Loading...
Please wait, while we are loading the content...
Similar Documents
Algorithms That Can Improve Speech Intelligibility
| Content Provider | Scilit |
|---|---|
| Author | Loizou, Philipos C. |
| Copyright Year | 2013 |
| Description | Book Name: Speech Enhancement |
| Abstract | Our knowledge surrounding the factors contributing to the lack of intelligibility benet with existing single-microphone noise-reduction algorithms is limited [1,4,5]. In most cases, we do not know how, and to what extent, a specic parameter of a noise-reduction algorithm needs to be modied so as to improve speech intelligibility. Clearly, one factor is related to the fact that we often are not able to estimate accurately the background noise spectrum, which is needed for the implementation of most single-microphone algorithms. While noise tracking or voice-activity detection algorithms have been found to perform well in steady background noise (e.g., car) environments (see Chapter 9), they generally do not perform well in nonstationary types of noise (e.g., multitalker babble). The second factor is that the majority of algorithms introduce distortions, which, in some cases, might be more damaging than the background noise itself [6]. For that reason, several algorithms have been proposed to minimize speech distortion while constraining the amount of noise distortion introduced to fall below a preset value [7,8] or below the auditory masking threshold [9]. Third, nonrelevant stochastic modulations arising from the nonlinear noise-speech interaction can contribute to reduction in speech intelligibility and, in some cases, more so than the deterministic modulation reduction [10]. The study in [5] assessed the effects of noise on speech intelligibility and has shown that the systematic algorithms had the most detrimental effects on speech intelligibility. The corruption of the ne structure and introduction of stochastic envelope uctuations associated with the inaccurate estimates of the noise intensity and nonlinear processing of the mixture envelopes further diminished speech intelligibility. It was argued that it was these stochastic effects that prevented spectral subtractive algorithms from improving speech perception in noise [5]. Next, we discuss some of the earlier factors in more detail and introduce another important factor that has been largely overlooked. |
| Related Links | https://content.taylorfrancis.com/books/download?dac=C2011-0-16639-5&isbn=9780429096181&doi=10.1201/b14529-21&format=pdf |
| Ending Page | 682 |
| Page Count | 48 |
| Starting Page | 635 |
| DOI | 10.1201/b14529-21 |
| Language | English |
| Publisher | Informa UK Limited |
| Publisher Date | 2013-02-25 |
| Access Restriction | Open |
| Subject Keyword | Book Name: Speech Enhancement Speech Intelligibility Algorithms That Can Improve Speech |
| Content Type | Text |
| Resource Type | Chapter |
