Exchanges for SPEech ReseArch aNd TechnOlogies

CORDIS fournit des liens vers les livrables publics et les publications des projets HORIZON.

Les liens vers les livrables et les publications des projets du 7e PC, ainsi que les liens vers certains types de résultats spécifiques tels que les jeux de données et les logiciels, sont récupérés dynamiquement sur OpenAIRE .

Livrables

Communication and Dissemination Plan

Organise communication activities, workshops, courses and other knowledge share actions. Ensure that the dissemination is compliant with open access requirements.

Report on four workshops

4 workshops will take place annually either in the US, in collaboration with JSALT workshops and in Europe, in Le Mans. A report will be writen after each workshop and a final report will be delivered after the fourth workshop.

Guidance for evaluation of explainability in speech

Description of protocols, metrics and scenarios to evaluate explainability of speech algorithms for different speech processing tasks.

Description of explainability for speech

This deliverable will provide a list and description of criteria for explainability in the context of speech processing

Scientific dissemination guidelines

Identify partners specificities and needs Writing guidelines to the attention of partners to ensure an active and coherent communication activity among countries

Guidance for evaluation with low resources

Description of protocols, metrics and scenarios designed to evaluate different systems for different speech tasks with low resources.

Solutions for corpus augmentation

Esperanto partners will study various methods to make use of limited corpora and artificially or automatically extend those corpora.This deliverable will report methods and performance of various approaches that can generalize well from only a few examples and can leverage diverse types of knowledge, such as typological information, annotated data from other languages or domains, unlabelled data, or multimodal data.

International open challenges for HAL speech processing

Esperanto consortium will organize open international research challenges to encourage and evaluate human assisted learning systems. Organisation of challenges will include the development of new metrics and protocols to evaluate human assisted learning systems in a fair and reproducible environment.

Guidance for evaluation of human assisted learning

Description of protocols, metrics and scenarios designed to evaluate different modes of human assisted learning (active learning, interactive learning) for different speech tasks.

Project website and visual identity

Setting up a visual identity and a website presenting to the general public the objectives of the project, its partners and the main tools employed. The website will also be a resource for the partners for all that concerns good practices.

Corpora for under-resource task

Esperanto will support the collection or extension of several corpora for under-resourced tasks such as a corpus for pronunciation evaluation and a corpus of pathological speech.

Corpora for under-resourced languages

ESPERANTO will create and extend corpora for under-resourced languages such as African languages including Ewondo, Féfé, Fufuldé, as well as Arabic Tunisian dialect.

Methods for explainability by design (SDK)

Implementation of various architecture designed for explainability. This SDK will include various modules designed to be shared amongst speech processing tasks to highlight the part of the incoming data that leads to the resulting decision and identify and characterize the bias induced in the system.

SDK for human assisted learning speech processing

Software library developed in open-source licence to tackle to issue of human assisted learning for various tasks of speech processing such as speaker diarization, speaker verification, speech translation of speech recognition.

Models that learn from small data

To deal with under-resource task, this deliverable will implement different approaches dealing with low or zero resource learning such as transfer learning and modeling based on the same information shared between languages or tasks, approaches that do not need annotated data, use of expert knowledge in empirical systems, systems using multimodal data for semantic supervision.

Publications

Cross-Corpus Speech Emotion Recognition with HuBERT Self-Supervised Representation

Auteurs: Miguel Pastor; Dayana Ribas; Alfonso Ortega; Antonio Miguel; Eduardo Lleida
Publié dans: Proc. IberSPEECH, Numéro 12, 2022
Éditeur: ISCA
DOI: 10.21437/iberspeech.2022-16

Multi-Channel Speaker Verification with Conv-Tasnet Based Beamformer

Auteurs: Mošner Ladislav, Plchot Oldřich, Burget Lukáš, Černocký Jan
Publié dans: Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, Page(s) 7982-7986, ISBN 978-1-6654-0540-9
Éditeur: IEEE Signal Processing Society
DOI: 10.1109/icassp43922.2022.9747771

