Yifan Yang

yfyeung's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 10 days ago

Pruned CTC for Memory-Efficient Large-Vocabulary ASR Training

Paper • 2609.33645 • Published 13 days ago • 3

upvoted a paper 16 days ago

Qwen3.8-Omni: Towards Native Omni-Modal Agents

Paper • 2609.25611 • Published 18 days ago • 6

upvoted 2 papers about 1 month ago

AuK Technical Report: An Open-Source Foundational Model for Speech Generation and Editing

Paper • 2609.08936 • Published Sep 8 • 161

VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction

Paper • 2608.26005 • Published Aug 26 • 154

upvoted a paper 4 months ago

MMAE: A Massive Multitask Audio Editing Benchmark

Paper • 2606.07229 • Published Jun 5 • 46

upvoted a collection 5 months ago

Typhoon ASR

Collection

A speech to text model for Thai • 17 items • Updated 29 days ago • 6

upvoted a paper 5 months ago

Evaluating the Expressive Appropriateness of Speech in Rich Contexts

Paper • 2605.09413 • Published May 10 • 5

upvoted 2 papers 6 months ago

SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations

Paper • 2510.25955 • Published Oct 29, 2025 • 2

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

Paper • 2604.10866 • Published Apr 13 • 69

upvoted a paper 8 months ago

Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

Paper • 2601.13044 • Published Jan 19 • 12

upvoted a collection 11 months ago

SPEAR encoders

Collection

[ICML2026] SPEAR: A Unified SSL Framework for Learning Speech and Audio Representations • 8 items • Updated Jun 22 • 4

upvoted a collection 12 months ago

WenetSpeech-Yue

Collection

A Large-scale Cantonese Speech Corpus with Multi-dimensional Annotation • 7 items • Updated Nov 18, 2025 • 5

upvoted 2 papers about 1 year ago

Zipformer: A faster and better encoder for automatic speech recognition

Paper • 2310.11230 • Published Oct 17, 2023 • 2

VibeVoice Technical Report

Paper • 2508.19205 • Published Aug 26, 2025 • 180