Nabarun Goswami

4 papers · 2018–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (2) 🏃 Academic Marathon (7) 🐝 Cross-Pollinator (12)

Conferences

INTERSPEECH (3) ICLR (1)

Top co-authors

Tatsuya Harada (2) Yuki Mitsufuji (2) Naoya Takahashi (2) Purvi Agrawal (1) Sudarsanam Parthasaarathy (1) Hanqin Wang (1)

Keywords

zero-shot learning (1) speech separation (1) speech synthesis (1) speech enhancement (1) speaker embedding (1) audio source separation (1) deep neural network (1) phase estimation (1) speaker adaptation (1) permutation invariant training (1) classification approach (1) music source separation (1) signal-to-distortion ratio (1) phase unwrapping (1) discretized phase (1) multi-speaker separation (1) speaker attractor (1)

Papers

T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via Multitask Learning ICLR 2025

SATTS: Speaker Attractor Text to Speech, Learning to Speak by Learning to Separate INTERSPEECH 2022

Recursive Speech Separation for Unknown Number of Speakers INTERSPEECH 2019

PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation INTERSPEECH 2018