Applied principles of clear 495 and Lombard speech for automated intelligibility enhancement in 496 noisy environments, Speech Communication, vol.48, issue.5, pp.549-558, 2006. ,
Near end listening enhancement: Speech intelligi-499 bility improvement in noisy environments, Proc. ICASSP, p.500 ,
, , pp.493-496, 2006.
Time and frequency de-502 pendent amplification for speech intelligibility enhancement in noisy en-503 vironments, Proc. Interspeech, vol.9, pp.557-560, 2008. ,
On optimal linear filtering of speech for 505 near-end listening enhancement, IEEE Signal Proc. Let, vol.20, issue.3, 2013. ,
, , p.508
Evaluating the intelligibility benefit of speech modifications in 509 known noise conditions, Speech Communication, vol.55, pp.572-585, 2013. ,
Speech-in-noise intelligibility im-511 provement based on spectral shaping and dynamic range compression, Proc. Interspeech, vol.512, pp.635-638, 2012. ,
Speaking clearly for the hard 514 of hearing. I: Intelligibility differences between clear and conversational 515 speech, J. Speech Hear. Res, vol.28, pp.96-103, 1985. ,
,
A note on the acoustic-phonetic characteristics 517 of inadvertently clear speech, Speech Communication, vol.14, issue.4, p.325, 1994. ,
Clear speech, p.520 ,
, The Handbook of Speech Perception, pp.521-207, 2005.
Effects of ambient noise on speaker intel-523 ligibility for words and phrases, J. Acoust. Soc. Am, vol.29, issue.12, pp.1320-1323, 1957. ,
Some 526 acoustic-phonetic correlates of speech produced in noise, p.527 ,
, , pp.1581-1584, 1985.
,
Effects of noise on speech production: Acoustic and perceptual 530 analyses, J. Acoust. Soc. Am, vol.84, issue.3, pp.917-928, 1988. ,
Information-preserving temporal reallocation of 532 speech in the presence of fluctuating maskers, Proc. Interspeech, p.533 ,
, , pp.3592-3596, 2013.
, , p.535
, Speaking clearly for the hard of hearing IV: Further studies of the role 536 of speaking rate, J. Speech Hear. Res, vol.39, issue.3, pp.494-509, 1996.
Effects of linear and nonlinear speech rate speech intelligibility in stationary and fluctuating maskers, p.539 ,
URL : https://hal.archives-ouvertes.fr/hal-01615914
, J. Acoust. Soc. Am, vol.141, pp.4126-4135, 2017.
On the dissociation of spectral and tem-541 poral cues to the voicing distinction in initial stop consonants, J. Acoust ,
, Soc. Am, vol.62, pp.436-448, 1977.
Speech 544 recognition with primarily temporal cues, Science, vol.270, issue.5234, p.303, 1995. ,
A study on the relationship between the 547 intelligibility and quality of algorithmically-modified speech for normal 548 hearing listeners, Journal of Otorhinolaryngology, Hearing and Balance, vol.549, p.5, 2017. ,
The effects of modified speech 551 styles on intelligibility for non-native listeners, Proc. Interspeech, pp.868-872, 2016. ,
The Sharvard Corpus: 554 A phonemically-balanced Spanish sentence resource for audiology ,
, J. Audiology, vol.53, pp.633-638, 2014.
,
,
IEEE Recommended practice for speech quality 559 measurements, IEEE Trans. Audio Acoust, pp.225-246, 1969. ,
,
, , p.561
Albayzín speech database: Design of the phonetic corpus, Eurospeech, pp.175-178, 1993. ,
Audio dynamic range compression for minimum perceived 564 distortion, IEEE Trans. on Audio and Electroacoustics, vol.17, issue.1, p.22, 1969. ,
A glimpsing model of speech perception in noise, J. Acoust ,
, Soc. Am, vol.119, issue.3, pp.1562-1573, 2006.
Cochlea-scaled entropy, not consonants, vowels, 569 or time, best predicts speech intelligibility, P. Natl. Acad. Sci. USA, vol.570, issue.27, pp.12387-12392, 2010. ,
Efficient non-uniform 572 time-scaling of speech with WSOLA, Int. Conf. on Speech and Com-573 puters (SPECOM), pp.163-166, 2005. ,
Haplo: Herramienta automática de procesamiento 575 linguístico ortofonético, Proc. Asociación Espaola de Linguística, p.576 ,
, , 2012.
A rationalized arcsine transform, Journal of Speech, p.578 ,
, Hearing Research, vol.28, pp.455-462, 1985.
Speech intelligibility is best 580 predicted by intensity, not cochlea-scaled entropy, J. Acoust. Soc. Am, vol.581, issue.3, pp.264-269, 2017. ,
,
Temporal factors in cochlea-583 scaled entropy and intensity-based intelligibility predictions, J. Acoust ,
, Soc. Am, vol.143, issue.6, 2018.
, Mon-586 treal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi, in: 587 Proc. Interspeech, pp.498-502, 2017.
, The Sounds of Spanish, p.589, 2005.
Cepstral 590 analysis based on the Glimpse proportion measure for improving the in-591 telligibility of HMM-based synthetic speech in noise, Proc. ICASSP, pp.3997-4000, 2012. ,
Automatic speech-to-background ratio se-594 lection to maintain speech intelligibility in broadcasts using an objective 595 intelligibility metric, Applied Sciences, vol.8, p.59, 2018. ,
A non-intrusive method for estimat-597 ,
, ing binaural speech intelligibility from noise-corrupted signals captured 598 by a pair of microphones, Speech Communication, vol.96, pp.116-128, 2017.
Glimpse-based metrics for predicting speech intel-600 ligibility in additive noise conditions, Proc. Interspeech, pp.601-2488, 2016. ,
Increasing speech intelligibility via spectral 603 shaping with frequency warping and dynamic range compression plus 604 transient enhancement, Proc. Interspeech, pp.3572-3576, 2013. ,