Shuo-Yiin Chang
12 papers · 2017–2023 · 1 conference · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🏃 Academic Marathon (6)
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🏆
Keyword Champion
(5)
🗃️
Keyword Collector
(58)
⚡
Prolific Year
(5)
📈
Trend Setter
💎
Century Club
(12)
❓
The Questioner
Conferences
INTERSPEECH (12)
Top co-authors
Keywords
streaming speech recognition
(5)
automatic speech recognition
(4)
voice activity detection
(2)
on-device speech recognition
(2)
recurrent neural network transducer
(2)
word error rate
(2)
end-to-end modeling
(2)
end-to-end speech recognition
(2)
speech recognition
(2)
recurrent neural network
(2)
turn-taking prediction
(2)
latency reduction
(2)
end-to-end model
(2)
low latency
(1)
auxiliary task
(1)
language model
(1)
language model training
(1)
optimal transport
(1)
long short-term memory
(1)
joint training
(1)
Papers
How to Estimate Model Transferability of Pre-Trained Speech Models?
INTERSPEECH 2023
Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR
INTERSPEECH 2023
Text Injection for Capitalization and Turn-Taking Prediction in Speech Models
INTERSPEECH 2023
A Language Agnostic Multilingual Streaming On-Device ASR System
INTERSPEECH 2022
Turn-Taking Prediction for Natural Conversational Speech
INTERSPEECH 2022
Streaming Intended Query Detection using E2E Modeling for Continued Conversation
INTERSPEECH 2022
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
INTERSPEECH 2022
E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
INTERSPEECH 2022
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling
INTERSPEECH 2021
Low Latency Speech Recognition Using End-to-End Prefetching
INTERSPEECH 2020
Endpoint Detection Using Grid Long Short-Term Memory Networks for Streaming Speech Recognition
INTERSPEECH 2017
Improved End-of-Query Detection for Streaming Speech Recognition
INTERSPEECH 2017