ISCA Archive Interspeech 2023
ISCA Archive Interspeech 2023

Short-term Extrapolation of Speech Signals Using Recursive Neural Networks in the STFT Domain

Maurice Oberhag, Daniel Neudek, Rainer Martin, Tobias Rosenkranz, Henning Puder

This paper investigates several approaches for the short-term extrapolation of speech signals. The signal extrapolation methods are embedded into a nested two-stage spectral analysis-synthesis system for single-channel noise reduction in hearing aids. They predict additional signal samples in the low-frequency sub-bands of the first analysis stage and may compensate the additional algorithmic latency of the second, higher-resolution analysis stage in these bands. We thus achieve a higher spectral resolution in frequency bands below 3 kHz without increasing the algorithmic latency of the overall system. In the context of noise reduction, especially female voices benefit from the increased spectral resolution in the lower sub-bands of the first stage. We show that among the investigated approaches, both recursive neural-network-based extrapolation methods provide benefits in conjunction with a noise reduction algorithm and outperform our baseline linear extrapolation method.