Header menu link for other important links
X
Automatic segmentation and labeling of continuous speech without bootstrapping
, N. R. Hemalatha, T. Nagarajan
Published in European Signal Processing Conference, EUSIPCO
2015
Volume: 06-10-September-2004
   
Pages: 561 - 564
Abstract
In this paper, a novel approach is proposed for automatically segmenting and transcribing continuous speech signal without the use of manually segmented and labeled speech corpora. The continuous speech signal is first segmented into syllable-like units by considering short-term energy as a magnitude spectrum of some arbitrary signal. Similar syllable segments are then grouped together using an unsupervised and incremental clustering technique. Separate models are generated for each cluster of syllable segments. At this stage, labels are assigned for each group of syllable segments manually. The syllable models of these clusters are then used to transcribe/recognize the continuous speech signal of closed-set speakers as well open-set speakers. As a syllable recognizer, our initial results on Indian television news bulletins of the the languages Tamil and Telugu shows that the performance is 43.3% and 32.9% respectively. © 2004 EUSIPCO.
About the journal
JournalEuropean Signal Processing Conference
PublisherEuropean Signal Processing Conference, EUSIPCO
ISSN22195491
Open AccessNo
Concepts (12)
  •  related image
    Signal processing
  •  related image
    Speech
  •  related image
    Transcription
  •  related image
    ARBITRARY SIGNALS
  •  related image
    Automatic segmentations
  •  related image
    Closed set
  •  related image
    CONTINUOUS SPEECH
  •  related image
    INCREMENTAL CLUSTERING
  •  related image
    Magnitude spectrum
  •  related image
    SHORT TERM ENERGIES
  •  related image
    SPEECH CORPORA
  •  related image
    Speech communication