Personal information

Emails & domains

Verified email addresses

Websites & social links

Webpage
Github

Keywords

artificial-intelligence, machine-learning, deep-learning, audio, audio-classification, sound-event-recognition, audio-captioning, text-generation, natural-language-processing

Countries

France

Activities

Collapse all

Employment (2)

Laboratoire Cognition, Langues, Langage, Ergonomie: Toulouse, FR

2024-07-01 to 2024-12-31 | CNRS Research Engineer on TIRIS-SILENCE project
Employment
Source: Self-asserted source
Étienne Labbé

Institut de Recherche en Informatique de Toulouse: Toulouse, Occitanie, FR

2020-10-01 to 2024-06-30 | PhD student (SAMoVA team)
Employment
Source: Self-asserted source
Étienne Labbé

Works (12)

CoNeTTE: An Efficient Audio Captioning System Leveraging Multiple Datasets With Task Embedding

IEEE/ACM Transactions on Audio, Speech, and Language Processing
2024 | Journal article
DOI: 10.1109/TASLP.2024.3430813
Contributors: Étienne Labbé; Thomas Pellegrini; Julien Pinquier
Source: check_circle
Crossref

Automated audio captioning with deep learning methods

2024-04-03 | Dissertation or Thesis
HAL: tel-04642941
Contributors: Etienne Labbé
Source: Self-asserted source
Étienne Labbé via HAL

Multilingual Audio Captioning using machine translated data

2023-09 | Working paper
HAL: hal-04220315
Contributors: Matéo Cousin; Etienne Labbé; Thomas Pellegrini
Source: Self-asserted source
Étienne Labbé via HAL

Killing two birds with one stone: can an audio captioning system also be used for audio-test retrieval?

2023-09-20 | Conference paper
HAL: hal-04180972
Contributors: Etienne Labbé; Thomas Pellegrini; Julien Pinquier
Source: Self-asserted source
Étienne Labbé via HAL

Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer

2023-09-08 | Conference paper
DOI: 10.48550/arXiv.2305.01482
HAL: hal-04207519
ARXIV: 2305.01482
ARXIV: 2305.01482
Contributors: Etienne Labbé; Julien Pinquier; Thomas Pellegrini
Source: Self-asserted source
Étienne Labbé via HAL

CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding

2023-09-01 | Working paper
HAL: hal-04193791
ARXIV: 2309.00454
ARXIV: 2309.00454
Contributors: Etienne Labbé; Thomas Pellegrini; Julien Pinquier
Source: Self-asserted source
Étienne Labbé via HAL

Adapting a ConvNeXt Model to Audio Classification on AudioSet

INTERSPEECH 2023
2023-08-20 | Conference paper
DOI: 10.21437/interspeech.2023-1564
Contributors: Thomas Pellegrini; Ismail Khalfaoui-Hassani; Etienne Labbé; Timothée Masquelier
Source: Self-asserted source
Étienne Labbé

IRIT-UPS DCASE 2023 AUDIO CAPTIONING AND RETRIEVAL SYSTEM

IRIT
2023-06 | Report
Source: Self-asserted source
Étienne Labbé

Comparison of semi-supervised deep learning algorithms for audio classification

EURASIP Journal on Audio, Speech, and Music Processing
2022 | Journal article
DOI: 10.1186/s13636-022-00255-6
Part of ISSN: 1687-4722
Contributors: Cances, Léo; Labbé, Etienne; Pellegrini, Thomas
Source: Self-asserted source
Étienne Labbé

Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates

2022-11-03 | Conference paper
HAL: hal-03810396
Contributors: Etienne Labbé; Thomas Pellegrini; Julien Pinquier
Source: Self-asserted source
Étienne Labbé via HAL

IRIT-UPS DCASE 2022 task6a system: stochastic decoding methods for audio captioning

2022-06 | Report
Contributors: Étienne Labbé
Source: Self-asserted source
Étienne Labbé

IRIT-UPS DCASE 2021 Audio Captioning System

2021-06 | Report
Contributors: Étienne Labbé
Source: Self-asserted source
Étienne Labbé
How many people are using ORCID?