Automatic phrase segmentation and clustering in spontaneous speech

Beke, András and Szaszák, György and Váradi, Viola (2013) Automatic phrase segmentation and clustering in spontaneous speech. In: IEEE 4th International Conference on Cognitive Infocommunications, CogInfoCom 2013, December 2-5, 2013., 2013.12.02-2013.12.05., Budapest.

[img] Text
Restricted to Repository staff only

Download (922kB) | Request a copy


The aim of this research is to segment spontaneous speech using an unsupervised learning technique. We are espe- cially interested from a machine perception or detection point- of-view, and focus on revealing some structure of prosody in spontaneous speech. The BEA (BEszélt nyelvi Adatbázis: spoken language database) spontaneous speech database is used to de- velop a speech segmentation system. The spontaneous narratives are annotated manually for intonational phrases and further diveded for phonological phrases. Word level transcription is also provided. The corpus contains 398 intonational phrases (IP) and 751 phonological phrases (PP) from 8 speakers. To automatially detect them, a two-step segmentation method is applied. In the first step, the IPs are detected automatically based on speech energy, spectral centroid and a double- thresholding technique. In the second step, PPs are segmented within the IPs, based on F0, energy and Kullback-Leibler divergence combined with adaptive thresholding method. The results show that the proposed method can provide good and efficient framework for segmenting Hungarian spontaneous speech, with a performance close to read speech.

Item Type: Conference or Workshop Item (Lecture)
Subjects: P Language and Literature / nyelvészet és irodalom > P0 Philology. Linguistics / filológia, nyelvészet
P Language and Literature / nyelvészet és irodalom > PH Finno-Ugrian, Basque languages and literatures / finnugor és baszk nyelvek és irodalom > PH04 Hungarian language and literature / magyar nyelv és irodalom
Depositing User: Dávid Timár
Date Deposited: 22 Jan 2014 10:48
Last Modified: 28 Jan 2014 15:52

Actions (login required)

Edit Item Edit Item