An improved spectral subtraction algorithm based on auditory masking in voice human-computer interaction

Author

Lu Ji xiang ; Wang Ping ; Yu Sui huai ; Lu Chang de

Author_Institution

Coll. of Mech. & Electr. Eng., Northwestern Polytech. Univ., Xi´an, China

fYear

2010

fDate

4-7 Aug. 2010

Firstpage

1938

Lastpage

1941

Abstract

As the primary research area of the Multimoda Human-computer Interaction, Voice Interaction mainly involves extraction and identification of the natural speech signal, where the former provides the reliable signal sources, which are analyzed by the latter. The speech enhancement technology is studied in this paper, aiming at the Voice Interactive. We propose an improved spectral subtraction (SS) algorithm based on auditory masking effect. The simulated results compared to the traditional SS show the effectiveness and superiority of the improved algorithm.

Keywords

human computer interaction; spectral analysis; speech enhancement; speech intelligibility; auditory masking effect; multimodal human computer interaction; signal source; spectral subtraction algorithm; speech enhancement technology; speech signal extraction; speech signal identification; voice human computer interaction; voice interaction; voice interactive; Human computer interaction; Masking threshold; Noise reduction; Signal to noise ratio; Speech; Speech enhancement; Auditory Masking; Multimodal Human-computer Interaction; Spectral Subtraction; Threshold; Voice Human-computer Interaction;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics and Automation (ICMA), 2010 International Conference on

Conference_Location

Xi´an

ISSN

2152-7431

Print_ISBN

978-1-4244-5140-1

Electronic_ISBN

2152-7431

Type

conf

DOI

10.1109/ICMA.2010.5589171

Filename

5589171