Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training
for Enhanced Speech Recognition and Translation

Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation

9 September 2024

Nithin Rao Koluguri

Travis M. Bartley

Oleksii Hrinchuk

Jagadeesh Balam

Boris Ginsburg

Papers citing "Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation"

4 / 4 papers shown

Title
Granary: Speech Recognition and Translation Dataset in 25 European Languages Nithin Rao Koluguri Monica Sekoyan George Zelenfroynd Sasha Meister Shuoyang Ding ... Yifan Peng Sara Papi Marco Gaido Alessio Brutti Boris Ginsburg 17 0 0 19 May 2025
HAINAN: Fast and Accurate Transducer for Hybrid-Autoregressive ASR Hainan Xu Travis M. Bartley Vladimir Bataev Boris Ginsburg 211 0 0 03 Oct 2024
CTC Alignments Improve Autoregressive Translation Brian Yan Siddharth Dalmia Yosuke Higuchi Graham Neubig Florian Metze A. Black Shinji Watanabe 46 33 0 11 Oct 2022
Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition Yu Zhang James Qin Daniel S. Park Wei Han Chung-Cheng Chiu Ruoming Pang Quoc V. Le Yonghui Wu VLM SSL 148 308 0 20 Oct 2020