Instantaneous Pitch Estimation via Wave-U-Net-Based Fundamental Waveform Enhancement
For researchers and practitioners in audio processing, this method provides more accurate and robust pitch estimation, especially for steep variations and degraded signals.
The authors propose a Wave-U-Net-based method for fundamental waveform enhancement to improve instantaneous pitch estimation, outperforming conventional deterministic approaches across speech, singing, musical instruments, and degraded signals.
Instantaneous pitch estimation plays an important role in analyzing steep pitch variations such as speech prosody and singing techniques. Conventional approaches estimate instantaneous frequency after isolating the fundamental waveform from signals that contain harmonics and noise, which makes the accuracy sensitive to imperfect fundamental filtering. In this study, we formulate fundamental waveform filtering as a speech enhancement problem. Specifically, we train a Wave-U-Net model to extract a fundamental waveform from an input speech signal. The instantaneous pitch is then obtained by computing the instantaneous frequency from the analytic signal of the estimated fundamental waveform. Experimental results show that the proposed method outperforms conventional deterministic approaches and provides accurate and robust instantaneous pitch estimation across diverse domains, including speech, singing voice, musical instruments, and degraded speech signals.