Inlämning av Examensarbete / Submission of Thesis

Somayeh Hosseini MEE10:73, pp. 73. ING/School of Engineering, 2010.

The work

Författare / Author: Somayeh Hosseini
smhsn1981@googlemail.com
Titel / Title: Mapping Based Noise Reduction for Robust Speech Recognition
Abstrakt Abstract:

This project aims at proposing a new noise reduction technique for speech
recognition purposes. The proposed method called mapping based noise
reduction is performed on the feature vectors extracted from speech signals.
In this work the dimensionality reduction functionality of algorithms
such as Locally Linear Embedding and Principal Component Analysis is
exploited to map the corrupted speech feature vectors to their corresponding
noise-free feature vectors. The feature vectors are first mapped to the
lower dimensional space and in this space the nearest clean vector to each
noisy vector is found, mapped back again to the original space and given
as the input to the speech recognition system. This approach is examined
on the speech signals with artificially added wind noise with different signal
to noise ratio values and articulated by two different speakers.

Ämnesord / Subject: Signalbehandling - Signal Processing

Nyckelord / Keywords: speech recognition, noise reduction, dimensionality reduction, mapping

Publication info

Dokument id / Document id:
Program:/ Programme Magisterprogram i Elektroteknik / Master of Science in Electrical Engineering
Registreringsdatum / Date of registration: 09/05/2010
Uppsatstyp / Type of thesis: Masterarbete/Master's Thesis (120 credits)

Context

Handledare / Supervisor: Dr. Nedelko Grbic
nedelko.grbic@bth.se
Examinator / Examiner: Dr. Nedelko Grbic
Organisation / Organisation: Blekinge Institute of Technology
Institution / School: ING/School of Engineering

+46 455 38 50 00
I samarbete med / In co-operation with: Fraunhofer Institute for Intelligent Analysis and Information Systems IAIS, Germany
Anmärkningar / Comments:

0098-711-6411897

Files & Access

Bifogad uppsats fil(er) / Files attached: main.pdf (1480 kB, öppnas i nytt fönster)