← Authors

Tsubasa Ochiai

20 papers · 2017–2024 · 2 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (2) πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (8) πŸ—ΊοΈ Taxonomy Completionist (25) 🀝 Dynamic Duo (17) 🧬 Topic Evolution ⚑ Prolific Year (5) πŸ—ƒοΈ Keyword Collector (77) πŸ’Ž Century Club (20) πŸ”₯ Unstoppable (8) ❓ The Questioner (3)

Conferences

INTERSPEECH (19) ICML (1)

Top co-authors

Marc Delcroix (17) Hiroshi Sato (10) Takafumi Moriya (8) Keisuke Kinoshita (8) Tomohiro Nakatani (6) Shoko Araki (6) Takanori Ashihara (5) Ryo Masumura (5) Tomohiro Tanaka (5) Atsunori Ogawa (4)

Keywords

speech enhancement (7) attention mechanism (5) automatic speech recognition (5) speech separation (3) speech recognition (3) target speech extraction (3) knowledge distillation (2) neural network (2) speaker separation (2) speaker verification (2) end-to-end learning (2) neural transducer (2) target sound extraction (2) orthogonal projection (1) source separation (1) few-shot learning (1) model complexity (1) self-supervised learning (1) probabilistic modeling (1) feature representation (1)

Papers

SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling INTERSPEECH 2024
Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers INTERSPEECH 2024
Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss INTERSPEECH 2023
Impact of Residual Noise and Artifacts in Speech Enhancement Errors on Intelligibility of Human and Machine INTERSPEECH 2023
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data INTERSPEECH 2023
Listen only to me! How well can target speech extraction handle false alarms? INTERSPEECH 2022
Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations INTERSPEECH 2022
Streaming Target-Speaker ASR with Neural Transducer INTERSPEECH 2022
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model INTERSPEECH 2022
How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR INTERSPEECH 2022
Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture INTERSPEECH 2021
Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition INTERSPEECH 2021
Few-Shot Learning of New Sound Classes for Target Sound Extraction INTERSPEECH 2021
PILOT: Introducing Transformers for Probabilistic Sound Event Localization INTERSPEECH 2021
Listen to What You Want: Neural Network-Based Universal Sound Selector INTERSPEECH 2020
Self-Distillation for Improving CTC-Transformer-Based ASR Systems INTERSPEECH 2020
End-to-End SpeakerBeam for Single Channel Target Speech Recognition INTERSPEECH 2019
Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues INTERSPEECH 2019
ESPnet: End-to-End Speech Processing Toolkit INTERSPEECH 2018
Multichannel End-to-end Speech Recognition ICML 2017