Search Results for author:
Found 27 papers, 11 papers with code
ON-TRAC’ systems for the IWSLT 2021 low-resource speech translation and multilingual speech translation shared tasks
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2021, low-resource speech translation and multilingual speech translation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
The VoicePrivacy 2024 Challenge Evaluation Plan
The task of the challenge is to develop a voice anonymization system for speech data which conceals the speaker's voice identity while protecting linguistic content and emotional states.
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.
Federated Learning for ASR based on Wav2vec 2.0
This paper presents a study on the use of federated learning to train an ASR model based on a wav2vec 2. 0 model pre-trained by self supervision.
The VoicePrivacy 2020 Challenge Evaluation Plan
The VoicePrivacy Challenge aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges.
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
The VoicePrivacy 2022 Challenge Evaluation Plan
Participants apply their developed anonymization systems, run evaluation scripts and submit objective evaluation results and anonymized speech data to the organizers.
Retrieving Speaker Information from Personalized Acoustic Models for Speech Recognition
The widespread of powerful personal devices capable of collecting voice of their users has opened the opportunity to build speaker adapted speech recognition system (ASR) or to participate to collaborative learning of ASR.
Privacy attacks for automatic speech recognition acoustic models in a federated learning framework
This paper investigates methods to effectively retrieve speaker information from the personalized speaker adapted neural network acoustic models (AMs) in automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
The VoicePrivacy 2020 Challenge: Results and findings
We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results.
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
Speaker anonymisation using the McAdams coefficient
Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating to intelligibility and naturalness.
Speech Pseudonymisation Assessment Using Voice Similarity Matrices
The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications.
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.
The Privacy ZEBRA: Zero Evidence Biometric Recognition Assessment
Mounting privacy legislation calls for the preservation of privacy in speech technology, though solutions are gravely lacking.
Cryptography and Security Audio and Speech Processing
Design Choices for X-vector Based Speaker Anonymization
The recently proposed x-vector based anonymization scheme converts any input voice into that of a random pseudo-speaker.
Introducing the VoicePrivacy Initiative
The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges.
Exploring Gaussian mixture model framework for speaker adaptation of deep neural network acoustic models
Experimental results on the TED-LIUM corpus show that the proposed adaptation technique can be effectively integrated into DNN and TDNN setups at different levels and provide additional gain in recognition performance: up to 6% of relative word error rate reduction (WERR) over the strong feature-space adaptation techniques based on maximum likelihood linear regression (fMLLR) speaker adapted DNN baseline, and up to 18% of relative WERR in comparison with a speaker independent (SI) DNN baseline model, trained on conventional features.
Dialogue history integration into end-to-end signal-to-concept spoken language understanding systems
The dialog history is represented in the form of dialog history embedding vectors (so-called h-vectors) and is provided as an additional information to end-to-end SLU models in order to improve the system performance.
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.
Recent Advances in End-to-End Spoken Language Understanding
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 end-to-end neural network model.
Curriculum d'apprentissage : reconnaissance d'entit\'es nomm\'ees pour l'extraction de concepts s\'emantiques (Curriculum learning : named entity recognition for semantic concept extraction)
Les r{\'e}sultats montrent un int{\'e}r{\^e}t {\`a} l{'}utilisation des donn{\'e}es d{'}entit{\'e}s nomm{\'e}es, permettant un gain relatif allant jusqu{'}{\`a} 6, 5 {\%}.
Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portability
We present an end-to-end approach to extract semantic concepts directly from the speech audio signal.
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation
We present the recent development on Automatic Speech Recognition (ASR) systems in comparison with the two previous releases of the TED-LIUM Corpus from 2012 and 2014.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Fast and Accurate OOV Decoder on High-Level Features
The proposed approach is based on using high-level features from an automatic speech recognition (ASR) system, so called phoneme posterior based (PPB) features, for decoding.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Exploration de param\`etres acoustiques d\'eriv\'es de GMM pour l'adaptation non supervis\'ee de mod\`eles acoustiques \`a base de r\'eseaux de neurones profonds (Exploring GMM-derived features for unsupervised adaptation of deep neural network acoustic models)
L{'}{\'e}tude pr{\'e}sent{\'e}e dans cet article am{\'e}liore une m{\'e}thode r{\'e}cemment propos{\'e}e pour l{'}adaptation de mod{\`e}les acoustiques markoviens coupl{\'e}s {\`a} un r{\'e}seau de neurones profond (DNN-HMM).
