Harmonic Summation-Based Robust Pitch Estimation in Noisy and Reverberant Environments

2025-09-19

AI Summary

To address the low fundamental frequency (F0) estimation accuracy under high-noise and strongly reverberant conditions, this paper proposes a robust pitch-tracking method based on harmonic summation. The method comprises three key contributions: (1) a mapping from the normalized average magnitude difference function (NAMDF) to frame-level pitch-state probabilities, enabling probabilistic pitch representation; (2) cross-harmonic octave modeling combined with inter-frame likelihood aggregation to enhance robustness in periodicity detection; and (3) integration of pitch continuity constraints into the Viterbi decoding process to improve decision stability amid multiple competing pitch candidates. Experimental results demonstrate that the proposed approach significantly reduces both gross pitch error (GPE) and voicing decision error (VDE) across a wide signal-to-noise ratio (SNR) range, consistently outperforming state-of-the-art methods in comprehensive evaluations.

Technology Category

Intelligent Robots: State EstimationSearch and Optimization: Mixed Discrete/Continuous SearchPlanning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

Web Mining and Content Analysis: Robustness and generalizability of Web mining methodsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsGraph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Accurate pitch estimation is essential for numerous speech processing applications, yet it remains challenging in high-distortion environments. This paper proposes a robust pitch estimation method that delivers robust pitch estimates in challenging noise environments. Our approach computes the Normalized Average Magnitude Difference Function (NAMDF), transforms it into a likelihood function, and generates probabilistic pitch states for frames at each sample shift. To enhance noise robustness, we aggregate likelihood values across integer multiples of the pitch period and neighboring frames. Furthermore, we introduce a simple yet effective continuity constraint in the Viterbi algorithm to refine pitch selection among multiple candidates. Experimental results show that our method consistently achieves lower Gross Pitch Error (GPE) and Voicing Decision Error (VDE) across various SNR levels, outperforming existing methods in both noisy and reverberant conditions.

Problem

• Robust pitch estimation in noisy and reverberant environments
• Enhancing noise robustness through harmonic likelihood aggregation
• Improving pitch accuracy using continuity constraints in Viterbi algorithm

Innovation

• NAMDF transformation into likelihood function
• Harmonic summation across pitch periods
• Viterbi algorithm with continuity constraint