OneBitPitch (OBP): Ultra-High-Speed Pitch Detection Algorithm Based on One-Bit Quantization and Modified Autocorrelation

Abstract

This paper presents a novel, high-speed, and low-complexity algorithm for pitch (F0) detection, along with a new dataset for testing and a comparison of some of the most effective existing techniques. The algorithm, called OneBitPitch (OBP), is based on a modified autocorrelation function applied to a single-bit signal for fast computation. The focus is explicitly on speed for real-time pitch detection applications in pitch detection. A testing procedure is proposed using a proprietary synthetic dataset (SYNTHPITCH) against three of the most widely used algorithms: YIN, SWIPE (Sawtooth Inspired Pitch Estimator) and NLS (Nonlinear-Least Squares-based). The results show how OBP is 9 times faster than the fastest of its alternatives, and 50 times faster than a gold standard like SWIPE, with a mean elapsed time of 4.6 ms, or 0.046 × realtime. OBP is slightly less accurate for high-precision landmarks and noisy signals, but its performance in terms of acceptable error (<2%) is comparable to YIN and SWIPE. NLS emerges as the most accurate, but it is not flexible, being dependent on the input and requiring prior setup. OBP shows to be robust to octave errors while providing acceptable accuracies at ultra-high speeds, with a building nature suited for FPGA (Field-Programmable Gate Array) implementations.

Keywords

• pitch detection
• F0
• algorithm
• auto-tune
• audio signal processing