T
Tetsuro Kitahara
Researcher at Nihon University
Publications - 71
Citations - 758
Tetsuro Kitahara is an academic researcher from Nihon University. The author has contributed to research in topics: Musical instrument & Music information retrieval. The author has an hindex of 15, co-authored 69 publications receiving 699 citations. Previous affiliations of Tetsuro Kitahara include Kwansei Gakuin University & Kyoto University.
Papers
More filters
Journal ArticleDOI
Instrument identification in polyphonic music: feature weighting to minimize influence of sound overlaps
TL;DR: A new solution to the problem of feature variations caused by the overlapping of sounds in instrument identification in polyphonic music by weighting features based on how much they are affected by overlapping, which improves instrument identification using musical context.
Journal ArticleDOI
A Modeling of Singing Voice Robust to Accompaniment Sounds and Its Application to Singer Identification and Vocal-Timbre-Similarity-Based Music Information Retrieval
TL;DR: A new representation of a singing voice from polyphonic musical audio signals including sounds of various musical instruments is demonstrated to improve the performance of an automatic singer identification system and to achieve an MIR system based on vocal timbre similarity.
Proceedings Article
Singer identification based on accompaniment sound reduction and reliable frame selection
Hiromasa Fujihara,Tetsuro Kitahara,Masataka Goto,Kazunori Komatani,Tetsuya Ogata,Hiroshi G. Okuno +5 more
TL;DR: A method for automatic singer identification from polyphonic musical audio signals including sounds of various instruments that was able to reduce the influences of accompaniment sounds and achieved an accuracy of 95%, while the accuracy for a conventional method was 53%.
Proceedings Article
Automatic Chord Transcription with Concurrent Recognition of Chord Symbols and Boundaries.
TL;DR: A method that recognizes musical chords from real-world audio signals in compact-disc recordings and generates hypotheses about tuples of chord symbols and chord boundaries, and outputs the most plausible one as the recognition result.
Proceedings ArticleDOI
Musical instrument identification based on F0-dependent multivariate normal distribution
TL;DR: This paper presents a method using an F0-dependent multivariate normal distribution of which mean is represented by a function of fundamental frequency (FO), which represents the pitch dependency of each feature, while the F1-normalized covariance represents the non-pitch dependency.