TY - JOUR
T1 - Auditory inspired machine learning techniques can improve speech intelligibility and quality for hearing-impaired listeners
AU - Monaghan, Jessica J. M.
AU - Goehring, Tobias
AU - Yang, Xin
AU - Bolner, Federico
AU - Wang, Shangqiguo
AU - Wright, Matthew C. M.
AU - Bleeck, Stefan
PY - 2017/3
Y1 - 2017/3
N2 - Machine-learning based approaches to speech enhancement have recently shown great promise for improving speech intelligibility for hearing-impaired listeners. Here, the performance of three machine-learning algorithms and one classical algorithm, Wiener filtering, was compared. Two algorithms based on neural networks were examined, one using a previously reported feature set and one using a feature set derived from an auditory model. The third machine-learning approach was a dictionary-based sparse-coding algorithm. Speech intelligibility and quality scores were obtained for participants with mild-to-moderate hearing impairments listening to sentences in speech-shaped noise and multi-talker babble following processing with the algorithms. Intelligibility and quality scores were significantly improved by each of the three machine-learning approaches, but not by the classical approach. The largest improvements for both speech intelligibility and quality were found by implementing a neural network using the feature set based on auditory modeling. Furthermore, neural network based techniques appeared more promising than dictionary-based, sparse coding in terms of performance and ease of implementation.
AB - Machine-learning based approaches to speech enhancement have recently shown great promise for improving speech intelligibility for hearing-impaired listeners. Here, the performance of three machine-learning algorithms and one classical algorithm, Wiener filtering, was compared. Two algorithms based on neural networks were examined, one using a previously reported feature set and one using a feature set derived from an auditory model. The third machine-learning approach was a dictionary-based sparse-coding algorithm. Speech intelligibility and quality scores were obtained for participants with mild-to-moderate hearing impairments listening to sentences in speech-shaped noise and multi-talker babble following processing with the algorithms. Intelligibility and quality scores were significantly improved by each of the three machine-learning approaches, but not by the classical approach. The largest improvements for both speech intelligibility and quality were found by implementing a neural network using the feature set based on auditory modeling. Furthermore, neural network based techniques appeared more promising than dictionary-based, sparse coding in terms of performance and ease of implementation.
UR - http://www.scopus.com/inward/record.url?scp=85041191034&partnerID=8YFLogxK
U2 - 10.1121/1.4977197
DO - 10.1121/1.4977197
M3 - Article
VL - 141
SP - 1985
EP - 1998
JO - The Journal of the Acoustical Society of America
JF - The Journal of the Acoustical Society of America
SN - 0001-4966
IS - 3
ER -