Robust speech recognition in the presence of noise using medical data

Author

Athanaselis, Theologos ; Bakamidis, Stelios ; Giannopoulos, George ; Dologlou, Ioannis ; Fotinea, Evita

Author_Institution

Dept. of Speech Technol., Inst. for Language & Speech Process., Athens

fYear

2008

fDate

10-12 Sept. 2008

Firstpage

349

Lastpage

352

Abstract

This paper discusses the improvement of speech recognition in the presence of noise, when a parametric method of signal enhancement is used. The speech enhancement method improves the performance of voice control MRI. This is important since errors in the presence of noise are more frequent and tend to make applications, such as spoken dialogue systems, too cumbersome to use. The input signal is corrupted with MRI noise with varying signal-to-noise ratio. A non-linear spectral subtraction method (NSS) as well as an SVD based noise reduction techniques (ISE) are used in conjunction with the Speech Recognition system of the FAST project, to quantify the impact of speech enhancement.

Keywords

biomedical MRI; noise; singular value decomposition; speech enhancement; speech recognition; SVD; medical data; noise reduction techniques; nonlinear spectral subtraction method; parametric method; robust speech recognition; signal enhancement; speech enhancement; spoken dialogue systems; voice control MRI; Hidden Markov models; Magnetic resonance imaging; Natural languages; Noise reduction; Noise robustness; Signal processing; Signal to noise ratio; Speech enhancement; Speech processing; Speech recognition; Non-linear Spectral Subtraction; Speech Recognition system; truncated SVD Procedure; voice control MRI;

fLanguage

English

Publisher

ieee

Conference_Titel

Imaging Systems and Techniques, 2008. IST 2008. IEEE International Workshop on

Conference_Location

Crete

Print_ISBN

978-1-4244-2496-2

Electronic_ISBN

978-1-4244-2497-9

Type

conf

DOI

10.1109/IST.2008.4659999

Filename

4659999