Speech Prosody 2012

Shanghai, China
May 22-25, 2012

Significance of Glottal Activity Detection for Duration Modification

D. Govind (1), S. R. Mahadeva Prasanna (1), B. Yegnanarayana (2)

(1) Electro-Medical and Speech Technology Laboratory, Indian Institute of Technology Guwahati, Assam, India
(2) International Institute of Information Technology Hyderabad, A.P, India

The objective of the present work is to demonstrate the signif- icance of glottal activity (GA) detection for duration modifica- tion. The accurate GA regions of the speech are derived using zero frequency filtered signal (ZFFS) obtained from zero fre- quency filtering (ZFF) of speech. The duration of the speech is modified according to the desired scaling factors from the epochs estimated using ZFF method. Initially, the duration modified speech is synthesized using the existing epoch based fast duration modification method by processing all the epochs present in the original speech. The final duration modified speech is derived by retaining the duration modified speech samples of the GA regions and original speech samples in the non-GA regions. The improved perceptual quality of the dura- tion modified speech is confirmed from the waveforms, spectro- grams and subjective evaluations.

Index Terms: Duration modification, epochs, zero frequency filtering, glottal activity detection

Full Paper

Bibliographic reference.  Govind, D. / Prasanna, S. R. Mahadeva / Yegnanarayana, B. (2012): "Significance of glottal activity detection for duration modification", In SP-2012, 470-473.