scholarly journals Enhancement of Speech Intelligibility using Binary Mask Based on Noise Constraints

2019 ◽  
Vol 8 (3) ◽  
pp. 3509-3516
Keyword(s):  
Hearing Aids ◽  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Random Noise ◽  
Wiener Filter ◽  
Binary Mask ◽  
Gain Function ◽  
Magnitude Spectrum ◽  
Objective Tests ◽  
Babble Noise

The primary aim of this paper is to examine the application of binary mask to improve intelligibility in most unfavorable conditions where hearing impaired/normal listeners find it difficult to understand what is being told. Most of the existing noise reduction algorithms are known to improve the speech quality but they hardly improve speech intelligibility. The paper proposed by Gibak Kim and Philipos C. Loizou uses the Weiner gain function for improving speech intelligibility. Here, in this paper we have proposed to apply the same approach in magnitude spectrum using the parametric wiener filter in order to study its effects on overall speech intelligibility. Subjective and objective tests were conducted to evaluate the performance of the enhanced speech for various types of noises. The results clearly indicate that there is an improvement in average segmental signal-to-noise ratio for the speech corrupted at -5dB, 0dB, 5dB and 10dB SNR values for random noise, babble noise, car noise and helicopter noise. This technique can be used in real time applications, such as mobile, hearing aids and speech–activated machines

scholarly journals Enhancement of Speech Intelligibility using Binary Mask Based on Channel Selection Criteria

2020 ◽  
Vol 8 (5) ◽  
pp. 5123-5131
Keyword(s):  
Noise Reduction ◽  
Speech Intelligibility ◽  
Selection Criteria ◽  
Signal To Noise Ratio ◽  
Random Noise ◽  
Wiener Filter ◽  
Gain Function ◽  
Signal To Noise ◽  
Short Time ◽  
Noise Reduction Algorithm

Most of the existing noise reduction algorithms used in hearing aid applications apply a gain function in order to reduce the noise intervention. In the present paper, we study the effect of the two types of speech distortions introduced by the gain functions. If these distortions are properly controlled large gains in intelligibility can be obtained. The sentences were corrupted by various kinds of noises i.e. babble noise, car noise, helicopter noise and random noise and processed through a noise-reduction algorithm. Subjective tests were conducted with normal hearing listeners by presenting the processed speech with controlled distortions. The method proposed by Kim et al uses the wiener filter. Here in this paper, we have used the parametric wiener filter. The experimental results clearly indicated improvement in intelligibility at 0dB, -5dB, +5dB and 10dB input signal-to-noise (SNR) values in short-time objective intelligibility (STOI) and Segmental signal-to-noise ratio (SSNR) objective measures.

Acoustical and Perceptual Comparison of Noise Reduction and Compression in Hearing Aids

2015 ◽  
Vol 58 (4) ◽  
pp. 1363-1376 ◽  
Author(s):  
Inge Brons ◽  
Rolph Houben ◽  
Wouter A. Dreschler
Keyword(s):  
Noise Reduction ◽  
Hearing Aids ◽  
Speech Intelligibility ◽  
Dynamic Range ◽  
Signal To Noise Ratio ◽  
Noise Levels ◽  
Dynamic Range Compression ◽  
Perceptual Comparison ◽  
Babble Noise ◽  
Processing Differences

Purpose Noise reduction and dynamic-range compression are generally applied together in hearing aids but may have opposite effects on amplification. This study evaluated the acoustical and perceptual effects of separate and combined processing of noise reduction and compression. Design Recordings of the output of 4 hearing aids for speech in babble noise at +4 dB signal-to-noise ratio were used in 3 experiments: (a) acoustical measurements to determine the influence of processing on speech and noise levels; (b) perceptual measurements to determine the detectability of processing differences for 16 listeners with hearing impairment; and (c) perceptual measurements to determine the effect of processing on speech intelligibility, noise annoyance, speech naturalness, and overall preference. Results Noise reduction and compression processing differed between hearing aids. The combined processing (noise reduction with compression) most strongly reduced noise and speech levels. The combined processing was detectably different between hearing aids, but compression processing alone was not. The combined processing did not influence speech intelligibility. Preference for combined processing was lower than previously observed for noise reduction without compression. Conclusions Differences in processing between hearing aids are perceptually salient. The effect of compression should be taken into account during the development and evaluation of hearing aid noise reduction.

