S
Shoji Kajita
Researcher at Nagoya University
Publications - 62
Citations - 772
Shoji Kajita is an academic researcher from Nagoya University. The author has contributed to research in topics: Microphone array & Speech processing. The author has an hindex of 14, co-authored 61 publications receiving 763 citations. Previous affiliations of Shoji Kajita include Kyoto University.
Papers
More filters
Proceedings ArticleDOI
Evaluation of blind signal separation method using directivity pattern under reverberant conditions
TL;DR: This paper describes a new blind signal separation method using the directivity patterns of a microphone array that improves the SNR of degraded speech by about 16 dB under non-reverberant condition and improves theSNR by 8.7 dB when the reverberation time is 184 ms.
Book ChapterDOI
Ontology-based semantic recommendation for context-aware e-learning
TL;DR: An ontology-based approach for semantic content recommendation towards context-aware e-learning and a personalized, complete, and augmented learning program is suggested for the learner.
Proceedings Article
Construction of Speech Corpus in Moving Car Environment
Nobuo Kawaguchi,Shigeki Matsubara,Hiroyuki Iwa,Shoji Kajita,Kazuya Takeda,Fumitada Itakura,Yasuyoshi Inagaki +6 more
TL;DR: The Center for Integrated Acoustic Information Research at Nagoya University has been collecting speech corpora in moving cars to advance the research and development of robust ASRs and spoken dialogue systems under high-noise conditions.
Proceedings ArticleDOI
Interpolating head related transfer functions in the median plane
TL;DR: In this paper, a simple linear interpolation method and spline interpolation methods are evaluated and advantages of both methods clarified, and the results indicate that HRTFs in the median plane can be interpolated by the methods.
Proceedings ArticleDOI
Speech recognition based on space diversity using distributed multi-microphone
TL;DR: The experimental results show that the proposed space diversity speech recognition system can attain about 80% in accuracy, while the performances of conventional HMMs using close-talking microphones are less than 50%, indicating that the space diversity approach is promising for robust speech recognition under a real acoustic environment.