1 citations · 1 across the 8 of their papers we have counts for
8 papers
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
Chi-Yuan Hsiao, Ke-Han Lu, Yu-Kuan Fu +3
End-to-end full-duplex Speech Language Models (SLMs) require precise turn-taking for natural interaction. However, optimizing temporal dynamics via standard raw-token reinforcement…
How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation
Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang +13
Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-…
Analyzing Mitigation Strategies for Catastrophic Forgetting in End-to-End Training of Spoken Language Models
Chi-Yuan Hsiao, Ke-Han Lu, Kai-Wei Chang +3
End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage train…
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning
Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish +4
We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50…
Dynamic-SUPERB Phase-2: A Collaboratively Expanding Benchmark for Measuring the Capabilities of Spoken Language Models with 180 Tasks
Chien-yu Huang, Wei-Chih Chen, Shu-wen Yang +77
Multimodal foundation models, such as Gemini and ChatGPT, have revolutionized human-machine interactions by seamlessly integrating various forms of data. Developing a universal spo…
SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning
Chien-yu Huang, Min-Han Shih, Ke-Han Lu +2
Instruction-based speech processing is becoming popular. Studies show that training with multiple tasks boosts performance, but collecting diverse, large-scale tasks and datasets i…
Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu +3
This work evaluated several cutting-edge large-scale foundation models based on self-supervision or weak supervision, including SeamlessM4T, SeamlessM4T v2, and Whisper-large-v3, o…
Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech
Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang +12
Text language models have shown remarkable zero-shot capability in generalizing to unseen tasks when provided with well-formulated instructions. However, existing studies in speech…