paper-with-me

홈 › Papers

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition

2021-10-09 · Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-wen Yang, Yu Tsao, Hung-Yi Lee, Shinji Watanabe

Self-supervised pretraining on speech data has achieved a lot of progress. High-fidelity representation of the speech signal is learned from a lot of untranscribed data and shows promising performance. Recently, there are several works focusing on evaluating the quality of self-supervised pretrained representations on various tasks without domain restriction, e.g. SUPERB. However, such evaluations do not provide a comprehensive comparison among many ASR benchmark corpora. In this paper, we focus on the general applications of pretrained speech representations, on advanced end-to-end automatic speech recognition (E2E-ASR) models. We select several pretrained speech representations and present the experimental results on various open-source and publicly available corpora for E2E-ASR. Without any modification of the back-end model architectures or training strategy, some of the experiments with pretrained representations, e.g., WSJ, WSJ0-2mix with HuBERT, reach or outperform current state-of-the-art (SOTA) recognition performance. Moreover, we further explore more scenarios for whether the pretraining representations are effective, such as the cross-language or overlapped speech. The scripts, configuratons and the trained models have been released in ESPnet to let the community reproduce our experiments and improve them.

📄 PDF Abstract BibTeX arXiv:2110.04590

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

PReLU A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values.…
Hierarchical Feature Fusion Hierarchical Feature Fusion (HFF) is a feature fusion method employed in ESP and EESP image…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Kaiming Initialization 설명 없음
Dilated Convolution 설명 없음
ESP 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Pretrained self-supervised speech models can recognize unseen consonants

2026-06-10 · Chihiro Taguchi, Éric Le Ferrand, Hirosi Nakagawa, Hitomi Ono 외 arxiv

Modern pretrained self-supervised automatic speech recognition models are trained on large-scale audio data to encode speech into contextualized representations. However, their training data are heavily skewed toward hig…

Speech Recognition

Probing for Phonology in Self-Supervised Speech Representations: A Case Study on Accent Perception

2025-06-21 · Nitin Venkateswaran, Kevin Tang, Ratree Wayland

Traditional models of accent perception underestimate the role of gradient variations in phonological features which listeners rely upon for their accent judgments. We investigate how pretrained representations from curr…

Self-Supervised Learning

Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation

2020-05-18 · Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh 외

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order t…

Self-Supervised LearningSpeaker Identification

Exploring Representation Learning for Small-Footprint Keyword Spotting

2023-03-20 · Fan Cui, Liyong Guo, Quandong Wang, Peng Gao 외

In this paper, we investigate representation learning for low-resource keyword spotting (KWS). The main challenges of KWS are limited labeled data and limited available device resources. To address those challenges, we e…

Contrastive LearningKeyword SpottingRepresentation LearningSmall-Footprint Keyword Spotting

Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing

2025-01-10 · Eklavya Sarkar, Mathew Magimai. -Doss

Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrate…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognition+1