Use of adaptive digital signal processing to improve speech communication for normally hearing and hearing-impaired subjects.

A two microphone adaptive digital noise cancellation technique was used to improve word-recognition ability of normally hearing and hearing-impaired subjects in the presence of varying amounts of multitalker speech babble noise and speech spectrum noise. Signal-to-noise ratios varied from -8 dB to +12 dB in 4 dB increments. The adaptive noise cancellation technique resulted in reducing both the speech babble and speech spectrum noises 18 to 22 dB. This reduction in noise resulted in average improvements in word recognition, at the poorest signal-to-noise ratios, ranging from 37% to 50% for the normally hearing subjects and 27% to 40% for the hearing-impaired subjects. Improvements in word recognition in the presence of speech babble noise as a result of adaptive filtering were just as large or larger than improvements found in the presence of speech spectrum noise. The amount of improvement of word-recognition scores was most pronounced at the least favorable signal-to-noise ratios.

Application of adaptive digital signal processing to speech enhancement for the hearing impaired.

A major complaint of individuals with normal hearing and hearing impairments is a reduced ability to understand speech in a noisy environment. This paper describes the concept of adaptive noise cancelling for removing noise from corrupted speech signals. Application of adaptive digital signal processing has long been known and is described from a historical as well as technical perspective. The Widrow-Hoff LMS (least mean square) algorithm developed in 1959 forms the introduction to modern adaptive signal processing. This method uses a "primary" input which consists of the desired speech signal corrupted with noise and a second "reference" signal which is used to estimate the primary noise signal. By subtracting the adaptively filtered estimate of the noise, the desired speech signal is obtained. Recent developments in the field as they relate to noise cancellation are described. These developments include more computationally efficient algorithms as well as algorithms that exhibit improved learning performance. A second method for removing noise from speech, for use when no independent reference for the noise exists, is referred to as single channel noise suppression. Both adaptive and spectral subtraction techniques have been applied to this problem--often with the result of decreased speech intelligibility. Current techniques applied to this problem are described, including signal processing techniques that offer promise in the noise suppression application.

Improvement in speech intelligibility in noise employing an adaptive filter with normal and hearing-impaired subjects.

It is well known that communication in noisy environments with reverberation present is a difficult problem to solve, particularly for the hearing-impaired listener. Two-microphone noise cancelling using an LMS adaptive filter in real time was used to process speech recorded in the presence of speech-spectrum noise at six different signal-to-noise ratios, -8, -4, 0, 4, 8, and 12 dB. Twelve normal-hearing and 11 sensorineural hearing-impaired subjects were tested. Results indicated mean improvement of 37.34 percent for the 12 normal-hearing subjects and 38.3 percent for 5 of the sensorineural hearing-impaired subjects. Individual data for the 5 remaining hearing-impaired subjects revealed severe speech intelligibility deficits when noise and reverberation contaminated the speech signal. It is proposed that rehabilitative audiological assessments include evaluation of an individual's ability to cope with reverberation and noise.