DocumentCode
591474
Title
Occurrence and duration modeling of sentence medial pause for Bangla text reading at different speech rate
Author
Acharya, Sanjeev ; Das Mandal, Shyamal Kumar
Author_Institution
Indian Inst. of Technol. Kharagpur, Kharagpur, India
fYear
2012
fDate
9-12 Dec. 2012
Firstpage
62
Lastpage
67
Abstract
One of the key issues for speech prosody is control of pause occurrence and duration. Occurrence of pause is unconditional at sentence boundaries with high probability at major syntactic boundaries such as clause boundaries and more or less arbitrarily at minor syntactic boundaries for text-readout speech. In this paper a detailed investigation is conducted for sentence-medial pauses for readout speech of Bangla for different speech rates. Based on the analysis, linear models with variables of syntactic unit length in terms of number of syllable and distance to directly modifying word are constructed for pause occurrence and duration for different speech rates. The models are evaluated using the test data which are not included in the analyzed data in different speech rates. The results show that the proposed models can predict occurrence probability correctly on average 82% cases for all speech rate, and pause duration within ±100 ms for 79% of the cases.
Keywords
natural language processing; probability; speech synthesis; Bangla readout speech; Bangla text reading; clause boundary; duration control; occurrence probability; pause occurrence control; sentence boundary; sentence medial pause; sentence-medial pause; speech prosody; speech rate; syntactic unit length variable; text-readout speech; Data models; Equations; Materials; Mathematical model; Predictive models; Speech; Syntactics; Text-to-Speech Synthesis (TTS); different speech rate; duration of pause; occurrence probability of pause; sentence medial pause;
fLanguage
English
Publisher
ieee
Conference_Titel
Speech Database and Assessments (Oriental COCOSDA), 2012 International Conference on
Conference_Location
Macau
Print_ISBN
978-1-4673-2811-1
Electronic_ISBN
978-1-4673-2812-8
Type
conf
DOI
10.1109/ICSDA.2012.6422479
Filename
6422479
Link To Document