223 citations
- H. Koibuchi16 · h 14
- A. Shiomi2 profiles9 · h 30
- C. Checchia2 profiles9 · h 17
- C. Kato2 profiles9 · h 33
- E. Vannuccini2 profiles9 · h 39
- F. Stolzi2 profiles9 · h 18
- G. Bigongiari2 profiles9 · h 27
- G. Castellini2 profiles9 · h 27
- G. Collazuol2 profiles9 · h 18
- H. Fuke2 profiles9 · h 29
- H. Krawczynski2 profiles9 · h 58
- J. Kataoka2 profiles9 · h 87
- Ibaraki National College of TechnologyJP33 papers
- Ibaraki UniversityJP30 papers
- The University of TokyoJP22 papers
- Kyoto UniversityJP14 papers
- Nagoya UniversityJP11 papers
- Waseda UniversityJP11 papers
- Yokohama National UniversityJP11 papers
- Aoyama Gakuin UniversityJP10 papers
- College of Industrial TechnologyJP10 papers
- Deleted Institution10 papers
- Hirosaki UniversityJP10 papers
- Hitachi (United Kingdom)GB10 papers
5 papers · 1 filter
End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection
Yuki Takashima, Yusuke Fujita, Shinji Watanabe +3
In this paper, we present a conditional multitask learning method for end-to-end neural speaker diarization (EEND). The EEND system has shown promising performance compared with tr…
Flow-based Self-supervised Density Estimation for Anomalous Sound Detection
Kota Dohi, Takashi Endo, Harsh Purohit +2
To develop a machine sound monitoring system, a method for detecting anomalous sound is proposed. Exact likelihood estimation using Normalizing Flows is a promising technique for u…
End-to-End Speaker Diarization as Post-Processing
Shota Horiguchi, Paola Garcia, Yusuke Fujita +2
This paper investigates the utilization of an end-to-end diarization model as post-processing of conventional clustering-based diarization. Clustering-based diarization methods par…
Block-Online Guided Source Separation
Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
We propose a block-online algorithm of guided source separation (GSS). GSS is a speech separation method that uses diarization information to update parameters of the generative mo…
Speaker Diarization with Region Proposal Network
Zili Huang, Shinji Watanabe, Yusuke Fujita +4
Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem. Although the standard diarization systems c…