A transfer learning based approach for pronunciation scoring

Auteurs: Sancinetti, Marcelo; Vidal, Jazmin; Bonomi, Cyntia; Ferrer, Luciana
Publié dans: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numéro 4, 2022, Page(s) 6812-6816, ISBN 978-1-6654-0540-9
Éditeur: IEEE
DOI: 10.48550/arxiv.2111.00976

Microphone Array Channel Combination Algorithms for Overlapped Speech Detection

Auteurs: Theo Mariotte; Anthony Larcher; Silvio Montrésor; Jean-Hugh Thomas
Publié dans: Interspeech 2022 Human and Humanizing Speech Technology, Numéro 12, 2022
Éditeur: ISCA
DOI: 10.21437/interspeech.2022-10758

Log-Likelihood-Ratio Cost Function as Objective Loss for Speaker Verification Systems

Auteurs: Victoria Mingote, Antonio Miguel, Alfonso Ortega, Eduardo Lleida
Publié dans: Interspeech 2021, 2021, Page(s) 2361-2365
Éditeur: ISCA
DOI: 10.21437/interspeech.2021-1085

Explainable by-design Audio Segmentation through Non-Negative Matrix Factorization and Probing

Auteurs: Martin Lebourdais, Théo Mariotte, Antonio Almudévar, Marie Tahon, Alfonso Ortega
Publié dans: Interspeech 2024, 2024, Page(s) 4753-4757
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-791

Extracting Speaker and Emotion Information from Self-Supervised Speech Models via Channel-Wise Correlations

Auteurs: Themos Stafylakis; Ladislav Mosner; Sofoklis Kakouros; Oldrich Plchot; Lukas Burget; Jan Cernocky
Publié dans: 2022 IEEE Spoken Language Technology Workshop (SLT), Numéro 22, 2023, ISBN 979-8-3503-9690-4
Éditeur: IEEE
DOI: 10.1109/slt54892.2023.10023345

ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection

Auteurs: Marie Tahon, Anthony Larcher, Martin Lebourdais, Fethi Bougares, Anna Silnova, Pablo Gimeno
Publié dans: Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024),, 2024
Éditeur: LREC-COLING

Learnable Sparse Filterbank for Speaker Verification

Auteurs: PENG Junyi, GU Rongzhi, MOŠNER Ladislav, PLCHOT Oldřich, BURGET Lukáš and ČERNOCKÝ Jan.
Publié dans: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Numéro "ISSN = ""1990-9772""", 2022, Page(s) 5110-5114
Éditeur: International Speech Communication Association (ISCA)
DOI: 10.21437/interspeech.2022-11309

Analysis of the domain mismatch problem in the Speech Emotion Recognition Task

Auteurs: Miguel A. Pastor, Alfonso Ortega, Dayana Ribas
Publié dans: IberSPEECH 2024, 2024, Page(s) 181-185
Éditeur: ISCA
DOI: 10.21437/iberspeech.2024-37

On the Use of Semantically-Aligned Speech Representations for Spoken Language Understanding

Auteurs: Gaelle Laperriere; Valentin Pelloin; Mickael Rouvier; Themos Stafylakis; Yannick Esteve
Publié dans: 2022 IEEE Spoken Language Technology Workshop (SLT), Numéro 24, 2023
Éditeur: IEEE
DOI: 10.1109/slt54892.2023.10023013

Multisv: Dataset for Far-Field Multi-Channel Speaker Verification

Auteurs: Mošner Ladislav, Plchot Oldřich, Burget Lukáš, Černocký Jan
Publié dans: Proceedings of ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, Page(s) 7977-7981, ISBN 978-1-6654-0540-9
Éditeur: IEEE Signal Processing Society
DOI: 10.1109/icassp43922.2022.9746833

Probabilistic Spherical Discriminant Analysis: An Alternative to PLDA for length-normalized embeddings.

