Search Results for author: Salah Zaiem

Found 17 papers, 9 papers with code

Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations

no code implementations30 Jun 2024 Salah Zaiem, Titouan Parcollet, Slim Essid

Despite being trained on massive and diverse datasets, speech self-supervised encoders are generally used for downstream purposes as mere frozen feature extractors or model initializers before fine-tuning.

Continual Learning Domain Generalization +2

Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences

1 code implementation22 Sep 2023 Hugo Malard, Salah Zaiem, Robin Algayres

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Leveraging Data Collection and Unsupervised Learning for Code-switched Tunisian Arabic Automatic Speech Recognition

no code implementations20 Sep 2023 Ahmed Amine Ben Abdallah, Ata Kabboudi, Amir Kanoun, Salah Zaiem

Crafting an effective Automatic Speech Recognition (ASR) solution for dialects demands innovative approaches that not only address the data scarcity issue but also navigate the intricacies of linguistic diversity.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

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

1 code implementation18 Sep 2023 George August Wright, Umberto Cappellazzo, Salah Zaiem, Desh Raj, Lucas Ondel Yang, Daniele Falavigna, Mohamed Nabih Ali, Alessio Brutti

In self-attention models for automatic speech recognition (ASR), early-exit architectures enable the development of dynamic models capable of adapting their size and architecture to varying levels of computational resources and ASR performance demands.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads

no code implementations28 Aug 2023 Salah Zaiem, Youcef Kemiche, Titouan Parcollet, Slim Essid, Mirco Ravanelli

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data.

Benchmarking Self-Supervised Learning

Automatic Data Augmentation for Domain Adapted Fine-Tuning of Self-Supervised Speech Representations

no code implementations1 Jun 2023 Salah Zaiem, Titouan Parcollet, Slim Essid

Self-Supervised Learning (SSL) has allowed leveraging large amounts of unlabeled speech data to improve the performance of speech recognition models even with small annotated datasets.

Data Augmentation Domain Adaptation +3

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?

1 code implementation1 Jun 2023 Salah Zaiem, Youcef Kemiche, Titouan Parcollet, Slim Essid, Mirco Ravanelli

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on speech tasks using only small amounts of annotated data.

Benchmarking Decoder +1

Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning

1 code implementation8 Apr 2022 Salah Zaiem, Titouan Parcollet, Slim Essid

Thus, this work introduces a conditional independance-based method which allows for automatically selecting a suitable distribution on the choice of augmentations and their parametrization from a set of predefined ones, for contrastive self-supervised pre-training.

Contrastive Learning Data Augmentation +2

Pretext Tasks selection for multitask self-supervised speech representation learning

1 code implementation1 Jul 2021 Salah Zaiem, Titouan Parcollet, Slim Essid, Abdel Heba

Through solving pretext tasks, self-supervised learning leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +6

End-to-End Speech Recognition from Federated Acoustic Models

1 code implementation29 Apr 2021 Yan Gao, Titouan Parcollet, Salah Zaiem, Javier Fernandez-Marques, Pedro P. B. de Gusmao, Daniel J. Beutel, Nicholas D. Lane

Training Automatic Speech Recognition (ASR) models under federated learning (FL) settings has attracted a lot of attention recently.

2k 4k +4

Conditional independence for pretext task selection in Self-supervised speech representation learning

1 code implementation15 Apr 2021 Salah Zaiem, Titouan Parcollet, Slim Essid

Through solving pretext tasks, self-supervised learning (SSL) leverages unlabeled data to extract useful latent representations replacing traditional input features in the downstream task.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +6

Sequence to Sequence Learning for Query Expansion

no code implementations25 Dec 2018 Salah Zaiem, Fatiha Sadat

Using sequence to sequence algorithms for query expansion has not been explored yet in Information Retrieval literature nor in Question-Answering's.

Information Retrieval Keyword Extraction +3

Cannot find the paper you are looking for? You can Submit a new open access paper.