Top Cited Papers
Open Access
- 20 March 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 28 (23299290) , 1118-1128
Abstract
We propose a model to estimate the fundamental frequency in monophonic audio, often referred to as pitch estimation. We acknowledge the fact that obtaining ground truth annotations at the required temporal and frequency resolution is a particularly daunting task. Therefore, we propose to adopt a self-supervised learning technique, which is able to estimate pitch without any form of supervision. The key observation is that pitch shift maps to a simple translation when the audio signal is analysed through the lens of the constant-Q transform (CQT). We design a self-supervised task by feeding two shifted slices of the CQT to the same convolutional encoder, and require that the difference in the outputs is proportional to the corresponding difference in pitch. In addition, we introduce a small model head on top of the encoder, which is able to determine the confidence of the pitch estimate, so as to distinguish between voiced and unvoiced audio. Our results show that the proposed method is able to estimate pitch at a level of accuracy comparable to fully supervised models, both on clean and noisy audio samples, yet it does not require access to large labeled datasets.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Neural Network Based Pitch Tracking in Very Noisy SpeechIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014
- Deep Scattering SpectrumIEEE Transactions on Signal Processing, 2014
- Absolute and relative pitch: Global versus local processing of chordsAdvances in Cognitive Psychology, 2014
- Melody Extraction from Polyphonic Music Signals: Approaches, applications, and challengesIEEE Signal Processing Magazine, 2014
- A sawtooth waveform inspired pitch estimator for speech and musicThe Journal of the Acoustical Society of America, 2008
- Comparison of pitch detection by cepstrum and spectral comb analysis2005
- The ETSI extended distributed speech recognition (DSR) standards: server-side speech reconstruction2004
- New phase-vocoder techniques for pitch-shifting, harmonizing and other exotic effects2003
- Real-time digital hardware pitch detectorIEEE Transactions on Acoustics, Speech, and Signal Processing, 1976
- Robust Estimation of a Location ParameterThe Annals of Mathematical Statistics, 1964