Yangyang Shi
29 papers · 2016–2026 · 7 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 ↓+8 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (53) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π§¬
Topic Evolution
π¬
Deep Specialist
(10)
π€
Dynamic Duo
(13)
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(144)
Top co-authors
Research topics
Deep Learning
(20)
Machine Learning
(16)
Speech & Audio
(14)
Recognition
(13)
Architectures
(10)
Natural Language Processing
(9)
Learning Types Β· Deep Learning
(9)
Application Areas
(8)
Optimization & Theory Β· Deep Learning
(6)
Artificial Intelligence
(5)
Generation
(5)
Learning Types Β· Machine Learning
(5)
Optimization & Theory Β· Machine Learning
(5)
Core AI
(4)
Resources & Methods
(4)
Keywords
automatic speech recognition
(6)
word error rate
(4)
language model
(3)
on-device speech recognition
(3)
speech recognition
(3)
knowledge distillation
(2)
real-time factor
(2)
acoustic model
(2)
streaming speech recognition
(2)
attention mechanism
(2)
latency optimization
(2)
acoustic modeling
(2)
speech synthesis
(1)
machine translation
(1)
domain adaptation
(1)
knowledge transfer
(1)
zero-shot learning
(1)
model quantization
(1)
text generation
(1)
self-supervised learning
(1)
Papers
EgoAVU: Egocentric Audio-Visual Understanding
CVPR 2026
OmniEvent: Unified Event Representation Learning
AAAI 2026
Agent-as-a-Judge: Evaluate Agents with Agents
ICML 2025
AutoMixer: Checkpoint Artifacts as Automatic Data Mixers
ACL 2025
Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions
NAACL 2025
MASV: Speaker Verification with Global and Local Context Mamba
Interspeech 2025
Self-Vocabularizing Training for Neural Machine Translation
NAACL 2025
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
ACL 2024
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
ICML 2024
Scaling Parameter-Constrained Language Models with Quality Data
EMNLP 2024
Speech ReaLLM β Real-time Speech Recognition with Multimodal Language Models by Teaching the Flow of Time
Interspeech 2024
Target-Aware Language Modeling via Granular Data Sampling
EMNLP 2024
Tumor Micro-environment Interactions Guided Graph Learning for Survival Analysis of Human Cancers from Whole-slide Pathological Images
CVPR 2024
Biased Self-supervised Learning for ASR
Interspeech 2023
Binary and Ternary Natural Language Generation
ACL 2023
Multi-Head State Space Model for Speech Recognition
Interspeech 2023
Revisiting Sample Size Determination in Natural Language Understanding
ACL 2023
Towards Zero-Shot Multilingual Transfer for Code-Switched Responses
ACL 2023
Streaming parallel transducer beam search with fast slow cascaded encoders
Interspeech 2022
Collaborative Training of Acoustic Encoders for Speech Recognition
Interspeech 2021
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
Interspeech 2021
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
Interspeech 2021
Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency
Interspeech 2021
Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios
Interspeech 2021
Transformer-Based Acoustic Modeling for Streaming Speech Synthesis
Interspeech 2021
Streaming Transformer-Based Acoustic Models Using Self-Attention with Augmented Memory
Interspeech 2020
Weak-Attention Suppression for Transformer Based Speech Recognition
Interspeech 2020
Deep LSTM based Feature Mapping for Query Classification
NAACL 2016
Recurrent Support Vector Machines For Slot Tagging In Spoken Language Understanding
NAACL 2016