Auteurs: BRUMMER Johan Nikolaas Langenhoven, SWART Albert du Preez, MOŠNER Ladislav, SILNOVA Anna, PLCHOT Oldřich, STAFYLAKIS Themos and BURGET Lukáš.
Publié dans: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH., Numéro "ISSN = ""1990-9772""", 2022, Page(s) 1446-1450
Éditeur: International Speech Communication Association (ISCA)
DOI: 10.21437/interspeech.2022-731

Speaker Embeddings for Diarization of Broadcast Data In The Allies Challenge

Auteurs: Anthony Larcher; Ambuj Mehrish; Marie Tahon; Sylvain Meignier; Jean Carrive; David Doukhan; Olivier Galibert; Nicholas Evans
Publié dans: ICASSP, Numéro 1, 2021
Éditeur: IEEE
DOI: 10.1109/icassp39728.2021.9414215

Semantic Enrichment Towards Efficient Speech Representations

Auteurs: Gaëlle Laperrière; Ha Nguyen; Sahar Ghannay; Bassam Jabaian; Yannick Estève
Publié dans: Proc. INTERSPEECH 2023, 2023, Page(s) 705-709, ISSN 1990-9772
Éditeur: ISCA
DOI: 10.21437/interspeech.2023-2234

S3prl-Disorder: Open-Source Voice Disorder Detection System based in the Framework of S3PRL-toolkit

Auteurs: Dayana Ribas, Miguel Angel Pastor Yoldi, Antonio Miguel, David Martínez, Alfonso Ortega, Eduardo Lleida
Publié dans: IberSPEECH 2022, 2024, Page(s) 136-140
Éditeur: ISCA
DOI: 10.21437/iberspeech.2022-28

Speech-Based Emotion Recognition with Self-Supervised Models Using Attentive Channel-Wise Correlations and Label Smoothing

Auteurs: Sofoklis Kakouros; Themos Stafylakis; Ladislav Mošner; Lukáš Burget
Publié dans: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numéro 19, 2023, Page(s) pp. 1-5, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10094673

Multi-Channel Speech Separation with Cross-Attention and Beamforming

Auteurs: "Ladislav Mosner, Oldřich Plchot, Junyi Peng, Lukáš Burget, Jan ""Honza"" Černocký"
Publié dans: Proc. INTERSPEECH 2023, 2023, Page(s) 693-1697, ISSN 1990-9772
Éditeur: International Speech Communication Association
DOI: 10.21437/interspeech.2023-2537

Predefined Prototypes for Intra-Class Separation and Disentanglement

Auteurs: Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon, Luis Vicente, Antonio Miguel, Eduardo Lleida
Publié dans: Interspeech 2024, 2024, Page(s) 3809-3813
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-825

Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?

Auteurs: Lin Zhang, Themos Stafylakis, Federico Landini, Mireia Diez, Anna Silnova, Lukáš Burget
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 123-130
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-18

Speaker Embeddings by Modeling Channel-Wise Correlations

Auteurs: Themos Stafylakis, Johan Rohdin, Lukáš Burget
Publié dans: Interspeech 2021, 2021, Page(s) 501-505
Éditeur: ISCA
DOI: 10.21437/interspeech.2021-1442

A Study on the Use of wav2vec Representations for Multiclass Audio Segmentation

Auteurs: Pablo Gimeno; Alfonso Ortega; Antonio Miguel; Eduardo Lleida
Publié dans: Proc. IberSPEECH2022, Numéro 8, 2022, Page(s) 56-60
Éditeur: ISCA
DOI: 10.21437/iberspeech.2022-12

End-to-End Speech Translation of Arabic to English Broadcast News

Auteurs: Fethi Bougares; Salim Jouili
Publié dans: WANLP@ACL 2022: Abu Dhabi, United Arab Emirates, Numéro 5, 2022, Page(s) 312–319, ISBN 978-1-959429-27-2
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2022.wanlp-1.29

A Phonetic Analysis of Speaker Verification Systems through Phoneme selection and Integrated Gradients

Auteurs: Thomas Thebaud, Gabriel Hernández, Sarah Flora Samson Juan, Marie Tahon
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 59-66
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-9

Improving Prosodic Features Extraction for Tone Detection in Yemba Language

Auteurs: Sturm, Kenfack Jeuguim Marc; Paulin, Melatagia Yonta
Publié dans: CCIS, Numéro 17, 2024, ISBN 978-0-7961-6069-0
Éditeur: Southern African Conference for Artificial Intelligence Research
DOI: 10.5281/zenodo.10174710

A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding

Auteurs: Gaëlle Laperrière, Sahar Ghannay, Bassam Jabaian, Yannick Estève
Publié dans: Interspeech 2024, 2024, Page(s) 812-816
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-1133

