Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Empirical Evaluation and Combination of Punctuation Prediction Models Applied to Broadcast News
 
conference paper

Empirical Evaluation and Combination of Punctuation Prediction Models Applied to Broadcast News

Nanchen, Alexandre
•
Garner, Philip N.
2019
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing

Natural language processing techniques are dependent upon punctuation to work well. When their input is taken from speech recognition, it is necessary to reconstruct the punctuation; in particular sentence boundaries. We define a range of features from low level acoustics to those with high level lexical semantics, including deep and recurrent models; these in turn are representative of a broad range of approaches used by previous authors for punctuation prediction. We combine the features using a gradient boosting machine that is also capable of indicating the relative importance of each feature. In an empirical study, we show that features from different semantic levels are in fact complementary, that combining statistical and deep learning methods yields better prediction results, and that generalization across different speaking styles is difficult to achieve without adaptation. Our best model achieves an F-Measure of 82.8 on a challenging broadcast news dataset.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ICASSP.2019.8683796
Author(s)
Nanchen, Alexandre
•
Garner, Philip N.
Date Issued

2019

Published in
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Start page

7275

End page

7279

URL

Related documents

http://publications.idiap.ch/downloads/papers/2019/Nanchen_ICASSP_2019.pdf
Written at

EPFL

EPFL units
LIDIAP  
Event name
2019 IEEE International Conference on Acoustics, Speech, and Signal Processing
Available on Infoscience
February 25, 2019
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/154749
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés