Pitch detection of musical sounds using adaptive comb filters controlled by time delay

Tadokoro, Yoshiaki; Matsumoto, Wataru; Yamaguchi, Michiru

doi:10.1109/icme.2002.1035730

Cited by 6 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, our experiments suggest that the first layer corresponds to learning a non-linearlyspaced, non-constant bandwidth filter bank. Traditional signal processing based approaches use techniques such as salience mapping [11,1] or comb filtering [18,19] in the second layer in order to enhance the pitch state of the interest. The two approaches are closely related and amount to summing certain frequencies in the desired frequency ranges.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Frequency Estimation from Waveforms Using Multi-Layered Neural Networks

Verma¹,

Schafer²

2016

Interspeech 2016

View full text Add to dashboard Cite

For frequency estimation in noisy speech or music signals, time domain methods based on signal processing techniques such as autocorrelation or average magnitude difference, often do not perform well. As deep neural networks (DNNs) have become feasible, some researchers have attempted with some success to improve the performance of signal processing based methods by learning on autocorrelation, Fourier transform or constant-Q filter bank based representations. In our approach, blocks of signal samples are input directly to a neural network to perform end to end learning. The emergence of subharmonic structure in the posterior vector of the output layer, along with analysis of the filter-like structures emerging in the DNN shows strong correlations with some signal processing based approaches. These NNs appear to learn a nonlinearlyspaced frequency representation in the first layer followed by comb-like filters. We find that learning representations from raw time-domain signals can achieve performance on par with the current state of the art algorithms for frequency estimation in noisy and polyphonic settings. The emergence of subharmonic structure in the posterior vector suggests that existing post-processing techniques such as harmonic product spectra and salience mapping may further improve the performance.

show abstract

Section: Discussionmentioning

confidence: 99%

“…We have studied fully connected networks that can map vectors of signal samples directly to the corresponding pitch states. We have found that the network learns a frequency representation in the first layer followed by comb filtering-like processing similar to [18,19]…”

Section: Related Workmentioning

confidence: 99%

Frequency Estimation from Waveforms Using Multi-Layered Neural Networks

Verma¹,

Schafer²

2016

Interspeech 2016

View full text Add to dashboard Cite

show abstract

“…To overcome these problems, we proposed another two method. One of them is based on the cascade connected adaptive comb filters where the necessary number of the cascaded comb filters is the minimum number that is necessary for a polyphony input, for example, three adaptive comb filters for the tones less than triple tones [10]. The other is the method that uses twelve comb filters connected in parallel and singular value decomposition (SVD) processing as shown in Fig.3 [11].…”

Section: Introductionmentioning

confidence: 99%

Pitch detection of musical sounds noticing minimum output of parallel connected comb filters

Tadokoro

Morita

Yamaguchi

TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region

Self Cite

View full text Add to dashboard Cite

This paper proposes a simple pitch detection method using the parallel connected comb filters. We can know the pitches of a musical sound by detecting the smaller outputs in twelve comb filters connected in parallel. Each comb filter has zero points corresponding to each pitch and its harmonic frequencies, and so the outputs of the comb filters corresponding to input pitch frequencies have smaller frequency components, and show smaller outputs than other comb filters' ones. We could detect the pitches with the probability of 98.2% for double tones and 91.1% for triple tones.

show abstract

GA-based Approach to Pitch Recognition of Musical Consonance

Natsui

Kubo

Tadokoro

Informatics in Control Automation and Robotics

View full text Add to dashboard Cite

Pitch detection of musical sounds using adaptive comb filters controlled by time delay

Cited by 6 publications

References 4 publications

Frequency Estimation from Waveforms Using Multi-Layered Neural Networks

Frequency Estimation from Waveforms Using Multi-Layered Neural Networks

Pitch detection of musical sounds noticing minimum output of parallel connected comb filters

GA-based Approach to Pitch Recognition of Musical Consonance

Contact Info

Product

Resources

About