Research on the Continuous Speech Feature Extraction Method for Different Noise

Wei Liu; Yi Ming Sun; Yan Xiu Liu

doi:10.4028/www.scientific.net/AMM.513-517.3589

Paper Titles

A Novel Three-Phase Three-Level Inverter with Asymmetrical Legs
p.3572

An Improved Physical Downlink Control Channel De-Resource Mapping Method in Long Term Evolution Systems
p.3577

LFSR Multi-Step Parallel Update Technology Utilizing Divider Circuit
p.3581

Design and Implementation of the Video Player Based on the Devkit8500D Hardware Platform
p.3585

Research on the Continuous Speech Feature Extraction Method for Different Noise
p.3589

Design of Perimeter Security Monitor System
p.3593

The Energy-Saving Control of Combined Multi-Unit for Building Automatic System in the Subway
p.3597

Forward Reflection Characteristics of Typical Smooth Building Walls and the Simulation Analysis
p.3601

Image Denoising with Contour-Based Directionlet Transform
p.3607

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 513-517Research on the Continuous Speech Feature...

Research on the Continuous Speech Feature Extraction Method for Different Noise

Abstract:

We propose a noise-robust continuous speech recognition (CSR) method for modeling and recognition. In recognition, we divide the continuous speech vectors to segments using proposed algorithm, then use DRA based on the segments for recognition. The proposed method efficiency is studied for noisy environment. DRA decreases the difference between the model and recognition continuous speech vectors. The new algorithm focuses on adjust the vectors by using different maxima in different segments. Segment-based DRA algorithm can make noisy speech feature vectors closer to the model. The average recognition rate has been improved at different noise and SNR conditions.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 513-517)

Pages:

3589-3592

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.513-517.3589

Citation:

Cite this paper

Online since:

February 2014

Authors:

Wei Liu*, Yi Ming Sun, Yan Xiu Liu

Keywords:

Continuous Speech Recognition, Noise Robust, Optimal Algorithm

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] X. Lu, S. Matsuda, M. Unoki, and S. Nakamura, Temporal modulation normalization for robust speech feature extraction and recognition, in Image and Signal Processing, CISP. International Congress, Oct. 2009, p.1–4.

DOI: 10.1109/cisp.2009.5303903

Google Scholar

[2] A. Acero, Acoustical and environmental robustness in automatic speech recognition, Ph.D. dissertation, Carnegie Mellon University, USA, (1990).

Google Scholar

[3] S. V. and J. W, Eds., Advanced Digital Signal Processing and Noise Reduction, Second Edition. WEST SUSSEX, PO19 1UD, ENDLAND: SONS, LTD, (2000).

Google Scholar

[4] N. Wada, N. Hayasaka, S. Yoshizawa, and Y. Miyanaga, Direct control on modulation spectrum for noise-robust speech recognition and spectral subtraction, in Circuits and Systems, ISCAS. Proceedings. IEEE International Symposium, 2006, p.2532–2536.

DOI: 10.1109/iscas.2006.1693139

Google Scholar

[5] W. Naoya and Y. Miyanaga, in International Symposium on Communications, Control and Signal Processing, ISCCSP. IEEE-EURASIP.

Google Scholar