First European Conference on Speech Communication and Technology

Paris, France
September 27-29, 1989

A Knowledge-Based Nasal Classifier for Use in Continuous Speech Recognition

B. Williams, S. M. Hiller, Fergus R. McInnes, Jonathan Dalby

Centre for Speech Technology Research, Edinburgh, UK

In a phoneme-based speaker-adaptive automatic recognition system for continuous English speech, a segmentation algorithm for nasals uses automatically derived thresholds on spectral energy measures. A Gaussian classifier using formant information, with duration, two compound measures, and a 'spectral contrast' measure, is applied to the hypothesised nasal segments, which are classified phonemically. Tests were carried out over the training data and over a second reading for each of two speakers. Results were comparable with earlier work as regards nasal/non-nasal hit rate, and better as regards the ratio of imposters to nasals. This method also goes further and achieves some success at the phonemic level.

Full Paper

Bibliographic reference.  Williams, B. / Hiller, S. M. / McInnes, Fergus R. / Dalby, Jonathan (1989): "A knowledge-based nasal classifier for use in continuous speech recognition", In EUROSPEECH-1989, 2252-2255.