{'}intelligence artificielle (IA) et l{'}utilisation croissante des architectures d{'}apprentissage profond, la question de l{'}{\'e}thique et de la transparence des syst{\`e}mes d{'}IA est devenue une pr{\'e}occupation centrale au sein de la communaut{\'e} de recherche.
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English
We conduct in this work an evaluation study comparing offline and online neural machine translation architectures.
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation.
Efficient Wait-k Models for Simultaneous Machine Translation
We also show that the 2D-convolution architecture is competitive with Transformers for simultaneous translation of spoken language.
Investigating Language Impact in Bilingual Approaches for Computational Language Documentation
For answering this question, we use the MaSS multilingual speech corpus (Boito et al., 2020) for creating 56 bilingual pairs that we apply to the task of low-resource unsupervised word segmentation and alignment.
Gender Representation in Open Source Speech Resources
With the rise of artificial intelligence (AI) and the growing use of deep-learning architectures, the question of ethics, transparency and fairness of AI systems has become a central concern within the research community.
A Data Efficient End-To-End Spoken Language Understanding Architecture
For that, in many cases, models are combined with an external language model to enhance their performance.
Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks
Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue.
FlauBERT: Unsupervised Language Model Pre-training for French
Language models have become a key step to achieve state-of-the art results in many different Natural Language Processing (NLP) tasks.
Ranked #2 on
Natural Language Inference
on XNLI French
Character-based NMT with Transformer
Character-based translation has several appealing advantages, but its performance is in general worse than a carefully tuned BPE baseline.
The LIG system for the English-Czech Text Translation Task of IWSLT 2019
Therefore, we implemented a Transformer-based encoder-decoder neural system which is able to use the output of a pre-trained language model as input embeddings, and we compared its performance under three configurations: 1) without any pre-trained language model (constrained), 2) using a language model trained on the monolingual parts of the allowed English-Czech data (constrained), and 3) using a language model trained on a large quantity of external monolingual data (unconstrained).
Naver Labs Europe's Systems for the Document-Level Generation and Translation Task at WNGT 2019
To address these challenges, we propose to leverage data from both tasks and do transfer learning between MT, NLG, and MT with source-side metadata (MT+NLG).
ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task
This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English-to-Portuguese language pair.
Controlling Utterance Length in NMT-based Word Segmentation with Attention
One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream.
How Does Language Influence Documentation Workflow? Unsupervised Word Discovery Using Translations in Multiple Languages
For language documentation initiatives, transcription is an expensive resource: one minute of audio is estimated to take one hour and a half on average of a linguist's work (Austin and Sallabank, 2013).
Improved Training Techniques for Online Neural Machine Translation
We investigate the sensitivity of such models to the value of k that is used during training and when deploying the model, and the effect of updating the hidden states in transformer models as new source tokens are read.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Word Recognition, Competition, and Activation in a Model of Visually Grounded Speech
In this paper, we study how word-like units are represented and activated in a recurrent neural model of visually grounded speech.
Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance
The disparity of available data for both gender causes performance to decrease on women.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MaSS: A Large and Clean Multilingual Corpus of Sentence-aligned Spoken Utterances Extracted from the Bible
However, the fact that the source content (the Bible) is the same for all the languages is not exploited to date. Therefore, this article proposes to add multilingual links between speech segments in different languages, and shares a large and clean dataset of 8, 130 parallel spoken utterances across 8 languages (56 language pairs).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Empirical Evaluation of Sequence-to-Sequence Models for Word Discovery in Low-resource Settings
This task consists in aligning word sequences in a source language with phoneme sequences in a target language, inferring from it word segmentation on the target side [5].
The Zero Resource Speech Challenge 2019: TTS without T
We present the Zero Resource Speech Challenge 2019, which proposes to build a speech synthesizer without any text or phonetic labels: hence, TTS without T (text-to-speech without text).
Models of Visually Grounded Speech Signal Pay Attention To Nouns: a Bilingual Experiment on English and Japanese
We investigate the behaviour of attention in neural models of visually grounded speech trained on two languages: English and Japanese.
Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation
In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i. e. human transcriptions, instead of Automatic Speech Recognition (ASR)'s transcriptions.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Analyzing Learned Representations of a Deep ASR Performance Prediction Model
In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate.
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding.
Ranked #2 on
Machine Translation
on IWSLT2015 German-English
A small Griko-Italian speech translation corpus
This paper presents an extension to a very low-resource parallel corpus collected in an endangered language, Griko, making it useful for computational research.
Unsupervised Word Segmentation from Speech with Attention
We present a first attempt to perform attentional word segmentation directly from the speech signal, with the final goal to automatically identify lexical units in a low-resource, unwritten language (UL).
Token-level and sequence-level loss smoothing for RNN language models
We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach.
ASR Performance Prediction on Unseen Broadcast Programs using Convolutional Neural Networks
In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs.
Bayesian Models for Unit Discovery on a Very Low Resource Language
Developing speech technologies for low-resource languages has become a very active research field over the last decade.
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop
We summarize the accomplishments of a multi-disciplinary workshop exploring the computational and scientific issues surrounding the discovery of linguistic units (subwords and words) in a language without orthography.
End-to-End Automatic Speech Translation of Audiobooks
We investigate end-to-end speech-to-text translation on a corpus of audiobooks specifically augmented for this task.
Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation
However, while large quantities of parallel texts (such as Europarl, OpenSubtitles) are available for training machine translation systems, there are no large (100h) and open source parallel corpora that include speech in a source language aligned to text in a target language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
The Zero Resource Speech Challenge 2017
We describe a new challenge aimed at discovering subword and word units from raw speech.
Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models
Word discovery is the task of extracting words from unsegmented text.
Disentangling ASR and MT Errors in Speech Translation
This enables - as a by-product - qualitative analysis on the SLT errors and their origin (are they due to transcription or to translation step?)
Amharic-English Speech Translation in Tourism Domain
This paper describes speech translation from Amharic-to-English, particularly Automatic Speech Recognition (ASR) with post-editing feature and Amharic-English Statistical Machine Translation (SMT).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set
Disfluencies and speed perturbation are added to the signal in order to sound more natural.
LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task
This paper presents the LIG-CRIStAL submission to the shared Automatic Post- Editing task of WMT 2017.
Traitement des Mots Hors Vocabulaire pour la Traduction Automatique de Document OCRis\'es en Arabe (This article presents a new system that automatically translates images of arabic documents)
Les exp{\'e}rimentations sont r{\'e}alis{\'e}s sur un corpus de journaux num{\'e}ris{\'e}s en arabe et permettent d{'}obtenir des am{\'e}liorations en score BLEU de 3, 73 et 5, 5 sur les corpus de d{\'e}veloppement et de test respectivement.
Machine Assisted Analysis of Vowel Length Contrasts in Wolof
Growing digital archives and improving algorithms for automatic analysis of text and speech create new research opportunities for fundamental research in phonetics.
Deep Investigation of Cross-Language Plagiarism Detection Methods
This paper is a deep investigation of cross-language plagiarism detection methods on a new recently introduced open dataset, which contains parallel and comparable collections of documents with multiple characteristics (different genres, languages and sizes of texts).
CompiLIG at SemEval-2017 Task 1: Cross-Language Plagiarism Detection Methods for Semantic Textual Similarity
We present our submitted systems for Semantic Textual Similarity (STS) Track 4 at SemEval-2017.
Using Word Embedding for Cross-Language Plagiarism Detection
This paper proposes to use distributed representation of words (word embeddings) in cross-language textual similarity detection.
First Automatic Fongbe Continuous Speech Recognition System: Development of Acoustic Models and Language Models
This paper reports our efforts toward an ASR system for a new under-resourced language (Fongbe).
Ranked #1 on
Speech Recognition
on Fongbe audio
Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation
This paper proposes a first attempt to build an end-to-end speech-to-text translation system, which does not use source language transcription during learning or decoding.
Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?
This paper presents an approach combining lexico-semantic resources and distributed representations of words applied to the evaluation in machine translation (MT).
Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks
This work focuses on the rapid development of linguistic annotation tools for resource-poor languages.
Automatic Quality Assessment for Speech Translation Using Joint ASR and MT Features
This paper addresses automatic quality assessment of spoken language translation (SLT).
Word2Vec vs DBnary ou comment (r\'e)concilier repr\'esentations distribu\'ees et r\'eseaux lexico-s\'emantiques ? Le cas de l'\'evaluation en traduction automatique (Word2Vec vs DBnary or how to bring back together vector representations and lexical resources ? A case study for machine translation evaluation)
Cet article pr{\'e}sente une approche associant r{\'e}seaux lexico-s{\'e}mantiques et repr{\'e}sentations distribu{\'e}es de mots appliqu{\'e}e {\`a} l{'}{\'e}valuation de la traduction automatique.
Projection Interlingue d'\'Etiquettes pour l'Annotation S\'emantique Non Supervis\'ee (Cross-lingual Annotation Projection for Unsupervised Semantic Tagging)
Dans une pr{\'e}c{\'e}dente contribution, nous avons propos{\'e} une m{\'e}thode pour la construction automatique d{'}un analyseur morpho-syntaxique via une projection interlingue d{'}annotations linguistiques {\`a} partir de corpus parall{\`e}les (m{\'e}thode fond{\'e}e sur les r{\'e}seaux de neurones r{\'e}currents).
MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP
We present MultiVec, a new toolkit for computing continuous representations for text at different granularity levels (word-level or sequences of words).
A Multilingual, Multi-style and Multi-granularity Dataset for Cross-language Textual Similarity Detection
In this paper we describe our effort to create a dataset for the evaluation of cross-language textual similarity detection.
Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of Wolof
This article presents the data collected and ASR systems developped for 4 sub-saharan african languages (Swahili, Hausa, Amharic and Wolof).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media Documents
In this paper, we describe the organization and the implementation of the CAMOMILE collaborative annotation framework for multimodal, multimedia, multilingual (3M) data.
Utilisation des r\'eseaux de neurones r\'ecurrents pour la projection interlingue d'\'etiquettes morpho-syntaxiques \`a partir d'un corpus parall\`ele
La construction d{'}outils d{'}analyse linguistique pour les langues faiblement dot{\'e}es est limit{\'e}e, entre autres, par le manque de corpus annot{\'e}s. Dans cet article, nous proposons une m{\'e}thode pour construire automatiquement des outils d{'}analyse via une projection interlingue d{'}annotations linguistiques en utilisant des corpus parall{\`e}les.
Utilisation de mesures de confiance pour am\'eliorer le d\'ecodage en traduction de parole
Les mesures de confiance au niveau mot (Word Confidence Estimation - WCE) pour la traduction auto- matique (TA) ou pour la reconnaissance automatique de la parole (RAP) attribuent un score de confiance {\`a} chaque mot dans une hypoth{\`e}se de transcription ou de traduction.
Collection of a Large Database of French-English SMT Output Corrections
We also post-edited 1, 500 gold-standard reference translations (of bilingual parallel corpora generated by professional) and noticed that 72 {\%} of these translations needed to be corrected during post-edition.
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corpora
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken language understanding systems.
