paper-with-me

Papers

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

2023-06-01 · 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. The high number of proposed approaches fostered the need and rise of extended benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, and while the number of considered tasks has been growing, most rely upon a single decoding architecture that maps the frozen SSL representations to the downstream labels. This work investigates the robustness of such benchmarking results to changes in the decoder architecture. Interestingly, it appears that varying the architecture of the downstream decoder leads to significant variations in the leaderboards of most tasks. Concerningly, our study reveals that benchmarking using limited decoders may cause a counterproductive increase in the sizes of the developed SSL models.

📄 PDF Abstract BibTeX arXiv:2306.00452

Code (1)

salah-zaiem/speechbrain-2 공식 구현 pytorch

Tasks

BenchmarkingDecoderSelf-Supervised Learning

Similar Papers 제목 키워드 기반

MT4SSL: Boosting Self-Supervised Speech Representation Learning by Integrating Multiple Targets

2022-11-14 · Ziyang Ma, Zhisheng Zheng, Changli Tang, Yujin Wang 외

In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extr…

Automatic Speech RecognitionMulti-Task LearningRepresentation LearningSelf-Supervised Learning+2

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

2023-08-28 · Salah Zaiem, Youcef Kemiche, Titouan Parcollet, Slim Essid 외

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotated data. The high number of proposed approaches fostered the emergence of compreh…

BenchmarkingSelf-Supervised Learning

Self-Supervised Speech Representation Learning: A Review

2022-05-21 · Abdelrahman Mohamed, Hung-Yi Lee, Lasse Borgholt, Jakob D. Havtorn 외

Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply th…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)BenchmarkingRepresentation Learning+3

Selective HuBERT: Self-Supervised Pre-Training for Target Speaker in Clean and Mixture Speech

2023-11-08 · Jingru Lin, Meng Ge, Wupeng Wang, Haizhou Li 외

Self-supervised pre-trained speech models were shown effective for various downstream speech processing tasks. Since they are mainly pre-trained to map input speech to pseudo-labels, the resulting representations are onl…

Speech Analysis of Language Varieties in Italy

2024-06-22 · Moreno La Quatra, Alkis Koudounas, Elena Baralis, Sabato Marco Siniscalchi

Italy exhibits rich linguistic diversity across its territory due to the distinct regional languages spoken in different areas. Recent advances in self-supervised learning provide new opportunities to analyze Italy's lin…

Contrastive LearningSelf-Supervised Learning