DocumentCode :
3049192
Title :
Comparison between DFT-, FCT-, Wavelet-, and Lattice Filter-Based Noise Reduction for ASR
Author :
Rank, Erhard ; Al-Khayat, Amar ; Tuan Van Pham ; Saffer, Zsolt ; Stark, Michael
Author_Institution :
SPSC-Lab., Graz Univ. of Technol., Graz, Austria
fYear :
2010
fDate :
1-4 Nov. 2010
Firstpage :
1
Lastpage :
4
Abstract :
We investigate noise reduction (NR) for speech signals for automatic speech recognition (ASR). We compare four transform based noise reduction algorithms according to their influence on ASR performance. These include frequency domain based algorithms using the discrete Fourier transform (DFT), the fast chirp transform (FCT), and the discrete wavelet transform (DWT), as well as a lattice filter based algorithm. Ten different types of noise with different characteristics are used, covering a broad range from almost stationary to highly non-stationary conditions. For single speakers, on average over the different noise types, a reduction of WER of up to 5.5% is possible. The DFT, DWT, and the lattice filter based algorithms lead to an improvement up to 2% relative WER on average over all speakers and noise types. Moreover, the application of the lattice filter based algorithm to recognition of noise-free data does not cause any degradation in the recognition performance. Hence the lattice filter based NR algorithm has a potential application in the real-life ASR systems.
Keywords :
discrete Fourier transforms; discrete wavelet transforms; frequency-domain analysis; interference suppression; lattice filters; speech recognition; ASR performance; DFT; DWT; FCT; WER; automatic speech recognition; discrete Fourier transform; discrete wavelet transform; fast chirp transform; frequency domain based algorithms; lattice filter based algorithm; lattice filter-based noise reduction; noise reduction algorithms; noise-free data; recognition performance; speech signals; Discrete Fourier transforms; Discrete wavelet transforms; Noise; Noise reduction; Signal processing algorithms; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computing and Communication Technologies, Research, Innovation, and Vision for the Future (RIVF), 2010 IEEE RIVF International Conference on
Conference_Location :
Hanoi
Print_ISBN :
978-1-4244-8074-6
Type :
conf
DOI :
10.1109/RIVF.2010.5633588
Filename :
5633588
Link To Document :
بازگشت