Assessing Level-dependent Segmental Contribution to the Intelligibility of Speech Processed by Single-channel Noise-suppression Algorithms

Guan, Tian1; Chu, Guangxing1; Chen, Fei2; Yang, Feng3

10.21437/Interspeech.2016-43

2016

19909772

17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5

08-12-September-2016

122-125

San Francisco, CA, United states

C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS, BAIXAS, F-66390, FRANCE

ISCA-INT SPEECH COMMUNICATION ASSOC

Most existing single-channel noise-suppression algorithms cannot improve speech intelligibility for normal-hearing listeners; however, the underlying reason for this performance deficit is still unclear. Given that various speech segments contain different perceptual contributions, the present work assesses whether the intelligibility of noisy speech can be improved when selectively suppressing its noise at high-level (vowel-dominated) or middle-level (containing vowel consonant transitions) segments by existing single-channel noise-suppression algorithms. The speech signal was corrupted by speech-spectrum shaped noise and two-talker babble masker, and its noisy high- or middle-level segments were replaced by their noise-suppressed versions processed by four types of existing single-channel noise-suppression algorithms. Experimental results showed that performing segmental noise-suppression at high- or middle-level led to decreased intelligibility relative to noisy speech. This suggests that the lack of intelligibility improvement by existing noise suppression algorithms is also present at segmental level, which may account for the deficit traditionally observed at full-sentence level.

Noise suppression speech intelligibility segmental contribution

其他

英语

CPCI-S ; ISSHP ; CPCI-SSH ; EI

Shenzhen Municipal Science and Technology Innovation Committee[CYJ20140416141331555]

Acoustics ; Computer Science ; Engineering ; Linguistics

Acoustics ; Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Linguistics

WOS:000409394400026

20164603003603

Audio signal processing ; Audition ; Linguistics ; Speech communication ; Speech processing ; Spurious signal noise

Ergonomics and Human Factors Engineering:461.4 ; Information Theory and Signal Processing:716.1 ; Speech:751.5

Web of Science

1.Tsinghua Univ, Grad Sch Shenzhen, Biomed Engn Res Ctr, Shenzhen, Peoples R China
2.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen, Peoples R China
3.Shenzhen Childrens Hosp, Shenzhen, Peoples R China

Guan, Tian,Chu, Guangxing,Chen, Fei,et al. Assessing Level-dependent Segmental Contribution to the Intelligibility of Speech Processed by Single-channel Noise-suppression Algorithms[C]. C/O EMMANUELLE FOXONET, 4 RUE DES FAUVETTES, LIEU DIT LOUS TOURILS, BAIXAS, F-66390, FRANCE:ISCA-INT SPEECH COMMUNICATION ASSOC,2016:122-125.