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

TL;DR

This paper introduces a hybrid pitch estimation method combining a small neural network with traditional DSP features, achieving high accuracy with low complexity suitable for real-time speech processing.

Contribution

A novel hybrid approach that integrates a small DNN with DSP features to match or surpass pure DNN estimators in performance and efficiency.

Findings

Hybrid estimator matches or exceeds pure DNN performance.

Achieves low complexity and minimal delay suitable for real-time applications.

Benefits neural vocoding tasks with the proposed method.

Abstract

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 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.