On Architectures and Training for Raw Waveform Feature Extraction in ASR-Reference-Cited by-同舟云学术

On Architectures and Training for Raw Waveform Feature Extraction in ASR

Published:2021-12-13 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
language:
Short-container-title:

Author:

Vieting Peter¹,Luscher Christoph¹,Michel Wilfried¹,Schluter Ralf¹,Ney Hermann¹

Affiliation:

1. Human Language Technology and Pattern Recognition Group, RWTH Aachen University,Computer Science Department,Aachen,Germany,52074

Funder

European Research Council (ERC)

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9687821/9687855/09688123.pdf?arnumber=9688123

Reference34 articles.

1. RE-TURNN as a generic flexible neural toolkit with application to translation and speech recognition;zeyer;Annual Meeting of the Assoc for Computational Linguis-tics,2018

2. RE-TURNN: the RWTH extensible training framework for universal recurrent neural networks;doetsch;Proc IEEE Int Conf on Acoustics Speech and Signal Processing (ICASSP),2017

3. RASR/NN: The RWTH neural network toolkit for speech recognition

4. RASR - the RWTH Aachen University open source speech recognition toolkit;rybach;Proc IEEE Workshop Automatic Speech Recognition and Understanding (ASRU),2011

5. Conformer: Convolution-augmented transformer for speech recog-nition;gulati;ArXiv Preprint,2020

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Efficient Utilization of Large Pre-Trained Models for Low Resource ASR;2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2023-06-04

2. FeaRLESS: Feature Refinement Loss for Ensembling Self-Supervised Learning Features in Robust End-to-end Speech Recognition;Interspeech 2022;2022-09-18

3. On Language Model Integration for RNN Transducer Based Speech Recognition;ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2022-05-23