Leveraging Self-Supervised Learning for Speaker Diarization

Auteurs: Jiangyu Han, Federico Landini, Johan Rohdin, Anna Silnova, Mireia Diez, Lukáš Burget
Publié dans: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025, Page(s) 1-5
Éditeur: IEEE
DOI: 10.1109/icassp49660.2025.10889475

Improving Speaker Verification with Self-Pretrained Transformer Models

Auteurs: "Junyi Peng, Oldřich Plchot, Themos Stafylakis, Ladislav Mosner, Lukáš Burget, Jan ""Honza"" Černocký"
Publié dans: Proc. INTERSPEECH 2023, 2023, Page(s) 5361-5365, ISSN 1990-9772
Éditeur: International Speech Communication Association
DOI: 10.21437/interspeech.2023-453

Training Speaker Embedding Extractors Using Multi-Speaker Audio with Unknown Speaker Boundaries.

Auteurs: STAFYLAKIS Themos, MOŠNER Ladislav, PLCHOT Oldřich, ROHDIN Johan A., SILNOVA Anna, BURGET Lukáš and ČERNOCKÝ Jan.
Publié dans: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Numéro "ISSN = ""1990-9772""", 2022, Page(s) 605-609
Éditeur: International Speech Communication Association (ISCA)
DOI: 10.21437/interspeech.2022-10165

BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge

Auteurs: Alexander Polok, Dominik Klement, Jiangyu Han, Šimon Sedláček, Bolaji Yusuf, Matthew Maciejewski, Matthew S Wiesner, Lukáš Burget
Publié dans: 8th International Workshop on Speech Processing in Everyday Environments (CHiME 2024), 2024, Page(s) 18-22
Éditeur: ISCA
DOI: 10.21437/chime.2024-4

Unsupervised multiple domain translation through controlled Disentanglement in variational autoencoder

Auteurs: Antonio Almudévar, Théo Mariotte, Alfonso Ortega, Marie Tahon
Publié dans: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, Page(s) 7010-7014
Éditeur: IEEE
DOI: 10.1109/icassp48485.2024.10446649

Improving Speaker Diarization for Low-Resourced Sarawak Malay Language Conversational Speech Corpus

Auteurs: Mohd Zulhafiz Rahim; Sarah Samson Juan; Fitri Suraya Mohamad
Publié dans: 2023 International Conference on Asian Language Processing (IALP), 2023, Page(s) 228-233
Éditeur: IEEE
DOI: 10.1109/ialp61005.2023.10337314

Multi-Speaker and Wide-Band Simulated Conversations as Training Data for End-to-End Neural Diarization

Auteurs: Federico Landini; Mireia Diez; Alicia Lozano-Diez; Lukáš Burget
Publié dans: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numéro 6, 2023, Page(s) 1-5, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10097049

Description and Analysis of ABC Submission to NIST LRE 2022

Auteurs: Pavel Matejka, Anna Silnova, Josef Slavíček, Ladislav Mosner, Oldřich Plchot, Michal Klčo, Junyi Peng, Themos Stafylakis, Lukáš Burget
Publié dans: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, 2023, Page(s) 511-515, ISSN 1990-9772
Éditeur: International Speech Communication Association
DOI: 10.21437/interspeech.2023-1529

An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification

Auteurs: Junyi Peng; Oldrich Plchot; Themos Stafylakis; Ladislav Mosner; Lukas Burget; Jan Cernocky
Publié dans: 2022 IEEE Spoken Language Technology Workshop (SLT), Numéro 5, 2023, Page(s) 555-562, ISBN 979-8-3503-9690-4
Éditeur: IEEE
DOI: 10.1109/slt54892.2023.10022775

Improved Vocal Effort Transfer Vector Estimation For Vocal Effort-Robust Speaker Verification

Auteurs: Iván López-Espejo, Santi Prieto, Alfonso Ortega, Eduardo Lleida
Publié dans: 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP), 2023, Page(s) 1-6
Éditeur: IEEE
DOI: 10.1109/mlsp55844.2023.10285923

Active Correction for Incremental Speaker Diarization of a Collection with Human in the Loop

