A Genetic Algorithm Approach with Harmonic Structure Evolution for Polyphonic Music Transcription

Reis, Gustavo; Fonseca, Nuno; Fernandez, Francisco Javier Ramírez; Ferreira, Aníbal

doi:10.1109/isspit.2008.4775722

Cited by 3 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors explored the influence of the "harmonic overfitting" phenomena, which is related to differences in the spectral envelope between different pianos. In 2008 Reis et al [20] proposed a new algorithm with adaptive spectral envelope modeling to reduce the impact of the harmonic overfitting, and later, in 2009 [21], the latter approach was extended to multi-timbre.…”

Section: A Genetic Algorithms and Multiple-f0 Estimationmentioning

confidence: 99%

“…Reis'09 [21] was included for comparison because we believe it is the best algorithm of all previous genetic algorithm approaches: Garcia algorithm [15] does not take into account onset time and offset time, Lu's approach [16] and Reis and Fernandez's algorithm [18] are limited to simple mathematical models (e.g., sawtooth wave, rectangle wave, sine wave) and for Reis et al [19], although it applies the first genetic algorithm approach to music transcription using real audio recordings, it lacks a means to deal with harmonic overfitting. Also, Reis et al [20] and [21] are essentially the same algorithm, except that the latter approach was extended to multi-timbre. This way, we can see how our proposal performs when compared to the previous best genetic algorithm approaches to automatic music transcription.…”

Section: Comparison With Other State-of-the-art Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation

Reis

Vega

Ferreira

2012

IEEE Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

This paper presents a new method for multiple fundamental frequency (F0) estimation on piano recordings. We propose a framework based on a genetic algorithm in order to analyze the overlapping overtones and search for the most likely F0 combination. The search process is aided by adaptive spectral envelope modeling and dynamic noise level estimation: while the noise is dynamically estimated, the spectral envelope of previously recorded piano samples (internal database) is adapted in order to best match the piano played on the input signals and aid the search process for the most likely combination of F0s. For comparison, several state-of-the-art algorithms were run across various musical pieces played by different pianos and then compared using three different metrics. The proposed algorithm ranked first place on Hybrid Decay/Sustain Score metric, which has better correlation with the human hearing perception and ranked second place on both onset-only and onset-offset metrics. A previous genetic algorithm approach is also included in the comparison to show how the proposed system brings significant improvements on both quality of the results and computing time.

show abstract

Section: A Genetic Algorithms and Multiple-f0 Estimationmentioning

confidence: 99%

Section: Comparison With Other State-of-the-art Algorithmsmentioning

confidence: 99%

Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation

Reis

Vega

Ferreira

2012

IEEE Trans. Audio Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

show abstract

“…To avoid the problem of harmonic overfitting, Reis et al [21] extended their previous approach [20] by creating harmonic gains that boost or cut the value of the 20 first harmonic peaks of each synthesized note. Those gains act almost like an equalizer but instead of operating in fixed frequency bands, they operate on each note harmonic.…”

Section: Genotypementioning

confidence: 99%

“…Another feature proposed by Reis et al [21] as a means to avoid the harmonic overfitting is note discard. Note discard is based on the assumption that most notes have similar dynamics.…”

Section: Note Discardmentioning

confidence: 99%

See 1 more Smart Citation

Evolutionary algorithms and automatic transcription of music

Reis

Fernandez

Ferreira

2012

Proceedings of the 14th Annual Conference Companion on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

The main problem behind Automatic Transcription (Multiple Fundamental Frequency -F0 -Estimation) relies on its complexity. Harmonic collision and partial overlapping create a frequency lattice that is almost impossible to deconstruct. Although traditional approaches to this problem of rely mainly in Digital Signal Processing (DSP) techniques, evolutionary algorithms have been applied recently to this problem and achieved competitive results. We describe all evolutionary approaches to the problem of automatic music transcription and how some were improved so they could achieve competitive results. Finally, we show how the best evolutionary approach performs on piano transcription, when compared with the state-of-the-art.

show abstract

Evolving a multi-classifier system with cartesian genetic programming for multi-pitch estimation of polyphonic piano music

Miragaia

Vega

Reis

2021

Proceedings of the 36th Annual ACM Symposium on Applied Computing

View full text Add to dashboard Cite

A Genetic Algorithm Approach with Harmonic Structure Evolution for Polyphonic Music Transcription

Cited by 3 publications

References 7 publications

Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation

Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level Estimation

Evolutionary algorithms and automatic transcription of music

Evolving a multi-classifier system with cartesian genetic programming for multi-pitch estimation of polyphonic piano music

Contact Info

Product

Resources

About