← Authors

Yusuke Fujita

17 papers · 2016–2024 · 2 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (13) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (11) 🌈 Renaissance Researcher (5) 🧭 Keyword Pioneer 🌍 Conference Polyglot (2) πŸƒ Academic Marathon (8) 🧬 Topic Evolution πŸ† Keyword Champion (2) πŸ—ƒοΈ Keyword Collector (84) πŸ’Ž Century Club (17) πŸ”₯ Unstoppable (7) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer

Conferences

INTERSPEECH (16) NIPS (1)

Top co-authors

Kenji Nagamatsu (8) Shinji Watanabe (8) Shota Horiguchi (7) Tatsuya Komatsu (5) Naoyuki Kanda (4) Yusuke Kida (3) Yuki Takashima (2) Yawen Xue (2) Bo Xu (2) Jiaming Xu (2)

Keywords

speaker diarization (6) speech recognition (4) speech enhancement (3) automatic speech recognition (3) guided source separation (2) self-conditioned ctc (2) acoustic model (2) data augmentation (2) intermediate prediction (2) word error rate (2) speech separation (2) source separation (2) end-to-end learning (2) speaker embedding (2) character error rate (2) connectionist temporal classification (2) sequence-to-sequence model (2) overlapping speech (2) acoustic modeling (1) adversarial training (1)

Papers

Audio Fingerprinting with Holographic Reduced Representations INTERSPEECH 2024
Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework INTERSPEECH 2024
Universal Score-based Speech Enhancement with High Content Preservation INTERSPEECH 2024
Target Vocabulary Recognition Based on Multi-Task Learning with Decomposed Teacher Sequences INTERSPEECH 2023
Better Intermediates Improve CTC Inference INTERSPEECH 2022
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR INTERSPEECH 2022
Semi-Supervised Training with Pseudo-Labeling for End-To-End Neural Diarization INTERSPEECH 2021
Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers INTERSPEECH 2021
Speaker-Conditional Chain Model for Speech Separation and Extraction INTERSPEECH 2020
End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors INTERSPEECH 2020
Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones INTERSPEECH 2020
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals NIPS 2020
End-to-End Neural Speaker Diarization with Permutation-Free Objectives INTERSPEECH 2019
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR INTERSPEECH 2019
Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition INTERSPEECH 2019
Lattice-free State-level Minimum Bayes Risk Training of Acoustic Models INTERSPEECH 2018
Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling INTERSPEECH 2016