Skip to content
conftrace_

Ke-Han Lu

5 papers · 2024–2025 · 2 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 ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 👥 Mega-Team · Legion

Venues

Interspeech (4) ICLR (1)

Top co-authors

Hung-yi Lee (4) Chi-Yuan Hsiao (2) Chih-Kai Yang (2) Chun-Yi Kuan (2) Kai-Wei Chang (2) Wei-Chih Chen (2) Shi-Xin Fang (1) Suwon Shon (1) Jia Qi Yip (1) Xuanjun Chen (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (2) Speech & Audio (2) Machine Learning (1) Natural Language Processing (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Processing (1) Recognition (1) Resources & Methods (1) Techniques (1)

Keywords

catastrophic forgetting (2) spoken language model (2) speech recognition (2) multimodal learning (1) instruction following (1) model merging (1) low-rank adaptation (1) evaluation benchmark (1) prompt sensitivity (1) experience replay (1) error correction (1) speech perception (1) hypothesis revision (1) speech language model (1) speech-text alignment (1) n-best reranking (1) reference corpus (1) audio understanding (1) instruction-based learning (1) descriptive captioning (1)

Papers

Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models Interspeech 2025 Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks ICLR 2025 Speech-IFEval: Evaluating Instruction-Following and Quantifying Catastrophic Forgetting in Speech-Aware Language Models Interspeech 2025 DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment Interspeech 2024 HypR: A comprehensive study for ASR hypothesis revising with a reference corpus Interspeech 2024