Auteurs: Larcher, Yevhenii Prokopalo; Meysam Shamsi; Loïc Barrault; Sylvain Meignier; Anthony
Publié dans: Applied Sciences; Volume 12; Numéro 4;, Numéro 20, 2022, Page(s) Pages: 1782, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app12041782

Diacorrect: Error Correction Back-End for Speaker Diarization

Auteurs: Jiangyu Han, Federico Landini, Johan Rohdin, Mireia Diez, Lukáš Burget, Yuhang Cao, Heng Lu, Jan Černocký
Publié dans: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024, Page(s) 11181-11185
Éditeur: IEEE
DOI: 10.1109/icassp48485.2024.10446968

Unsupervised Representation Learning for Speech Activity Detection in the Fearless Steps Challenge 2021

Auteurs: Pablo Gimeno, Alfonso Ortega, Antonio Miguel, Eduardo Lleida
Publié dans: Interspeech 2021, 2021, Page(s) 4359-4363
Éditeur: ISCA
DOI: 10.21437/interspeech.2021-309

An Explainable Proxy Model for Multilabel Audio Segmentation

Auteurs: Mariotte, Théo; Almudévar, Antonio; Tahon, Marie; Ortega, Alfonso
Publié dans: International Conference on Acoustics Speech and Signal Processing, IEEE, Apr 2024, Seoul (Korea), Numéro 5, 2024
Éditeur: IEEE Signal Processing Society
DOI: 10.1109/icassp48485.2024.10446648

Lifelong Learning MOS Prediction for Synthetic Speech Quality Evaluation

Auteurs: Félix Saget, Meysam Shamsi, Marie Tahon
Publié dans: Interspeech 2024, 2024, Page(s) 1220-1224
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-959

Analyzing speaker verification embedding extractors and back-ends under language and channel mismatch

Auteurs: SILNOVA Anna, STAFYLAKIS Themos, MOŠNER Ladislav, PLCHOT Oldřich, ROHDIN Johan A., MATĚJKA Pavel, BURGET Lukáš, GLEMBEK Ondřej a BRUMMER Johan Nikolaas Langenhoven.
Publié dans: Proceedings of The Speaker and Language Recognition Workshop (Odyssey 2022), 2022, Page(s) 9-16
Éditeur: International Speech Communication Association (ISCA)
DOI: 10.21437/odyssey.2022-2

EnCodecMAE: leveraging neural codecs for universal audio representation learning

Auteurs: Leonardo Pepino, Pablo Riera, Luciana Ferrer
Publié dans: Interspeech 2025, 2025, Page(s) 3519-3523
Éditeur: ISCA
DOI: 10.21437/interspeech.2025-506

Toroidal Probabilistic Spherical Discriminant Analysis

Auteurs: Anna Silnova; Niko Brümmer; Albert Swart; Lukáš Burget
Publié dans: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numéro 2, 2023, Page(s) 1-5, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10095580

The ViVoLab System for the Odyssey Emotion Recognition Challenge 2024 Evaluation

Auteurs: Miguel Ángel Pastor, Alfonso Ortega, Antonio Miguel, Dayana Ribas
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 274-280
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-39

Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction

Auteurs: Sergio Burdisso, Srikanth Madikeri, Petr Motlicek
Publié dans: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024, Page(s) 5421-5440
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.emnlp-main.310

Automatic Voice Identification after Speech Resynthesis using PPG

Auteurs: Thibault Gaudier, Marie Tahon, Anthony Larcher, Yannick Estève
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 187-193
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-27

Cross-Lingual Transfer Learning for Low-Resource Speech Translation

Auteurs: Sameer Khurana, Nauman Dawalatabad, Antoine Laurent, Luis Vicente, Pablo Gimeno, Victoria Mingote, James Glass
Publié dans: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2024, Page(s) 670-674
Éditeur: IEEE
DOI: 10.1109/icasspw62465.2024.10626683

3MAS: a multitask, multilabel, multidataset semi-supervised audio segmentation model

Auteurs: Martin Lebourdais, Pablo Gimeno, Théo Mariotte, Marie Tahon, Alfonso Ortega, Anthony Larcher
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 232-239
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-33

