activity
20192026
most citedGuided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR

12 citations · 60 across the 52 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

cs.CL2019

Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models

Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita +3

This paper investigates the use of target-speaker automatic speech recognition (TS-ASR) for simultaneous speech recognition and speaker diarization of single-channel dialogue recor…

eess.AS2019

End-to-End Neural Speaker Diarization with Self-attention

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi +3

Speaker diarization has been mainly developed based on the clustering of speaker embeddings. However, the clustering-based approach has two major problems; i.e., (i) it is not opti…

eess.AS2019

End-to-End Neural Speaker Diarization with Permutation-Free Objectives

Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi +2

In this paper, we propose a novel end-to-end neural-network-based speaker diarization method. Unlike most existing methods, our proposed method does not have separate modules for e…

cs.CL2019★ 3 cited

Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition

Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima +3

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's…

cs.CL2019★ 12 cited

Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR

Naoyuki Kanda, Christoph Boeddeker, Jens Heitkaemper +4

In this paper, we present Hitachi and Paderborn University's joint effort for automatic speech recognition (ASR) in a dinner party scenario. The main challenges of ASR systems for…