Keisuke Imoto

5 papers · 2023–2025 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze

Venues

Interspeech (5)

Top co-authors

Kentaro Onda (2) Daisuke Saito (2) Nobuaki Minematsu (2) Satoru Fukayama (2) Yasunori Ohishi (1) Kota Dohi (1) Kanta Shimonishi (1) Masaki Onishi (1) Shigeo Morishima (1) Keitaro Tanaka (1)

Research topics

Deep Learning (3) Speech & Audio (3) Learning Types · Deep Learning (3) Machine Learning (2) Analysis (2) Recognition (2) Artificial Intelligence (1) Application Areas (1) Core AI (1) Learning Types · Machine Learning (1) Synthesis (1)

Keywords

self-supervised learning (3) automatic speech recognition (2) discrete token (2) sound separation (1) sound synthesis (1) audio captioning (1) zero-shot inference (1) speech tokenization (1) accent robustness (1) contrastive language-audio pretraining (1) masked modeling (1) audio-language representation (1) speech resynthesis (1) environmental sound (1) environmental sound separation (1) single-source sound (1) caption-based dataset (1) audio extraction (1) caption dataset (1) audio mixture (1)

Papers

Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data Interspeech 2025 Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora Interspeech 2025 Training Onset-and-Offset-Aware Sound Event Detection on a Heterogeneous Dataset via Probabilistic Sequential Modeling Interspeech 2025 M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation Interspeech 2024 CAPTDURE: Captioned Sound Dataset of Single Sources Interspeech 2023