Search Results - "Zaiem, Salah"

DP-Parse: Finding Word Boundaries from Raw Speech with an Instance Lexicon by Algayres, Robin, Ricoul, Tristan, Karadayi, Julien, Laurençon, Hugo, Zaiem, Salah, Mohamed, Abdelrahman, Sagot, Benoît, Dupoux, Emmanuel

“…Finding word boundaries in continuous speech is challenging as there is little or no equivalent of a ‘space’ delimiter between words. Popular Bayesian…”
Get full text

Pretext Tasks Selection for Multitask Self-Supervised Audio Representation Learning by Zaiem, Salah, Parcollet, Titouan, Essid, Slim, Heba, Abdelwahab

“…Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features…”
Get full text

Speech self-supervised representations benchmarking: A case for larger probing heads by Zaiem, Salah, Kemiche, Youcef, Parcollet, Titouan, Essid, Slim, Ravanelli, Mirco

“…Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high…”
Get full text

Pretext Tasks selection for multitask self-supervised speech representation learning by Zaiem, Salah, Parcollet, Titouan, Essid, Slim, Heba, Abdelwahab

“…Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features…”
Get full text

Leveraging Data Collection and Unsupervised Learning for Code-Switched Tunisian Arabic Automatic Speech Recognition by Abdallah, Ahmed Amine Ben, Kabboudi, Ata, Kanoun, Amir, Zaiem, Salah

“…Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but…”
Get full text

CL-MASR: A Continual Learning Benchmark for Multilingual ASR by Della Libera, Luc, Mousavi, Pooneh, Zaiem, Salah, Subakan, Cem, Ravanelli, Mirco

“…Modern multilingual automatic speech recognition (ASR) systems like Whisper have made it possible to transcribe audio in multiple languages with a single…”
Get full text

End-to-End Speech Recognition from Federated Acoustic Models by Gao, Yan, Parcollet, Titouan, Zaiem, Salah, Fernandez-Marques, Javier, de Gusmao, Pedro P. B., Beutel, Daniel J., Lane, Nicholas D.

“…Training Automatic Speech Recognition (ASR) models under federated learning (FL) settings has attracted a lot of attention recently. However, the FL scenarios…”
Get full text

Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations by Zaiem, Salah, Parcollet, Titouan, Essid, Slim

“…Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature…”
Get full text

Fine-Tuning Strategies for Faster Inference Using Speech Self-Supervised Models: A Comparative Study by Zaiem, Salah, Algayres, Robin, Parcollet, Titouan, Essid, Slim, Ravanelli, Mirco

“…Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it…”
Get full text

Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences by Malard, Hugo, Zaiem, Salah, Algayres, Robin

“…Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of…”
Get full text

Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations by Zaiem, Salah, Parcollet, Titouan, Essid, Slim

“…Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with…”
Get full text

Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning by Zaiem, Salah, Parcollet, Titouan, Essid, Slim

“…Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent…”
Get full text

Sequence to Sequence Learning for Query Expansion by Zaiem, Salah, Sadat, Fatiha

“…Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering's. We tried…”
Get full text

Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition by Abdallah, Ahmed Amine Ben, Kabboudi, Ata, Kanoun, Amir, Zaiem, Salah

“…Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but…”
Get full text

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads by Zaiem, Salah, Kemiche, Youcef, Parcollet, Titouan, Essid, Slim, Ravanelli, Mirco

“…Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high…”
Get full text

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right? by Zaiem, Salah, Kemiche, Youcef, Parcollet, Titouan, Essid, Slim, Ravanelli, Mirco

“…INTERSPEECH 2023 Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on…”
Get full text

Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study by Zaiem, Salah, Algayres, Robin, Parcollet, Titouan, Essid, Slim, Ravanelli, Mirco

“…Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. In this context, it…”
Get full text

Conditional independence for pretext task selection in Self-supervised speech representation learning by Zaiem, Salah, Parcollet, Titouan, Essid, Slim

“…Through solving pretext tasks, self-supervised learning (SSL) leverages unlabeled data to extract useful latent representations replacing traditional input…”
Get full text

Pretext Tasks selection for multitask self-supervised speech representation learning by Zaiem, Salah, Parcollet, Titouan, Essid, Slim, Heba, Abdel

“…Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features…”
Get full text

How Should We Extract Discrete Audio Tokens from Self-Supervised Models? by Mousavi, Pooneh, Duret, Jarod, Zaiem, Salah, Della Libera, Luca, Ploujnikov, Artem, Subakan, Cem, Ravanelli, Mirco

“…Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audio tokens must…”
Get full text