10 papers
TiCo: Time-Controllable Spoken Dialogue Model
Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu +2
We introduce TiCo, a time-controllable spoken dialogue model (SDM) that follows time-constrained instructions (e.g., "Please generate a response lasting about 15 seconds") and gene…
Game-Time: Evaluating Temporal Dynamics in Spoken Language Models
Kai-Wei Chang, En-Pei Hu, Chun-Yi Kuan +7
Conversational Spoken Language Models (SLMs) are emerging as a promising paradigm for real-time speech interaction. However, their capacity of temporal dynamics, including the abil…
DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu +25
We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Langu…
Causal Tracing of Audio-Text Fusion in Large Audio Language Models
Wei-Chih Chen, Chien-yu Huang, Hung-yi Lee
Despite the strong performance of large audio language models (LALMs) in various tasks, exactly how and where they integrate acoustic features with textual context remains unclear.…
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…
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…