Shuo-Yiin Chang

Google (United States) — United States

Computer Science · Physical Sciences

18h-index3.6kcitations64works92.02yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Speech Recognition and Synthesis(54), Speech and Audio Processing(44), Music and Audio Processing(34), Speech and dialogue systems(11), Natural Language Processing Techniques(9)

Publications62 total

Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
2024· 5 cited
Multilingual and Fully Non-Autoregressive ASR with Large Language Model Fusion: A Comprehensive Study
arXiv (Cornell University)·2024· 1 citedOpen Access
Improved Long-Form Speech Recognition by Jointly Modeling the Primary and Non-primary Speakers
arXiv (Cornell University)·2023Open Access
Improved Long-Form Speech Recognition By Jointly Modeling The Primary And Non-Primary Speakers
2023· 1 cited
Towards General-Purpose Text-Instruction-Guided Voice Conversion
2023· 3 cited
Towards General-Purpose Text-Instruction-Guided Voice Conversion
arXiv (Cornell University)·2023Open Access
How to Estimate Model Transferability of Pre-Trained Speech Models?
2023· 7 cited
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models
arXiv (Cornell University)·2023Open Access
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
2023· 1 cited
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models
2023
How to Estimate Model Transferability of Pre-Trained Speech Models?
arXiv (Cornell University)·2023Open Access
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
arXiv (Cornell University)·2023Open Access
UML: A Universal Monolingual Output Layer For Multilingual Asr
2023· 3 cited
Multi-Output RNN-T Joint Networks for Multi-Task Learning of ASR and Auxiliary Tasks
2023· 3 cited
Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion
2023· 8 cited
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
2023· 5 cited
UML: A Universal Monolingual Output Layer for Multilingual ASR
arXiv (Cornell University)·2023Open Access
Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
2022 IEEE Spoken Language Technology Workshop (SLT)·2023· 8 cited
E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model
arXiv (Cornell University)·2022Open Access
Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
arXiv (Cornell University)·2022Open Access
page 1 of 4Next →

Frequent Co-authors

Tara N. Sainath(36), Yanzhang He(17), Trevor Strohman(17), Bo Li(13), Ruoming Pang(13), David Rybach(11), Yonghui Wu(11), Rohit Prabhavalkar(10), Arun Narayanan(8), Chung‐Cheng Chiu(8), Ian McGraw(6), Qiao Liang(6), Yu Zhang(6), Anmol Gulati(6), James Qin(6), Cyril Allauzen(6), Ding Zhao(5), Cal Peyser(5), Jiahui Yu(5), Wei Han(5)