A Phoneme-Scale Assessment of Multichannel Speech Enhancement Algorithms

In the intricate acoustic landscapes where speech intelligibility is challenged by noise and reverberation, multichannel speech enhancement emerges as a promising solution for individuals with hearing loss. Such algorithms are commonly evaluated at the utterance scale. However, this approach overlooks the granular acoustic nuances revealed by phoneme-specific analysis, potentially obscuring key insights into their performance. This paper presents an in-depth phoneme-scale evaluation of three state-of-the-art multichannel speech enhancement algorithms. These algorithms-filter-and-sum network, minimum variance distortionless response, and Tango-are here extensively evaluated across different noise conditions and spatial setups, employing realistic acoustic simulations with measured room impulse responses, and leveraging diversity offered by multiple microphones in a binaural hearing setup. The study emphasizes the fine-grained phoneme-scale analysis, revealing that while some phonemes like plosives are heavily impacted by environmental acoustics and challenging to deal with by the algorithms, others like nasals and sibilants see substantial improvements after enhancement. These investigations demonstrate important improvements in phoneme clarity in noisy conditions, with insights that could drive the development of more personalized and phoneme-aware hearing aid technologies. Additionally, while this study provides extensive data on the physical metrics of processed speech, these physical metrics do not necessarily imitate human perceptions of speech, and the impact of the findings presented would have to be investigated through listening tests.