2008 International Conference on Signal Processing, Communications and Networking 2008
DOI: 10.1109/icscn.2008.4447162
|View full text |Cite
|
Sign up to set email alerts
|

Automated Detection of Transition Segments for Intensity and Time-Scale Modification for Speech Intelligibility Enhancement

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2009
2009
2021
2021

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 19 publications
0
3
0
Order By: Relevance
“…Although they obtained intelligibility improvements of 7% at -10 dB SNR, they only evaluated their method at moderate noise levels (-10 and 0 dB) where intelligibility is not severely affected by background noise. Jayan et al described a real-time algorithm that improves speech intelligibility by increasing the duration and intensity of transient speech [9]. However, they presented psycho-acoustic testing results for only one subject.…”
Section: Introductionmentioning
confidence: 93%
“…Although they obtained intelligibility improvements of 7% at -10 dB SNR, they only evaluated their method at moderate noise levels (-10 and 0 dB) where intelligibility is not severely affected by background noise. Jayan et al described a real-time algorithm that improves speech intelligibility by increasing the duration and intensity of transient speech [9]. However, they presented psycho-acoustic testing results for only one subject.…”
Section: Introductionmentioning
confidence: 93%
“…They found increases of up to 15% in recognition rates for words presented by a range of speakers in white noise. Real-time methods for improving intelligibility by emphasizing transient segments of speech have been described but these methods had limited ability to improve intelligibility [10] [11]. Techniques to emphasize transients have also been proposed for coding in cochlear implants and shown to improve recognition of speech cues [12] [13].…”
Section: Introductionmentioning
confidence: 99%
“…Psycho-acoustic tests showed an intelligibility enhancement of speech. Jayan et al (2008) achieved to detect automatically transient parts of speech and perform on these regions intensity and time-scale modifications. Intelligibility tests reported intelligibility enhancement of non-sense syllables on high noise levels (-9 and -12dB SNR).…”
Section: Consonant Propertiesmentioning
confidence: 99%