• Publications
  • Influence
Singer Identification Based on Accompaniment Sound Reduction and Reliable Frame Selection
TLDR
This paper describes a method for automatic singer identification from polyphonic musical audio signals including sounds of various instruments. Expand
  • 63
  • 7
  • PDF
A Modeling of Singing Voice Robust to Accompaniment Sounds and Its Application to Singer Identification and Vocal-Timbre-Similarity-Based Music Information Retrieval
TLDR
This paper describes a method of modeling the characteristics of a singing voice from polyphonic musical audio signals including sounds of various musical instruments. Expand
  • 76
  • 6
  • PDF
Instrument Identification in Polyphonic Music: Feature Weighting to Minimize Influence of Sound Overlaps
TLDR
We provide a new solution to the problem of feature variations caused by the overlapping of sounds in instrument identification in polyphonic music. Expand
  • 87
  • 5
  • PDF
Pitch-Dependent Identification of Musical Instrument Sounds
TLDR
This paper describes a musical instrument identification method that takes into consideration the pitch dependency of timbres of musical instruments. Expand
  • 25
  • 2
  • PDF
Instrogram: Probabilistic Representation of Instrument Existence for Polyphonic Music
TLDR
This paper presents a new technique for recognizing musical instruments in polyphonic music that calculates the temporal trajectory of instrument existence probabilities for every possible F0. Expand
  • 22
  • 2
  • PDF
Musical instrument identification based on F0-dependent multivariate normal distribution
TLDR
The pitch dependency of timbres has not been fully exploited in musical instrument identification. Expand
  • 25
  • 2
  • PDF
Environmental Sound Recognition for Robot Audition Using Matching-Pursuit
TLDR
This paper presents the environmental recognition of two sound sources fired simultaneously using matching pursuit (MP) with the Gabor wavelet, which extracts salient audio features from a signal. Expand
  • 24
  • 2
Using Bass-line Features for Content-Based MIR
TLDR
We propose new audio features that can be extracted from bass lines and apply them to automatic genre classification and music collection visualization. Expand
  • 10
  • 2
  • PDF
Music Genre Classification and Similarity Calculation Using Bass-Line Features
TLDR
We design new audio features to be extracted from bass lines to improve the similarity measure and classification accuracy. Expand
  • 6
  • 2
Automatic melody harmonization with triad chords: A comparative study
TLDR
We present a comparative study evaluating and comparing the performance of a set of canonical approaches to the task of automatic melody harmonization, including a template matching based model, a hidden Markov based model and two deep learning based models. Expand
  • 2
  • 2
  • PDF