Speaker Normalization and Model Selection of Combined Neural Networks
作者:
CESARE FURLANELLO,
DIEGO GIULIANI,
EDMONDO TRENTIN,
STEFANO MERLER,
期刊:
Connection Science
(Taylor Available online 1997)
卷期:
Volume 9,
issue 1
页码: 31-50
ISSN:0954-0091
年代: 1997
DOI:10.1080/095400997116720
出版商: Taylor & Francis Group
关键词: Keywords: Speech Recognition;Speaker Normalization;Combining Neural Networks;Bootstrap;Radial Basis Function;Multi-layer Perceptron
数据来源: Taylor
摘要:
This paper introduces bootstrap error estimation for automatic tuning of parameters in combined networks, applied as front-end preprocessors for a speech recognition system based on hidden Markov models. The method is evaluated on a large-vocabulary (10 000 words) continuous speech recognition task. Bootstrap estimates of minimum mean squared error allow selection of speaker normalization models improving recognition performance. The procedure allows a flexible strategy for dealing with inter-speaker variability without requiring an additional validation set. Recognition results are compared for linear, generalized radial basis functions and multi-layer perceptron network architectures.
点击下载:
PDF (302KB)
返 回