Classification of background noises for hearing-aid applications.

A background-noise classification procedure is being developed for hearing-aid applications, wherein the hearing-aid response would be adjusted in response to changes in the noise environment. The classification procedure is based on measuring four signal features giving the fluctuations of the signal envelope and the mean frequency and low- and high-frequency slopes of the average spectrum. A more complicated procedure, based on determining the envelope modulation spectra in auditory critical bands, was also investigated and was found to offer no advantages over the simpler procedure. The accuracy of the classification procedure was determined for eleven everyday background noises under optimal conditions where the training and test noise sequences were different portions of the same short noise recording. A cluster analysis was used to determine the similarities among the feature vectors for the noises, and when the noises are grouped into a reduced number of clusters the noise-classification accuracy using the four features exceeds 90%.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  F K Kuk.  A Screening Procedure for Modified Simplex in Frequency‐Gain Response Selection , 1994, Ear and hearing.

[3]  D Byrne.  Effects of frequency response characteristics on speech discrimination and perceived intelligibility and pleasantness of speech for hearing-impaired listeners. , 1986, The Journal of the Acoustical Society of America.

[4]  J M Festen,et al.  The effect of varying the amplitude-frequency response on the masked speech-reception threshold of sentences for hearing-impaired listeners. , 1989, The Journal of the Acoustical Society of America.

[5]  R Plomp,et al.  The effect of varying the slope of the amplitude-frequency response on the masked speech-reception threshold of sentences. , 1987, The Journal of the Acoustical Society of America.

[6]  Jeffrey P. Woodard,et al.  Modeling and classification of natural sounds by product code hidden Markov models , 1992, IEEE Trans. Signal Process..

[7]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[8]  J L Punch,et al.  Aided Listener Preferences in Laboratory Versus Real‐World Environments , 1994, Ear and hearing.

[9]  P. Fitzgibbons,et al.  Gap detection in normal and hearing-impaired listeners. , 1982, The Journal of the Acoustical Society of America.

[10]  M. A. Bouman,et al.  Relation between Hearing Threshold and Duration for Tone Pulses , 1959 .

[11]  C S Watson,et al.  Signal duration and signal frequency in relation to auditory sesitivity. , 1969, The Journal of the Acoustical Society of America.

[12]  H. Dillon,et al.  The National Acoustic Laboratories' (NAL) New Procedure for Selecting the Gain and Frequency Response of a Hearing Aid , 1986, Ear and hearing.

[13]  James M. Kates,et al.  A time-domain digital cochlear model , 1991, IEEE Trans. Signal Process..

[14]  J M Festen,et al.  The effect of frequency-selective attenuation on the speech-reception threshold of sentences in conditions of low-frequency noise. , 1991, The Journal of the Acoustical Society of America.

[15]  B. Moore,et al.  Gap detection and masking in hearing-impaired and normal-hearing subjects. , 1987, The Journal of the Acoustical Society of America.

[16]  J M Kates,et al.  A test suite for hearing aid evaluation. , 1990, Journal of rehabilitation research and development.