• Publications
  • Influence
SIFT-based local spectrogram image descriptor: a novel feature for robust music identification
TLDR
We propose to use scale invariant feature transform (SIFT) local descriptors computed from a spectrogram image as sub-fingerprints for music identification. Expand
  • 23
  • 5
A careful look at ECG sampling frequency and R-peak interpolation on short-term measures of heart rate variability.
As the literature on heart rate variability (HRV) continues to burgeon, so too do the challenges faced with comparing results across studies conducted under different recording conditions andExpand
  • 47
  • 2
  • PDF
Multi-Stage Non-Negative Matrix Factorization for Monaural Singing Voice Separation
TLDR
A novel algorithm for singing voice separation in monaural mixtures is proposed. Expand
  • 46
  • 2
  • PDF
A novel audio fingerprinting method robust to time scale modification and pitch shifting
TLDR
A novel audio fingerprinting method that is highly robust to Time Scale Modification (TSM) and pitch shifting is proposed. Expand
  • 33
  • 2
On the music content authentication
TLDR
We propose a novel algorithm to protect the integrity and authenticity of music signals by segmenting them into beat-based frames and using fuzzy logic. Expand
  • 3
Fusing transcription results from polyphonic and monophonic audio for singing melody transcription in polyphonic music
TLDR
This paper presents a new system for singing melody transcription from polyphonic songs where multiple monophonic recordings of people singing the song. Expand
  • 4
  • PDF
Estimating double tuned mass dampers for structures under ground acceleration using a novel optimum criterion
The double tuned mass dampers (DTMD), consisting of one larger mass block (i.e. one larger tuned mass damper (TMD)) and one smaller mass block (i.e. one smaller TMD), have been proposed to seek forExpand
  • 46
Latent time-frequency component analysis: A novel pitch-based approach for singing voice separation
TLDR
We propose an algorithm for singing voice separation in monaural mixtures, based on the latent timefrequency component analysis of time-frequency representations of the original input song mixture, to overcome the missing information. Expand
  • 4
Towards Solving the Bottleneck of Pitch-based Singing Voice Separation
TLDR
Singing voice separation from accompaniment in monaural music recordings is a crucial technique in music information retrieval. Expand
  • 2
Vocal Melody Extraction via DNN-based Pitch Estimation and Salience-based Pitch Refinement
TLDR
We propose to use melody MIDI files, which are more massively available, as the sources of labels to train a deep neural network (DNN) model for melody extraction. Expand
  • 1
...
1
2
...