Yukun Ma
14 papers · 2016–2025 · 4 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 ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (31)
🧭
Keyword Pioneer
💎
Century Club · Bronze
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(71)
Top co-authors
Research topics
Speech & Audio
(9)
Machine Learning
(8)
Deep Learning
(7)
Artificial Intelligence
(6)
Core AI
(6)
Application Areas
(5)
Learning Types · Deep Learning
(5)
Recognition
(5)
Natural Language Processing
(4)
Generation
(3)
Learning Types · Machine Learning
(3)
Analysis
(2)
Core Methods
(2)
Processing
(2)
Techniques
(2)
Keywords
automatic speech recognition
(3)
self-supervised learning
(3)
model compression
(2)
multimodal learning
(2)
speaker separation
(2)
multi-task learning
(2)
target speaker extraction
(2)
audio-visual learning
(2)
representation learning
(2)
speech processing
(1)
response generation
(1)
speech recognition
(1)
domain adaptation
(1)
named entity recognition
(1)
attention mechanism
(1)
zero-shot learning
(1)
class-incremental learning
(1)
text classification
(1)
language modeling
(1)
matrix factorization
(1)
Papers
A-SMiLE: Affective Sparse Mixture-of-Experts Adapter with Multi-Task Learning for Spoken Dialogue Models
Interspeech 2025
FD-Bench: A Full-Duplex Benchmarking Pipeline Designed for Full Duplex Spoken Dialogue Systems
Interspeech 2025
Online Audio-Visual Autoregressive Speaker Extraction
Interspeech 2025
Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction
Interspeech 2025
Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
Interspeech 2024
ACA-Net: Towards Lightweight Speaker Verification using Asymmetric Cross Attention
Interspeech 2023
Adapter-tuning with Effective Token-dependent Representation Shift for Automatic Speech Recognition
Interspeech 2023
A Unified Recognition and Correction Model under Noisy and Accent Speech Conditions
Interspeech 2023
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
EMNLP 2023
Dual Acoustic Linguistic Self-supervised Representation Learning for Cross-Domain Speech Recognition
Interspeech 2023
Dual-Memory Multi-Modal Learning for Continual Spoken Keyword Spotting with Confidence Selection and Diversity Enhancement
Interspeech 2023
Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch
ICLR 2021
MulCode: A Multiplicative Multi-way Model for Compressing Neural Language Model
EMNLP 2019
Label Embedding for Zero-shot Fine-grained Named Entity Typing
COLING 2016