H
Hiromi Ishizaki
Researcher at KDDI
Publications - 23
Citations - 148
Hiromi Ishizaki is an academic researcher from KDDI. The author has contributed to research in topics: Web search query & Music information retrieval. The author has an hindex of 7, co-authored 23 publications receiving 145 citations.
Papers
More filters
Proceedings ArticleDOI
Full-automatic dj mixing system with optimal tempo adjustment based on measurement function of user discomfort
TL;DR: This paper proposes an automatic DJ mixing method that can automate the processes of real world DJs and describes a prototype for a fully automatic DJ mix-like playing system, which is robust for any combination of tempi of songs to be mixed.
Book ChapterDOI
Feature Based Sentiment Analysis of Tweets in Multiple Languages
TL;DR: A method is proposed that identifies product features using review articles and then conducts sentiment analysis on tweets containing those features, which can increase the precision of feature extraction by up to 40% compared to features extracted directly from tweets.
Proceedings Article
Usability evaluation of visualization interfaces for content-based music retrieval systems
TL;DR: Evaluated user evaluations of a typical 2-D visualization method for content-based MIR systems and a novel interface to improve MIR usability conclude that the functions of the 3-D system can significantly improve both the efcienc y and usability of Mir systems.
Book ChapterDOI
Feature Analysis and Normalization Approach for Robust Content-Based Music Retrieval to Encoded Audio with Different Bit Rates
Shuhei Hamawaki,Shintaro Funasawa,Jiro Katto,Hiromi Ishizaki,Keiichiro Hoashi,Yasuhiro Takishima +5 more
TL;DR: How the bit rate differences affect MIR results is examined, methods to normalize MFCC features extracted from encoded files with various bit rates are proposed, and their effects to stabilize MIR Results are shown.
Patent
Music-linked advertisement distoribution method, device, and system
TL;DR: In this paper, a song categorization module calculates degrees of association between an acoustic feature amount of a song being played (hereinafter, current song) and feature amounts of the song categories, and a song-related distribution object advertisement candidate group extraction module determines a distribution-object advertisement corresponding to a song category with a high degree of association.