Acoustic Modelling of Drum Sounds with Hidden Markov Models for Music Transcription

Paulus, Jouni

doi:10.1109/icassp.2006.1661257

Cited by 4 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To get an accurate FFT, music samples are segmented into 23 ms frames [4]. When compared with other sample rates and segment size combinations, this gives the best performance [5].For windowing, Hamming window is used because the combination of Mel frequency and Hamming window gives improved results [6]. Thirteen MFCC coefficients are calculated for each window.…”

Section: ) Extracting Mfccmentioning

confidence: 99%

An Adaptive Approach to Identify Genre in Music Videos Using Word2Vec Model

Florence

Mohan

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-The vector representations of words presented by Word2Vec model have been shown to be very useful in many application developments due to the semantic information they convey. This paper proposes a similar form, the MusicGenre2Vec. MusicGenre2Vec represents the numerical genre features of music segments inside the vector with the intention to describe the phonetic systems of the tune segments in an excellent way. We are hoping the vector representations obtained in this way can describe more precisely the phonetic structures of the Music indicators, so the Music segments that sound alike would have vector representations close by within the space. This form of depiction is called MusicGenre2Vec in this paper. The proposed system gives 80% of accuracy in finding the Genre of a video song.

show abstract

Section: ) Extracting Mfccmentioning

confidence: 99%

An Adaptive Approach to Identify Genre in Music Videos Using Word2Vec Model

Florence

Mohan

2017

IJARCSSE

View full text Add to dashboard Cite

show abstract

“…While this procedure has proved particularly successful on solo drum signals [5], [6], its application to polyphonic music [7]- [9] is more challenging, as most of the features used for classification are sensitive to the presence of background music. Efforts have been made lately by Paulus [10] to jointly perform the segmentation and the classification, as a single decoding process of a hidden Markov model. A second procedure consists in searching for occurrences of a reference temporal [11] or time-frequency [12] template within the music signal.…”

Section: Introductionmentioning

confidence: 99%

Transcription and Separation of Drum Signals From Polyphonic Music

Gillet

Richard

2008

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-The purpose of this article is to present new advances in music transcription and source separation with a focus on drum signals. A complete drum transcription system is described, which combines information from the original music signal and a drum track enhanced version obtained by source separation. In addition to efficient fusion strategies to take into account these two complementary sources of information, the transcription system integrates a large set of features, optimally selected by feature selection. Concurrently, the problem of drum track extraction from polyphonic music is tackled both by proposing a novel approach based on harmonic/noise decomposition and time/frequency masking and by improving an existing Wiener filtering-based separation method. The separation and transcription techniques presented are thoroughly evaluated on a large public database of music signals. A transcription accuracy between 64.5% and 80.3% is obtained, depending on the drum instrument, for well-balanced mixes, and the efficiency of our drum separation algorithms is illustrated in a comprehensive benchmark.

show abstract