An Auditory-Masking-Threshold-Based Noise Suppression Algorithm GMMSE-AMT[ERB] for Listeners with Sensorineural Hearing
- PDF / 1,130,601 Bytes
- 16 Pages / 600 x 792 pts Page_size
- 12 Downloads / 228 Views
An Auditory-Masking-Threshold-Based Noise Suppression Algorithm GMMSE-AMT[ERB] for Listeners with Sensorineural Hearing Loss Ajay Natarajan Robust Speech Processing Group, Center for Spoken Language Research, and Department of Electrical and Computer Engineering, University of Colorado at Boulder, Boulder, CO 80309-0309, USA Email: [email protected]
John H. L. Hansen Center for Robust Speech Systems, Department of Electrical Engineering, Erik Jonsson School of Engineering & Computer Science, and Callier Center (Speech and Hearing), School of Behavioral and Brain Sciences, University of Texas at Dallas, Richardson, TX 75083, USA Email: [email protected]
Kathryn Hoberg Arehart Department of Speech, Language and Hearing Sciences, University of Colorado at Boulder, 2501 Kittredge Loop Road, UCB 409, Boulder, CO 80309-0409, USA Email: [email protected]
Jessica Rossi-Katz Department of Speech, Language and Hearing Sciences, University of Colorado at Boulder, 2501 Kittredge Loop Road, UCB 409, Boulder, CO 80309-0409, USA Email: [email protected] Received 6 May 2004; Revised 21 December 2004 This study describes a new noise suppression scheme for hearing aid applications based on the auditory masking threshold (AMT) in conjunction with a modified generalized minimum mean square error estimator (GMMSE) for individual subjects with hearing loss. The representation of cochlear frequency resolution is achieved in terms of auditory filter equivalent rectangular bandwidths (ERBs). Estimation of AMT and spreading functions for masking are implemented in two ways: with normal auditory thresholds and normal auditory filter bandwidths (GMMSE-AMT[ERB]-NH) and with elevated thresholds and broader auditory filters characteristic of cochlear hearing loss (GMMSE-AMT[ERB]-HI). Evaluation is performed using speech corpora with objective quality measures (segmental SNR, Itakura-Saito), along with formal listener evaluations of speech quality rating and intelligibility. While no measurable changes in intelligibility occurred, evaluations showed quality improvement with both algorithm implementations. However, the customized formulation based on individual hearing losses was similar in performance to the formulation based on the normal auditory system. Keywords and phrases: normal hearing, hearing impaired, auditory masking threshold, equivalent rectangular bandwidth, generalized minimum mean square estimation.
1.
INTRODUCTION
Individuals with sensorineural hearing loss have more difficulty understanding speech compared to those with normal hearing. This effect is compounded in diverse environments that may contain time varying cues/signals or multiple competing speakers. This increased difficulty in understanding speech in noise is due to (a) reduced audibility of speech sounds in listeners with elevated auditory thresholds,
and (b) suprathreshold processing deficits characteristic of sensorineural hearing loss. Hearing aids incorporate different strategies to compensate for reduced audibility and for suprathreshold pr
Data Loading...