Phoneme-Based Ratio Mask Estimation for Reverberant Speech Enhancement in Cochlear Implant Processors
This addresses speech enhancement in cochlear implants for users in reverberant settings, but it is incremental as it builds on existing mask estimation methods by incorporating phonemic information.
The study tackled speech intelligibility for cochlear implant users in reverberant environments by proposing a phoneme-based mask estimation algorithm, which improved intelligibility compared to conventional masks in tests with normal hearing listeners.
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.