activity
20162024
most citedSyntactic and Semantic Features For Code-Switching Factored Language Models

70 citations · 108 across the 28 of their papers we have counts for

collaborators
Showing cs.CLShow all

41 papers · 1 filter

cs.CL2024

Improving noisy student training for low-resource languages in End-to-End ASR using CycleGAN and inter-domain losses

Chia-Yu Li, Ngoc Thang Vu

Training a semi-supervised end-to-end speech recognition system using noisy student training has significantly improved performance. However, this approach requires a substantial a…

cs.CL20232 cited

Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction

Manuel Mager, Rajat Bhatnagar, Graham Neubig +2

Neural models have drastically advanced state of the art for machine translation (MT) between high-resource languages. Traditionally, these models rely on large amounts of training…

cs.CL2023

Oh, Jeez! or Uh-huh? A Listener-aware Backchannel Predictor on ASR Transcriptions

Daniel Ortega, Chia-Yu Li, Ngoc Thang Vu

This paper presents our latest investigation on modeling backchannel in conversations. Motivated by a proactive backchanneling theory, we aim at developing a system which acts as a…

cs.CL2023

Modeling Speaker-Listener Interaction for Backchannel Prediction

Daniel Ortega, Sarina Meyer, Antje Schweitzer +1

We present our latest findings on backchannel modeling novelly motivated by the canonical use of the minimal responses Yeah and Uh-huh in English and their correspondent tokens in…

cs.CL20222 cited

ArzEn-ST: A Three-way Speech Translation Corpus for Code-Switched Egyptian Arabic - English

Injy Hamed, Nizar Habash, Slim Abdennadher +1

We present our work on collecting ArzEn-ST, a code-switched Egyptian Arabic - English Speech Translation Corpus. This corpus is an extension of the ArzEn speech corpus, which was c…

cs.CL2022

Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis

Florian Lux, Ching-Yi Chen, Ngoc Thang Vu

Embedding paralinguistic properties is a challenging task as there are only a few hours of training data available for domains such as emotional speech. One solution to this proble…