8 papers
Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information
Shih-Heng Wang, Tiantian Feng, Aditya Kommineni +4
Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretabilit…
Speech Codec Probing from Semantic and Phonetic Perspectives
Xuan Shi, Chang Zeng, Tiantian Feng +3
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. Speech tokenizers are expected to preserve both semantic and acoustic i…
Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks
Shih-Heng Wang, Jiatong Shi, Jinchuan Tian +2
This paper investigates three crucial yet underexplored aspects of the generalization capabilities of neural audio codecs (NACs): (i) whether NACs can generalize to unseen language…
The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties
William Chen, Chutong Meng, Jiatong Shi +10
Recent improvements in multilingual ASR have not been equally distributed across languages and language varieties. To advance state-of-the-art (SOTA) ASR models, we present the Int…
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…
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…