Review of Recent Research on the Selection of Frequency-Gain Characteristics for Hearing Aids

1980 ◽  
Vol 89 (5_suppl) ◽  
pp. 79-83
Author(s):  
Richard Lippmann
Keyword(s):  
Hearing Aids ◽  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Hearing Aid ◽  
Linear Amplification ◽  
Percentage Points ◽  
Gain Characteristic ◽  
The Relationship ◽  
Fitting Hearing Aids ◽  
Selection Of

Following the Harvard master hearing aid study in 1947 there was little research on linear amplification. Recently, however, there have been a number of studies designed to determine the relationship between the frequency-gain characteristic of a hearing aid and speech intelligibility for persons with sensorineural hearing loss. These studies have demonstrated that a frequency-gain characteristic that rises at a rate of 6 dB/octave, as suggested by the Harvard study, is not optimal. They have also demonstrated that high-frequency emphasis of 10–40 dB above 500–1000 Hz is beneficial. Most importantly, they have demonstrated that hearing aids as they are presently being fit do not provide maximum speech intelligibility. Percent word correct scores obtained with the best frequency-gain characteristics tested in various studies have been found to be 9 to 19 percentage points higher than scores obtained with commercial aids owned by subjects. This increase in scores is equivalent to an increase in signal-to-noise ratio of 10 to 20 dB. This is a significant increase which could allow impaired listeners to communicate in many situations where they presently cannot. These results demonstrate the need for further research on linear amplification aimed at developing practical suggestions for fitting hearing aids.

scholarly journals Creating Clarity in Noisy Environments by Using Deep Learning in Hearing Aids

2021 ◽  
Vol 42 (03) ◽  
pp. 260-281
Author(s):  
Asger Heidemann Andersen ◽  
Sébastien Santurette ◽  
Michael Syskind Pedersen ◽  
Emina Alickovic ◽  
Lorenz Fiedler ◽  
...  
Keyword(s):  
Deep Learning ◽  
Hearing Aids ◽  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Noisy Environments ◽  
Listening Effort ◽  
Sound Processing ◽  
Listening Environments ◽  
The One ◽  
The Individual

AbstractHearing aids continue to acquire increasingly sophisticated sound-processing features beyond basic amplification. On the one hand, these have the potential to add user benefit and allow for personalization. On the other hand, if such features are to benefit according to their potential, they require clinicians to be acquainted with both the underlying technologies and the specific fitting handles made available by the individual hearing aid manufacturers. Ensuring benefit from hearing aids in typical daily listening environments requires that the hearing aids handle sounds that interfere with communication, generically referred to as “noise.” With this aim, considerable efforts from both academia and industry have led to increasingly advanced algorithms that handle noise, typically using the principles of directional processing and postfiltering. This article provides an overview of the techniques used for noise reduction in modern hearing aids. First, classical techniques are covered as they are used in modern hearing aids. The discussion then shifts to how deep learning, a subfield of artificial intelligence, provides a radically different way of solving the noise problem. Finally, the results of several experiments are used to showcase the benefits of recent algorithmic advances in terms of signal-to-noise ratio, speech intelligibility, selective attention, and listening effort.

Energy Based Dual-Microphone Electronic Speech Segregation

2013 ◽  
Vol 385-386 ◽  
pp. 1381-1384
Author(s):  
Yi Jiang ◽  
Hong Zhou ◽  
Yuan Yuan Zu ◽  
Xiao Chen
Keyword(s):  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Energy Difference ◽  
Binary Mask ◽  
Speech Signal Processing ◽  
Noise Sources ◽  
Speech Segregation ◽  
Time Result ◽  
Spatial Noise ◽  
Enhancement Algorithm

Speech segregation based on energy has a good performance on dual-microphone electronic speech signal processing. The implication of the binary mask to an auditory mixture has been shown to yield substantial improvements in signal-to-noise-ratio (SNR) and intelligibility. To evaluate the performance of a binary mask based dual microphone speech enhancement algorithm, various spatial noise sources and reverberation test conditions are used. Two compare dual microphone systems based on energy difference and machine learning are used at the same time. Result with SNR and speech intelligibility show that more robust performance can be achieved than the two compare systems.

