Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR-Reference-Cited by-同舟云学术

Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR

Published:2022-05-23 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Chang Xuankai¹,Moritz Niko¹,Hori Takaaki¹,Watanabe Shinji²,Roux Jonathan Le¹

Affiliation:

1. Mitsubishi Electric Research Laboratories (MERL),Cambridge,MA,USA

2. Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA

Publisher

IEEE

Link

Reference30 articles.

2. Sequence transduction with recurrent neural networks;graves;arXiv preprint arXiv 1211 3711,2012

5. Differentiable weighted finite-state transducers;hannun;arXiv preprint arXiv 2010 00170,2020

Cited by 2 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. AGADIR: Towards Array-Geometry Agnostic Directional Speech Recognition;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

2. Cocktail Hubert: Generalized Self-Supervised Pre-Training for Mixture and Single-Source Speech;ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2023-06-04