Back to Search
Start Over
Connected word recognition using a cascaded neuro-computational model.
- Source :
-
Connection Science . Dec2016, Vol. 28 Issue 4, p332-345. 14p. - Publication Year :
- 2016
-
Abstract
- We propose a novel framework for processing a continuous speech stream that contains a varying number of words, as well as non-speech periods. Speech samples are segmented into word-tokens and non-speech periods. An augmented version of an earlier-proposed, cascaded neuro-computational model is used for recognising individual words within the stream. Simulation studies using both a multi-speaker-dependent and speaker-independent digit string database show that the proposed method yields a recognition performance comparable to that obtained by a benchmark approach using hidden Markov models with embedded training. [ABSTRACT FROM PUBLISHER]
Details
- Language :
- English
- ISSN :
- 09540091
- Volume :
- 28
- Issue :
- 4
- Database :
- Academic Search Index
- Journal :
- Connection Science
- Publication Type :
- Academic Journal
- Accession number :
- 120129680
- Full Text :
- https://doi.org/10.1080/09540091.2016.1212814