The CONILIUM proposition for Odyssey Emotion Challenge : Leveraging major class with complex annotations

Auteurs: Meysam Shamsi, Lara Gauder, Marie Tahon
Publié dans: The Speaker and Language Recognition Workshop (Odyssey 2024), 2024, Page(s) 281-287
Éditeur: ISCA
DOI: 10.21437/odyssey.2024-40

Challenging margin-based speaker embedding extractors by using the variational information bottleneck

Auteurs: Themos Stafylakis, Anna Silnova, Johan Rohdin, Oldřich Plchot, Lukáš Burget
Publié dans: Interspeech 2024, 2024, Page(s) 3220-3224
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-2058

Sur la vérification du locuteur à partir de traces d’exécution de modèles acoustiques personnalisés

Auteurs: Tomashenko, Natalia; Mdhaffar, Salima; Tommasi, Marc; Estève, Yannick; Bonastre, Jean-François
Publié dans: Journées d'Études sur la Parole - JEP2022, Jun 2022, Île de Noirmoutier, France, Numéro 13, 2022
Éditeur: ISCA
DOI: 10.21437/jep.2022-91

ON-TRAC Consortium Systems for the IWSLT 2023 Dialectal and Low-resource Speech Translation Tasks

Auteurs: Antoine Laurent, Souhir Gahbiche, Ha Nguyen, Haroun Elleuch, Fethi Bougares, Antoine Thiol, Hugo Riguidel, Salima Mdhaffar, Gaëlle Laperrière, Lucas Maison, Sameer Khurana, Yannick Estève
Publié dans: Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), 2023, Page(s) 219–226, ISBN 2-9517408-4-0
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2023.iwslt-1.18

Strategies for Improving Low Resource Speech to Text Translation Relying on Pre-trained ASR Models

Auteurs: Santosh Kesiraju; Marek Sarvaš; Tomáš Pavlíček; Cécile Macaire; Alejandro Ciuba
Publié dans: Proc. INTERSPEECH 2023, Numéro 14, 2023, Page(s) 2148--2152, ISSN 1990-9772
Éditeur: ISCA
DOI: 10.21437/interspeech.2023-2506

Discriminative Training of VBx Diarization

Auteurs: Klement, Dominik; Diez, Mireia; Landini, Federico; Burget, Lukáš; Silnova, Anna; Delcroix, Marc; Tawara, Naohiro
Publié dans: Crossref, Numéro 5, 2024
Éditeur: IEEE
DOI: 10.1109/icassp48485.2024.10446119

BUT CHiME-7 system description

Auteurs: Karafiát, Martin; Veselý, Karel; Szöke, Igor; Mošner, Ladislav; Beneš, Karel; Witkowski, Marcin; Barchi, Germán; Pepino, Leonardo
Publié dans: CHiME-7 proceedings, Numéro 8, 2023
Éditeur: arxiv
DOI: 10.48550/arxiv.2310.11921

Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect

Auteurs: Salima Mdhaffar, Haroun Elleuch, Fethi Bougares, Yannick Estève
Publié dans: Proceedings of The Second Arabic Natural Language Processing Conference, 2024, Page(s) 130-139
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2024.arabicnlp-1.12

Development of ABC systems for the 2021 edition of NIST Speaker Recognition Evaluation

Auteurs: ALAM Jahangir, BURGET Lukáš, GLEMBEK Ondřej, MATĚJKA Pavel, MOŠNER Ladislav, PLCHOT Oldřich, ROHDIN Johan A., SILNOVA Anna and STAFYLAKIS Themos et al.
Publié dans: Proceedings of The Speaker and Language Recognition Workshop (Odyssey 2022), 2022, Page(s) 346-353
Éditeur: International Speech Communication Association (ISCA)
DOI: 10.21437/odyssey.2022-48

ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings

Auteurs: Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas
Publié dans: Interspeech 2024, 2024, Page(s) 1620-1624
Éditeur: ISCA
DOI: 10.21437/interspeech.2024-917

