activity
20212024
most citedCTC Alignments Improve Autoregressive Translation

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL2025

OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models

William Chen, Jinchuan Tian, Yifan Peng +3

Neural scaling laws offer valuable insights for designing robust sequence processing architectures. While these laws have been extensively characterized in other modalities, their…

cs.CL2024

Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking

Brian Yan, Vineel Pratap, Shinji Watanabe +1

Multilingual Automatic Speech Recognition (ASR) models are typically evaluated in a setting where the ground-truth language of the speech utterance is known, however, this is often…

cs.CL2022

Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence Generation

Motoi Omachi, Brian Yan, Siddharth Dalmia +2

The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve…

cs.CL2022

Towards Zero-Shot Code-Switched Speech Recognition

Brian Yan, Matthew Wiesner, Ondrej Klejch +2

In this work, we seek to build effective code-switched (CS) automatic speech recognition systems (ASR) under the zero-shot setting where no transcribed CS speech data is available…

cs.CL2022

Avoid Overthinking in Self-Supervised Models for Speech Recognition

Dan Berrebbi, Brian Yan, Shinji Watanabe

Self-supervised learning (SSL) models reshaped our approach to speech, language and vision. However their huge size and the opaque relations between their layers and tasks result i…

cs.CL2022

Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models

Siddhant Arora, Siddharth Dalmia, Brian Yan +3

End-to-end spoken language understanding (SLU) systems are gaining popularity over cascaded approaches due to their simplicity and ability to avoid error propagation. However, thes…