activity
20222025
most citedAligning Speech to Languages to Enhance Code-switching Speech Recognition

5 citations · 8 across the 11 of their papers we have counts for

collaborators

12 papers

cs.CL2025

WST: Weakly Supervised Transducer for Automatic Speech Recognition

Dongji Gao, Chenda Liao, Changliang Liu +5

The Recurrent Neural Network-Transducer (RNN-T) is widely adopted in end-to-end (E2E) automatic speech recognition (ASR) tasks but depends heavily on large-scale, high-quality anno…

cs.CL2025

HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translation

Amir Hussein, Cihan Xiao, Matthew Wiesner +3

Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT…

eess.AS2024★ 5 cited

Aligning Speech to Languages to Enhance Code-switching Speech Recognition

Hexin Liu, Xiangyu Zhang, Haoyang Zhang +4

Code-switching (CS) refers to the switching of languages within a speech signal and results in language confusion for automatic speech recognition (ASR). To address language confus…

eess.AS2024

Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Model

Xiangyu Zhang, Daijiao Liu, Hexin Liu +5

Recently, Denoising Diffusion Probabilistic Models (DDPMs) have attained leading performances across a diverse range of generative tasks. However, in the field of speech synthesis,…

cs.CL2023★ 1 cited

A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors

Shuyue Stella Li, Beining Xu, Xiangyu Zhang +3

In this work, we study the features extracted by English self-supervised learning (SSL) models in cross-lingual contexts and propose a new metric to predict the quality of feature…

eess.AS2023

Enhancing Code-switching Speech Recognition with Interactive Language Biases

Hexin Liu, Leibny Paola Garcia, Xiangyu Zhang +2

Languages usually switch within a multilingual speech signal, especially in a bilingual society. This phenomenon is referred to as code-switching (CS), making automatic speech reco…