Xutai Ma
21 papers · 2018–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (33) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(11)
🧭
Keyword Pioneer
👥
Mega-Team · Legion
🧬
Topic Evolution
🚀
Conference Pioneer
🔥
Unstoppable · Bronze
⚡
Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(91)
Top co-authors
Research topics
Natural Language Processing
(12)
Speech & Audio
(11)
Deep Learning
(10)
Applications
(10)
Machine Learning
(9)
Recognition
(9)
Artificial Intelligence
(8)
Architectures
(8)
Core AI
(7)
Synthesis
(5)
Learning Types · Machine Learning
(4)
Learning Types · Deep Learning
(4)
Understanding
(3)
Application Areas
(2)
Optimization & Theory
(2)
Keywords
simultaneous translation
(6)
speech translation
(6)
speech-to-speech translation
(4)
speech recognition
(3)
spoken language translation
(3)
semantic parsing
(3)
self-supervised learning
(3)
attention mechanism
(2)
multilingual translation
(2)
latency metric
(2)
abstract meaning representation
(2)
machine translation
(2)
discrete representation
(2)
low-resource language
(2)
end-to-end model
(2)
neural machine translation
(1)
semi-supervised learning
(1)
speech synthesis
(1)
multilingual nlp
(1)
sequence labeling
(1)
Papers
Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation
EMNLP 2025
SSR: Alignment-Aware Modality Connector for Speech Language Models
ACL 2025
Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation
COLING 2024
FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN
ACL 2024
MMM: Multi-Layer Multi-Residual Multi-Stream Discrete Speech Representation from Self-supervised Learning Model
Interspeech 2024
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
ICLR 2024
FINDINGS OF THE IWSLT 2023 EVALUATION CAMPAIGN
ACL 2023
Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks
ACL 2023
Direct Speech-to-Speech Translation With Discrete Units
ACL 2022
Findings of the IWSLT 2022 Evaluation Campaign
ACL 2022
From Start to Finish: Latency Reduction Strategies for Incremental Speech Synthesis in Simultaneous Speech-to-Speech Translation
Interspeech 2022
FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN
ACL 2021
Fairseq S2T: Fast Speech-to-Text Modeling with Fairseq
AACL 2020
FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN
ACL 2020
Monotonic Multihead Attention
ICLR 2020
Self-Training for End-to-End Speech Translation
Interspeech 2020
SIMULEVAL: An Evaluation Toolkit for Simultaneous Translation
EMNLP 2020
SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
AACL 2020
AMR Parsing as Sequence-to-Graph Transduction
ACL 2019
Broad-Coverage Semantic Parsing as Transduction
EMNLP 2019
Cross-lingual Decompositional Semantic Parsing
EMNLP 2018