Noise-Robust DSP-Assisted Neural Pitch Estimation With Very Low Complexity

• Published in: Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 11851 - 11855
• Main Authors: Subramani, Krishna, Valin, Jean-Marc, Buthe, Jan, Smaragdis, Paris, Goodwin, Mike
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.04.2024
• Subjects: Artificial neural networks; Estimation; Frequency estimation; instantaneous frequency; Pitch estimation; Real-time systems; Signal processing; Signal processing algorithms; Speech coding
• ISSN: 2379-190X
• DOI: 10.1109/ICASSP48485.2024.10447962

Pitch estimation is an essential step of many speech processing algorithms, including speech coding, synthesis, and enhancement. Recently, pitch estimators based on deep neural networks (DNNs) have been outperforming well-established DSP-based techniques. Unfortunately, these new estimators can be impractical to deploy in real-time systems, both because of their relatively high complexity, and the fact that some require significant lookahead. We show that a hybrid estimator using a small deep neural network (DNN) with traditional DSP-based features can match or exceed the performance of pure DNN-based models, with a complexity and algorithmic delay comparable to traditional DSP-based algorithms. We further demonstrate that this hybrid approach can provide benefits for a neural vocoding task.