paper-with-me

Papers

Investigating the 'Autoencoder Behavior' in Speech Self-Supervised Models: a focus on HuBERT's Pretraining

2024-05-14 · Valentin Vielzeuf

Self-supervised learning has shown great success in Speech Recognition. However, it has been observed that finetuning all layers of the learned model leads to lower performance compared to resetting top layers. This phenomenon is attributed to the ''autoencoder'' behavior: top layers contain information closer to the input and are less suitable for tasks that require linguistic information, such as Speech Recognition.To better our understanding of this behavior, we propose to study the evolution of high-level information within the model during pretraining. We focus on the HuBERT model, which exhibits a less pronounced ''autoencoder'' behavior. By experimentally exploring various factors that may have an impact, we aim to improve the training procedure and enhance the top layers of HuBERT for high-level tasks.Furthermore, our experiments demonstrate that these improvements in the training procedure result in faster convergence and competitive performance on downstream tasks.

📄 PDF Abstract BibTeX arXiv:2405.08402

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learningspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

A vector quantized masked autoencoder for speech emotion recognition

2023-04-21 · Samir Sadok, Simon Leglaive, Renaud Séguier

Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the fie…

Emotion RecognitionSelf-Supervised LearningSpeech Emotion Recognition

A vector quantized masked autoencoder for audiovisual speech emotion recognition

2023-05-05 · Samir Sadok, Simon Leglaive, Renaud Séguier

An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoe…

Contrastive LearningEmotion RecognitionRepresentation LearningSelf-Supervised Learning+1

Investigating self-supervised front ends for speech spoofing countermeasures

2021-11-15 · Xin Wang, Junichi Yamagishi

Self-supervised speech model is a rapid progressing research topic, and many pre-trained models have been released and used in various down stream tasks. For speech anti-spoofing, most countermeasures (CMs) use signal pr…

Face Swapping

Masked Autoencoders as Universal Speech Enhancer

2026-02-02 · Rajalaxmi Rajagopalan, Ritwik Giri, Zhiqiang Tang, Kyu Han arxiv

Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable…

Self-Supervised LearningSpeech Enhancement

Investigating self-supervised learning for speech enhancement and separation

2022-03-15 · Zili Huang, Shinji Watanabe, Shu-wen Yang, Paola Garcia 외

Speech enhancement and separation are two fundamental tasks for robust speech processing. Speech enhancement suppresses background noise while speech separation extracts target speech from interfering speakers. Despite a…

Self-Supervised LearningSpeech EnhancementSpeech Separation