K
Kazuya Takeda
Researcher at Nagoya University
Publications - 546
Citations - 9667
Kazuya Takeda is an academic researcher from Nagoya University. The author has contributed to research in topics: Speech processing & Speech enhancement. The author has an hindex of 42, co-authored 495 publications receiving 7719 citations. Previous affiliations of Kazuya Takeda include Kobe Women's University & Nara Institute of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
CENSREC-4: Development of Evaluation Framework for Distant-talking Speech Recognition under Reverberant Environments
Masato Nakayama,Takanobu Nishiura,Yuki Denda,Norihide Kitaoka,Kazumasa Yamamoto,Takeshi Yamada,Satoru Tsuge,Chiyomi Miyajima,Masakiyo Fujimoto,Tetsuya Takiguchi,Satoshi Tamura,Tetsuji Ogawa,Shigeki Matsuda,Shingo Kuroiwa,Kazuya Takeda,Satoshi Nakamura +15 more
TL;DR: The results of evaluation experiments proved that CENSREC-4 is an effective database for evaluating the new dereverberation method because the traditional dereVerberation process had difficulty sufficiently improving the recognition performance.
Journal ArticleDOI
Effects of pressure on the cleaning action of cathode spot in low vacuum
Kazuya Takeda,S. Takeuchi +1 more
TL;DR: In this paper, a simplified model for the removal of oxide and roughening of the surface was developed, which explained the close relation between the removal rate of oxides and the effect of surface roughness.
Posted Content
Back-Translation-Style Data Augmentation for End-to-End ASR
Tomoki Hayashi,Shinji Watanabe,Yu Zhang,Tomoki Toda,Takaaki Hori,Ramón Fernandez Astudillo,Kazuya Takeda +6 more
TL;DR: In this article, a neural text-to-encoder model is proposed to predict hidden states from a large amount of unpaired text, then the decoder is retrained using the generated hidden states as additional training data.
Proceedings Article
Data collection and evaluation of aurora-2 japanese corpus
Satoshi Nakamura,Kazumasa Yamamoto,Kazuya Takeda,Shingo Kuroiwa,Norihide Kitaoka,Takeshi Yamada,Mitsunori Mizumachi,Takanobu Nishiura,Masakiyo Fujimoto,Akira Saso,Toshiki Endo +10 more
TL;DR: A Japanese noisy speech corpus and its evaluation scripts, called AURORA-2J, which includes Japanese connected digits and command words collected in a moving car and its baseline performance is described.
Book ChapterDOI
Speaker Identification Using Harmonic Structure of LP-residual Spectrum
TL;DR: It is shown that PDSS can compensate for the LPC cepstrum and delta cepStrum for improving speaker identification performance and is proposed as a new feature parameter to extract information of the harmonic structure of the linear prediction residual spectrum.