paper-with-me

Papers

FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition

2022-06-30 · Szu-Jui Chen, Jiamin Xie, John H. L. Hansen

Self-supervised learning representations (SSLR) have resulted in robust features for downstream tasks in many fields. Recently, several SSLRs have shown promising results on automatic speech recognition (ASR) benchmark corpora. However, previous studies have only shown performance for solitary SSLRs as an input feature for ASR models. In this study, we propose to investigate the effectiveness of diverse SSLR combinations using various fusion methods within end-to-end (E2E) ASR models. In addition, we will show there are correlations between these extracted SSLRs. As such, we further propose a feature refinement loss for decorrelation to efficiently combine the set of input features. For evaluation, we show that the proposed 'FeaRLESS learning features' perform better than systems without the proposed feature refinement loss for both the WSJ and Fearless Steps Challenge (FSC) corpora.

📄 PDF Abstract BibTeX arXiv:2206.15056

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Self-Supervised Learningspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Scenario Aware Speech Recognition: Advancements for Apollo Fearless Steps & CHiME-4 Corpora

2021-09-23 · Szu-Jui Chen, Wei Xia, John H. L. Hansen

In this study, we propose to investigate triplet loss for the purpose of an alternative feature representation for ASR. We consider a general non-semantic speech representation, which is trained with a self-supervised cr…

speech-recognitionSpeech RecognitionTriplet

Fearless Steps Challenge Phase-1 Evaluation Plan

2022-11-03 · Aditya Joglekar, John H. L. Hansen

The Fearless Steps Challenge 2019 Phase-1 (FSC-P1) is the inaugural Challenge of the Fearless Steps Initiative hosted by the Center for Robust Speech Systems (CRSS) at the University of Texas at Dallas. The goal of this …

FEARLESS STEPS Challenge (FS-2): Supervised Learning with Massive Naturalistic Apollo Data

2020-08-15

The Fearless Steps Initiative by UTDallas-CRSS led to the digitization, recovery, and diarization of 19,000 hours of original analog audio data, as well as the development of algorithms to extract meaningful information …

Multi-scale Hierarchical Vision Transformer with Cascaded Attention Decoding for Medical Image Segmentation

2023-03-29 · Md Mostafijur Rahman, Radu Marculescu

Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we …

DecoderImage SegmentationMedical Image SegmentationSegmentation+1

Robust Self-Ensembling Network for Hyperspectral Image Classification

2021-04-08 · Yonghao Xu, Bo Du, Liangpei Zhang

Recent research has shown the great potential of deep learning algorithms in the hyperspectral image (HSI) classification task. Nevertheless, training these models usually requires a large amount of labeled data. Since t…

ClassificationGeneral ClassificationHyperspectral Image Classificationimage-classification+1