FRICATIVE PHONEME DETECTION WITH ZERO DELAY

Metehan Yurt, Alberto N. Escalante B., Veniamin I. Morgenshtern

Keywords: fricative detection, phoneme detection, speech recognition, deep learning, hearing aids, zero delay, extrapolation, TIMIT

TL;DR: A deep learning based approach for zero delay fricative phoneme detection

Abstract: People with high-frequency hearing loss rely on hearing aids that employ frequency lowering algorithms. These algorithms shift some of the sounds from the high frequency band to the lower frequency band where the sounds become more perceptible for the people with the condition. Fricative phonemes have an important part of their content concentrated in high frequency bands. It is important that the frequency lowering algorithm is activated exactly for the duration of a fricative phoneme, and kept off at all other times. Therefore, timely (with zero delay) and accurate fricative phoneme detection is a key problem for high quality hearing aids. In this paper we present a deep learning based fricative phoneme detection algorithm that has zero detection delay and achieves state-of-the-art fricative phoneme detection accuracy on the TIMIT Speech Corpus. All reported results are reproducible and come with easy to use code that could serve as a baseline for future research.

Code: https://www.dropbox.com/s/kqlw6xc1ff8lu3l/fricatives-master.zip?dl=0