6 papers
ParaS2S: Benchmarking and Aligning Spoken Language Models for Paralinguistic-aware Speech-to-Speech Interaction
Shu-wen Yang, Ming Tu, Andy T. Liu +5
Speech-to-Speech (S2S) models have shown promising dialogue capabilities, but their ability to handle paralinguistic cues - such as emotion, tone, and speaker attributes - and to r…
Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction
Shu-wen Yang, Byeonggeun Kim, Kuan-Po Huang +8
Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language P…
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…
IMPACT: Iterative Mask-based Parallel Decoding for Text-to-Audio Generation with Diffusion Modeling
Kuan-Po Huang, Shu-wen Yang, Huy Phan +8
Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent t…
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…
Building a Taiwanese Mandarin Spoken Language Model: A First Attempt
Chih-Kai Yang, Yu-Kuan Fu, Chen-An Li +18
This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech…