UML: A Universal Monolingual Output Layer for Multilingual ASR

22 February 2023

Papers citing "UML: A Universal Monolingual Output Layer for Multilingual ASR"

8 / 8 papers shown

Title
Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation Qiuming Zhao Guangzhi Sun Chao Zhang Mingxing Xu Thomas Fang Zheng MoMe VLM 83 0 0 24 Feb 2025
Learn and Don't Forget: Adding a New Language to ASR Foundation Models Mengjie Qian Siyuan Tang Rao Ma Kate Knill Mark J. F. Gales CLL 18 3 0 09 Jul 2024
Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints Hao Yen Sabato Marco Siniscalchi Chin-Hui Lee 20 1 0 16 Sep 2023
Building High-accuracy Multilingual ASR with Gated Language Experts and Curriculum Training Eric Sun Jinyu Li Yuxuan Hu Yilun Zhu Long Zhou ... Peidong Wang Linquan Liu Shujie Liu Ed Lin Yifan Gong 11 6 0 01 Mar 2023
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification C. Zhang Bo-wen Li Tara N. Sainath Trevor Strohman S. Mavandadi Shuo-yiin Chang Parisa Haghani 135 28 0 13 Sep 2022
Improving the fusion of acoustic and text representations in RNN-T Chao Zhang Bo-wen Li Zhiyun Lu Tara N. Sainath Shuo-yiin Chang AI4CE 28 12 0 25 Jan 2022
A Configurable Multilingual Model is All You Need to Recognize All Languages Long Zhou Jinyu Li Eric Sun Shujie Liu 83 40 0 13 Jul 2021
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging Rohit Prabhavalkar Yanzhang He David Rybach S. Campbell A. Narayanan Trevor Strohman Tara N. Sainath 41 35 0 12 Dec 2020