Comparing Classification Methods in Isolated Vowel Classification
| Autor: | Peter Tarabek, Andrea Tinajová, Martin Klimo, Ondrej Such, Santiago Barreda |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Ground truth
Computer science business.industry Posterior probability Feature extraction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION TIMIT Pattern recognition Multiclass classification Support vector machine ComputingMethodologies_PATTERNRECOGNITION Vowel Artificial intelligence business Classifier (UML) |
| Zdroj: | 2018 World Symposium on Digital Intelligence for Systems and Machines (DISA). |
| DOI: | 10.1109/disa.2018.8490601 |
| Popis: | Frame-wise processing of speech is the standard approach in automated speech recognition. The problem of assigning correct posterior classification probabilities to individual frames is quite subtle, because there is no ground truth available. It can be approached only indirectly, by considering a classification or recognition task requiring classification of a longer sequence of frames and inferring quality of posteriors from its success. In our paper we consider the problem of classification of isolated vowels in the TIMIT corpus with the ultimate goal of judging the quality of frame posteriors. We design a novel two level model for this purpose. At the first, spectral level, the posterior distribution is computed via multiclass classification based on the spectrum of each analysis frame. At the second, temporal level, temporal analysis of the first level posteriors is performed and serves as the input to a second level classifier. As an application of this model we compare multiple pairwise coupling classifiers. Experimental results indicate that currently preferred coupling methods based on the Bradley-Terry model give poorer quality posteriors than a simpler coupling method based on averaging. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|