Effect of Signal-to-Noise Ratio on Directional Microphone Benefit and Preference

2005 ◽  
Vol 16 (09) ◽  
pp. 662-676 ◽  
Author(s):  
Brian E. Walden ◽  
Rauna K. Surr ◽  
Kenneth W. Grant ◽  
W. Van Summers ◽  
Mary T. Cord ◽  
...  
Keyword(s):  
Hearing Aids ◽  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Hearing Aid ◽  
Directional Hearing ◽  
Signal To Noise ◽  
Directional Microphones ◽  
Directional Microphone ◽  
The Individual ◽  
Directional Hearing Aids

This study examined speech intelligibility and preferences for omnidirectional and directional microphone hearing aid processing across a range of signal-to-noise ratios (SNRs). A primary motivation for the study was to determine whether SNR might be used to represent distance between talker and listener in automatic directionality algorithms based on scene analysis. Participants were current hearing aid users who either had experience with omnidirectional microphone hearing aids only or with manually switchable omnidirectional/directional hearing aids. Using IEEE/Harvard sentences from a front loudspeaker and speech-shaped noise from three loudspeakers located behind and to the sides of the listener, the directional advantage (DA) was obtained at 11 SNRs ranging from -15 dB to +15 dB in 3 dB steps. Preferences for the two microphone modes at each of the 11 SNRs were also obtained using concatenated IEEE sentences presented in the speech-shaped noise. Results revealed that a DA was observed across a broad range of SNRs, although directional processing provided the greatest benefit within a narrower range of SNRs. Mean data suggested that microphone preferences were determined largely by the DA, such that the greater the benefit to speech intelligibility provided by the directional microphones, the more likely the listeners were to prefer that processing mode. However, inspection of the individual data revealed that highly predictive relationships did not exist for most individual participants. Few preferences for omnidirectional processing were observed. Overall, the results did not support the use of SNR to estimate the effects of distance between talker and listener in automatic directionality algorithms.

scholarly journals Perceptual Evaluation of Signal-to-Noise-Ratio-Aware Dynamic Range Compression in Hearing Aids

2020 ◽  
Vol 24 ◽  
pp. 233121652093053
Author(s):  
Borys Kowalewski ◽  
Torsten Dau ◽  
Tobias May
Keyword(s):  
Hearing Aids ◽  
Speech Intelligibility ◽  
Dynamic Range ◽  
Signal To Noise Ratio ◽  
Signal To Noise ◽  
Perceptual Evaluation ◽  
Dynamic Range Compression ◽  
Subjective Preference ◽  
Noise Ratio ◽  
Fast Acting

Dynamic range compression is a compensation strategy commonly used in modern hearing aids. Fast-acting systems respond relatively quickly to the fluctuations in the input level. This allows for more effective compression of the dynamic range of speech and hence enhanced the audibility of its low-intensity components. However, such processing also amplifies the background noise, distorts the modulation spectra of both the speech and the background, and can reduce the output signal-to-noise ratio (SNR). Recently, May et al. proposed a novel SNR-aware compression strategy, in which the compression speed is adapted depending on whether speech is present or absent. Fast-acting compression is applied to speech-dominated time–frequency (T-F) units, while noise-dominated T-F units are processed using slow-acting compression. It has been shown that this strategy provides a similar effective compression of the speech dynamic range as conventional fast-acting compression, while introducing fewer distortions of the modulation spectrum of the background and providing an improved output SNR. In this study, this SNR-aware compression strategy was compared with conventional fast- and slow-acting compression in terms of speech intelligibility and subjective preference in a group of 17 hearing-impaired listeners with varying degree of hearing loss. The results show a speech intelligibility benefit of the SNR-aware compression strategy over the conventional slow-acting system. Furthermore, the SNR-aware approach demonstrates an increased subjective preference compared with both conventional fast- and slow-acting systems.

scholarly journals An End-to-End Deep Learning Sound Coding Strategy for Cochlear Implants

2021 ◽  
Author(s):  
Tom Gajecki ◽  
Waldo Nogueira
Keyword(s):  
Speech Intelligibility ◽  
Signal To Noise Ratio ◽  
Wiener Filter ◽  
Sound Coding ◽  
Electric Hearing ◽  
Potential Benefits ◽  
Speech Performance ◽  
Coding Strategy ◽  
End To End ◽  
Enhancement Algorithm

Cochlear implant (CI) users struggle to understand speech in noisy conditions. In this work, we propose an end-to-end speech coding and denoising sound coding strategy that estimates the electrodograms from the raw audio captured by the microphone. We compared this approach to a classic Wiener filter and TasNet to assess its potential benefits in the context of electric hearing. The performance of the network is assessed by means of noise reduction performance (signal-to-noise-ratio improvement) and objective speech intelligibility measures. Furthermore, speech intelligibility was measured in 5 CI users to assess the potential benefits of each of the investigated algorithms. Results suggest that the speech performance of the tested group seemed to be equally good using our method compared to the front-end speech enhancement algorithm.

Sign in / Sign up

Export Citation Format

Share Document