We propose the design of a hearing aid device based on the wavelet transform. The fast wavelet transform is used to decompose speech into diierent frequency components. This paper presents the diiculties in the use of wavelet transforms for speech processing, and shows how the careful selection of wavelet coeecients can enable the four major categories of speech-voiced speech, plosives, fricati...

The Teleface project, a project that aims at evaluating the possibilities for a telephone communication aid for the hard of hearing, is presented as well as the different parts of the project: audio-visual speech synthesis, visual speech measurement and multimodal speech intelligibility studies. Some results from the first test series are presented. Introduction It is well known that visual inf...

Using similar recording and analysis techniques, the long-term average speech spectra of English and Mandarin were compared in order to identify difference that might influence hearing-aid fitting strategies. Despite the well-documented pitch contour differences between English and Mandarin, no significant difference was found in the long-term average spectral analysis. Implications for hearing...

OBJECTIVE The aim was to investigate whether frequency compression (FC) hearing aids provide additional benefit to that conferred by conventional amplification. DESIGN Participants wore the same hearing aid with FC enabled and disabled for six weeks (ABA design) in each condition. Speech recognition tests (in both quiet and in noise) were administered alongside two questionnaires. Performance...

The present study investigated the effects of monaural and binaural amplification on speech understanding in noise and acceptance of noise for 39 listeners with hearing impairment. Results demonstrated that speech understanding in noise improved with binaural amplification; however, acceptance of noise was not dependent on monaural or binaural amplification for most listeners. These results sug...

A custom in-the-ear (ITE) hearing aid fitting was compared to two over-the-ear (OTE) hearing aid fittings for each of 9 subjects with mild to moderately severe hearing losses. Speech intelligibility via the three instruments was compared using the Speech Intelligibility Rating (SIR) test. The relationship between functional gain and coupler gain was compared for the ITE and the higher rated OTE...

This study has been performed in order to evaluate a prototype for the human – computer interface of a computer-based speech training aid named ARTUR. The main feature of the aid is that it can give suggestions on how to improve articulations. Two user groups were involved: three children aged 9 – 14 with extensive experience of speech training with therapists and computers, and three children ...

Speech-recognition thresholds (SRTs) were obtained in nine sensorineural hearing-impaired subjects wearing an adaptive-filter hearing aid under four separate listening conditions. The SRT was obtained with the filter in and out of the circuit in order to relate the effects of noise reduction to speech recognition performance. The noise level was held constant while the speech level varied (tran...

Measurement of hearing aid outcome is particularly difficult because there are numerous dimensions to consider (e.g., performance, satisfaction, benefit). Often there are discrepancies between scores in these dimensions. It is difficult to reconcile these discrepancies because the materials and formats used to measure each dimension are so very different. We report data obtained with an outcome...

Currently, in uncorrupted acoustic environments, a state-of-the-art, continuous speech, 5000word vocabulary speech recognizer can achieve a recognition accuracy of 95%. In a telephone channel acoustic environment, the same recognition system can double in error rate, which is unacceptable for most applications. It is the goal of this project to quantitatively measure how well a speech recogniti...