Phoneme-Based Ratio Mask Estimation for Reverberant Speech Enhancement in Cochlear Implant Processors

TL;DR

This paper introduces a phoneme-based mask estimation method for reverberant speech enhancement in cochlear implants, showing improved speech intelligibility when perfect phoneme knowledge is used, indicating potential benefits for CI users.

Contribution

It proposes a novel phoneme-specific mask estimation approach that leverages phonemic information to improve reverberant speech enhancement for cochlear implant users.

Findings

Phoneme-based masks outperform conventional masks in speech intelligibility.

Perfect phoneme knowledge enhances mask effectiveness.

Results suggest potential benefits for cochlear implant users in reverberant environments.

Abstract

Cochlear implant (CI) users have considerable difficulty in understanding speech in reverberant listening environments. Time-frequency (T-F) masking is a common technique that aims to improve speech intelligibility by multiplying reverberant speech by a matrix of gain values to suppress T-F bins dominated by reverberation. Recently proposed mask estimation algorithms leverage machine learning approaches to distinguish between target speech and reverberant reflections. However, the spectro-temporal structure of speech is highly variable and dependent on the underlying phoneme. One way to potentially overcome this variability is to leverage explicit knowledge of phonemic information during mask estimation. This study proposes a phoneme-based mask estimation algorithm, where separate mask estimation models are trained for each phoneme. Sentence recognition tests were conducted in normal hearing listeners to determine whether a phoneme-based mask estimation algorithm is beneficial in the ideal scenario where perfect knowledge of the phoneme is available. The results showed that the phoneme-based masks improved the intelligibility of vocoded speech when compared to conventional phoneme-independent masks. The results suggest that a phoneme-based speech enhancement strategy may potentially benefit CI users in reverberant listening environments.