A novel approach to isolated word recognition
- 1 November 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Speech and Audio Processing
- Vol. 7 (6), 620-628
- https://doi.org/10.1109/89.799687
Abstract
A voice signal contains the psychological and physiological properties of the speaker as well as dialect differences, acoustical environment effects, and phase differences. For these reasons, the same word uttered by different speakers can be very different. In this paper, two theories are developed by considering two optimization criteria applied to both the training set and the test set. The first theory is well known and uses what is called Criterion 1 here and ends up with the average of all vectors belonging to the words in the training set. The second theory is a novel approach and uses what is called Criterion 2 here, and it is used to extract the common properties of all vectors belonging to the words in the training set. It is shown that Criterion 2 is superior to Criterion 1 when the training set is of concern. In Criterion 2, the individual differences are obtained by subtracting a reference vector from other vectors, and individual difference vectors are used to obtain orthogonal vector basis by using the Gram-Schmidt orthogonalization method. The common vector is obtained by subtracting projections of any vector of the training set on the orthogonal vectors from this same vector. It is proved that this common vector is unique for any word class in the training set and independent of the chosen reference vector. This common vector is used in isolated word recognition, and it is also shown that Criterion 2 is superior to Criterion 1 for the test set. From the theoretical and experimental study, it is seen that the recognition rates increase as the number of speakers in the training set increases. This means that the common vector obtained from Criterion 2 represents the common properties of a spoken word better than the common or average vector obtained from Criterion 1.Keywords
This publication has 15 references indexed in Scilit:
- Noise compensation for linear prediction via orthogonal transformationElectronics Letters, 1996
- A signal subspace approach for speech enhancementPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Successive orthogonalizations in the multistage CELP coderPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- Recognition of speaker-dependent continuous speech with KEALPublished by Elsevier BV ,1990
- Isolated and Connected Word Recognition—Theory and Selected ApplicationsPublished by Elsevier BV ,1990
- Speaker-Independent Recognition of Isolated Words Using Clustering TechniquesPublished by Elsevier BV ,1990
- An order-recursive algorithm for estimating pole-zero modelsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1987
- A unified approach to speaker verification with noisy speech inputsSpeech Communication, 1982
- Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentencesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1980
- On creating reference templates for speaker independent recognition of isolated wordsIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978