Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Autor: Wright, George August, Cappellazzo, Umberto, Zaiem, Salah, Raj, Desh, Yang, Lucas Ondel, Falavigna, Daniele, Ali, Mohamed Nabih, Brutti, Alessio

The ability to dynamically adjust the computational load of neural models during inference is crucial for on-device processing scenarios characterised by limited and time-varying computational resources. A promising solution is presented by early-exi

Externí odkaz: http://arxiv.org/abs/2309.09546

Speech Technology for Unwritten Languages

Autor: Mark Hasegawa-Johnson, Lucas Ondel, Elin Larsen, Shruti Palaskar, Liming Wang, Sebastian Stüker, Francesco Ciannella, Markus Müller, Odette Scharenborg, Rachid Riad, Florian Metze, Pierre Godard, Laurent Besacier, Mingxing Du, Alan W. Black, Danny Merkx, Emmanuel Dupoux, Philip Arthur, Graham Neubig

Publikováno v: IEEE/ACM Transactions on Audio, Speech and Language Processing
IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, ⟨10.1109/TASLP.2020.2973896⟩
IEEE/ACM Transactions on Audio Speech and Language Processing, 28, 964-975
IEEE/ACM Transactions on Audio Speech and Language Processing, 28, pp. 964-975
IEEE/ACM Transactions on Audio, Speech and Language Processing, Institute of Electrical and Electronics Engineers, 2020, ⟨10.1109/TASLP.2020.2973896⟩
IEEE-ACM Transactions on Audio, Speech, and Language Processing, 28

International audience; Speech technology plays an important role in our everyday life. Speech is, among others, used for human-computer interaction, including, for instance, information retrieval and on-line shopping. In the case of an unwritten lan

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91e8981c6d7470b56776e09c0e74b11f
https://doi.org/10.1109/taslp.2020.2973896

GPU-Accelerated Forward-Backward algorithm with Application to Lattice-Free MMI

Autor: Lucas Ondel, Lea-Marie Lam-Yee-Mui, Martin Kocour, Caio Filippo Corro, Lukas Burget

We propose to express the forward-backward algorithm in terms of operations between sparse matrices in a specific semiring. This new perspective naturally leads to a GPU-friendly algorithm which is easy to implement in Julia or any programming langua

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e8380c4a73b81e01ce353d81c07d41c9

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

Autor: Murat Saraclar, Lucas Ondel, Jan Cernocky, Lukas Burget, Bolaji Yusuf

Publikováno v: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, Toronto, Canada
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
ICASSP

In this work, we propose a hierarchical subspace model for acoustic unit discovery. In this approach, we frame the task as one of learning embeddings on a low-dimensional phonetic subspace, and simultaneously specify the subspace itself as an embeddi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bc2c07e978fdaf90ef01c29eab033583

The Zero Resource Speech Challenge 2019: TTS without T

Autor: Julien Karadayi, Laurent Besacier, Lucas Ondel, Ewan Dunbar, Mathieu Bernard, Charlotte Dugrain, Juan Benjumea, Robin Algayres, Xuan-Nga Cao, Alan W. Black, Lucie Miskic, Emmanuel Dupoux, Sakriani Sakti

Publikováno v: Interspeech 2019-20th Annual Conference of the International Speech Communication Association
Interspeech 2019-20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria
Interspeech 2019
HAL
INTERSPEECH

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). We provide raw audio for a target voice in an unknown language (

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70041f392a31bf9960c8122fb1de83d6
https://hal.archives-ouvertes.fr/hal-02274112