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters

Auteurs: Junyi Peng; Themos Stafylakis; Rongzhi Gu; Oldřich Plchot; Ladislav Mošner; Lukáš Burget; Jan Černocký
Publié dans: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Numéro 6, 2023, Page(s) 1-5, ISBN 978-1-7281-6327-7
Éditeur: IEEE
DOI: 10.1109/icassp49357.2023.10094795

Automatic Speech Interruption Detection: Analysis, Corpus, and System

Auteurs: Lebourdais, Martin; Tahon, Marie; Laurent, Antoine; Meignier, Sylvain
Publié dans: Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-Coling 2024), Numéro 21, 2024
Éditeur: ELRA and ICCL

Generalizing AUC Optimization to Multiclass Classification for Audio Segmentation With Limited Training Data

Auteurs: Pablo Gimeno; Victoria Mingote; Alfonso Ortega; Antonio Miguel; Eduardo Lleida
Publié dans: IEEE Signal Processing Letters, Numéro 4, 2021, Page(s) 1135 - 1139, ISSN 1070-9908
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2021.3084501

YembaTones: a syllable-tone annotated dataset for speech recognition and prosodic analysis of the Yemba language.

Auteurs: Kenfack Jeuguim Marc Sturm; Paulin Melatagia Yonta; Sandembouo Etienne
Publié dans: Data in Brief, Numéro 11, 2023, ISSN 2352-3409
Éditeur: Elsevier BV
DOI: 10.1016/j.dib.2023.109860

Towards Lifelong Human Assisted Speaker Diarization

Auteurs: Meysam Shamsi; Anthony Larcher; Loic Barrault; Sylvain Meignier; Yevheni Prokopalo; Marie Tahon; Ambuj Mehrish; Simon Petitrenaud; Olivier Galibert; Samuel Gaist; André Anjos; Sebastien Marcel; Marta R. Costa-jussà
Publié dans: Computer Speech & Language, Numéro 4, 2023, ISSN 0885-2308
Éditeur: Academic Press
DOI: 10.1016/j.csl.2022.101437

aDCF Loss Function for Deep Metric Learning in End-to-End Text-Dependent Speaker Verification Systems

Auteurs: Victoria Mingote; Antonio Miguel; Dayana Ribas; Alfonso Ortega; Eduardo Lleida
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 25 January 2022, 2022, Page(s) 772-784, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2022.3145307

Direct Text to Speech Translation System Using Acoustic Units

Auteurs: Victoria Mingote, Pablo Gimeno, Luis Vicente, Sameer Khurana, Antoine Laurent and Jarod Duret
Publié dans: IEEE Signal Processing Letters, Numéro vol. 30, 2023, Page(s) 1262-1266, ISSN 1070-9908
Éditeur: Institute of Electrical and Electronics Engineers
DOI: 10.1109/lsp.2023.3313513

An Overview of the IberSpeech-RTVE 2022 Challenges on Speech Technologies

Auteurs: Eduardo Lleida; Luis Javier Rodriguez-Fuentes; Javier Tejedor; Alfonso Ortega; Antonio Miguel; Virginia Bazán; Carmen Pérez; Alberto de Prada; Mikel Penagarikano; Amparo Varona; Germán Bordel; Doroteo Torre-Toledano; Aitor Álvarez; Haritz Arzelus
Publié dans: Applied Sciences; Volume 13; Numéro 15;, Numéro 5, 2023, Page(s) Pages: 8577, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app13158577

Application of the multilingual acoustic representation model XLSR for the transcription of Ewondo

Auteurs: Nzeuhang Yannick Yomie, Yonta Paulin Melatagia, Lecouteux Benjamin
Publié dans: Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, Numéro Volume 42 - Special issue CRI..., 2024, ISSN 1638-5713
Éditeur: Centre pour la Communication Scientifique Directe (CCSD)
DOI: 10.46298/arima.13621

Class token and knowledge distillation for multi-head self-attention speaker verification systems

Auteurs: Victoria Mingote; Antonio Miguel; Alfonso Ortega; Eduardo Lleida
Publié dans: Digital Signal Processing, Numéro 6, 2023, ISSN 1051-2004
Éditeur: Academic Press
DOI: 10.1016/j.dsp.2022.103859

Evaluating Posterior Probabilities: Decision Theory, Proper Scoring Rules, and Calibration

Auteurs: Ferrer, Luciana; Ramos, Daniel
Publié dans: back arrowBack to Homepage Transactions on Machine Learning Research, Numéro 14, 2025, ISSN 2835-8856
Éditeur: TMLR

Multimodal Diarization Systems by Training Enrollment Models as Identity Representations

Auteurs: Victoria Mingote; Ignacio Viñals; Pablo Gimeno; Antonio Miguel; Alfonso Ortega; Eduardo Lleida
Publié dans: Applied Sciences, Numéro 12-3, 2022, Page(s) 1141, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app12031141

Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detection

Auteurs: Théo Mariotte, Anthony Larcher, Silvio Montrésor, Jean-Hugh Thomas
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 32, 2024, Page(s) 1859-1872, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2024.3369531

pathfinder: A Semantic Framework for Literature Review and Knowledge Discovery in Astronomy

Auteurs: Kartheik G. Iyer, Mikaeel Yunus, Charles O’Neill, Christine Ye, Alina Hyk, Kiera McCormick, Ioana Ciucă, John F. Wu, Alberto Accomazzi, Simone Astarita, Rishabh Chakrabarty, Jesse Cranney, Anjalie
Publié dans: The Astrophysical Journal Supplement Series, Numéro 275, 2024, Page(s) 38, ISSN 0067-0049
Éditeur: University of Chicago Press
DOI: 10.3847/1538-4365/ad7c43

Wiener Filter and Deep Neural Networks: A Well-Balanced Pair for Speech Enhancement

Auteurs: Dayana Ribas; Antonio Miguel; Alfonso Ortega; Eduardo Lleida
Publié dans: Applied Sciences, Numéro 3 ; Volume 12; Numéro 18;, 2022, Page(s) Pages: 9000, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app12189000

Automatic Voice Disorder Detection Using Self-Supervised Representations

Auteurs: Dayana Ribas; Miguel A. Pastor; Antonio Miguel; David Martinez; Alfonso Ortega; Eduardo Lleida
Publié dans: IEEE Access, Numéro 6, 2023, Page(s) 14915-14927,, ISSN 2169-3536
Éditeur: Institute of Electrical and Electronics Engineers Inc.
DOI: 10.1109/access.2023.3243986

Cross-Corpus Training Strategy for Speech Emotion Recognition Using Self-Supervised Representations

Auteurs: Miguel A. Pastor; Dayana Ribas; Alfonso Ortega; Antonio Miguel; Eduardo Lleida
Publié dans: Applied Sciences, Numéro 13, 2023, Page(s) 9062, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app13169062

Unsupervised Adaptation of Deep Speech Activity Detection Models to Unseen Domains

Auteurs: Pablo Gimeno; Dayana Ribas; Alfonso Ortega; Antonio Miguel; Eduardo Lleida
Publié dans: Applied Sciences, Numéro 3, 2022, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app12041832

DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors

Auteurs: Federico Landini, Mireia Diez, Themos Stafylakis, Lukáš Burget
Publié dans: IEEE/ACM Transactions on Audio, Speech, and Language Processing, Numéro 32, 2024, Page(s) 3450-3465, ISSN 2329-9290
Éditeur: IEEE Advancing Technology for Humanity
DOI: 10.1109/taslp.2024.3422818

The Domain Mismatch Problem in the Broadcast Speaker Attribution Task

Auteurs: Ignacio Viñals, Alfonso Ortega, Antonio Miguel, Eduardo Lleida
Publié dans: Applied Sciences, Numéro 11/18, 2021, Page(s) 8521, ISSN 2076-3417
Éditeur: MDPI
DOI: 10.3390/app11188521

Automatic Voice Disorder Detection from a Practical Perspective

Auteurs: Jazmin Vidal, Dayana Ribas, Cyntia Bonomi, Eduardo Lleida, Luciana Ferrer, Alfonso Ortega
Publié dans: Journal of Voice, 2024, ISSN 0892-1997
Éditeur: Mosby Inc.
DOI: 10.1016/j.jvoice.2024.03.001

Recherche de données OpenAIRE...

Livrables

Publications

Partager cette page Partager cette page sur les réseaux sociaux

Télécharger Télécharger le contenu de la page