Abstract:
Speaker independent speech recognition is
important for successful development of speech
recognizer in most real world applications. This paper
emphasizes speaker independent based on voice
conversion usinga pitch shifting method,Pitch
SynchronousOver Lap Add Algorithm (PSOLA).It
depends on detecting the pitch of the signal
(fundamental frequency) and changing it according to
the target pitch period using time stretching with Pitch
SynchronousOver Lap Add Algorithm (PSOLA), then
resampling the signal in order to have the same play
rate.The traditional voice activity detection algorithms
which track only energy cannot successfully identify
potential speech from input because the unwanted part
of the speech also has some energy and appears to be
speech. In the proposed system, VAD (Voice Activity
Detection) that calculates energy of high frequency
part separately as zero crossing rate to differentiate
noise from speech is used.
Description:
I am very gradeful to Dr. Khin Thidar Lynn and
Dr Mie Mie Thaw for fruitful discussion during the
preparation of this paper and also special thank to
Rector, Professors and colleges from University of
Computer Studies, Mandalay. I would like to thank all
my teachers, fiends and my husband who taught and
help me during the period of studies and thesis in
Computer University, Mandalay.