works on

From the 2 of 10 linked papers with an AI index.

collaborators

10 papers

cs.SD2026

Dissecting Sensitivity to Training Language in Self-Supervised Speech Learning Using Neural Audio Codec Tokens

Daigo Takizawa, Tomohiko Nakamura, Samuele Cornell +3

The paper investigates how the language used to train neural audio codecs and self‑supervised speech models affects performance, finding that codec training language has little imp…

cs.CL2026

An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi +4

The paper introduces PhoneticXEUS, a multilingual phone recognition system trained on large-scale data that achieves state-of-the-art error rates on both many languages and accente…

eess.AS2026

ESPnet3: Infrastructure for Scalable Speech and Audio Research in the Foundation Model Era

Masao Someki, Alexander Polok, Carlos Carvalho +14

Recent speech research involves increasingly large datasets, complex models, and diverse experimental workflows. However, existing frameworks require substantial engineering effort…

cs.SD2026

Bagpiper-Edit: Zero-Shot Open-Ended Audio Editing via Rich-Caption

Xun Gong, Jinchuan Tian, Haoran Wang +3

Current text-guided audio editing methods rely on paired training data, predefined operation templates, and separate processing pipelines across speech, music, and sound. We presen…

cs.CL2026

Evaluating Large Language Models Abilities for Addressee, Turn-change, and Next Speaker Prediction in Meetings

Ryo Fukuda, Takatomo Kano, Siddhant Arora +7

We investigate turn-taking in multimodal multi-party conversations using large language models (LLMs). We construct an evaluation framework for three tasks: addressee detection, tu…

cs.SD2025

Robust Training of Singing Voice Synthesis Using Prior and Posterior Uncertainty

Yiwen Zhao, Jiatong Shi, Yuxun Tang +2

Singing voice synthesis (SVS) has seen remarkable advancements in recent years. However, compared to speech and general audio data, publicly available singing datasets remain limit…