Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
نویسندگان
چکیده
To improve speech recognition performance, acoustic feature transformation based on discriminant analysis has been widely used. For the same purpose, discriminative training of HMMs has also been used. In this letter we investigate the effectiveness of these two techniques and their combination. We also investigate the robustness of matched and mismatched noise conditions between training and evaluation environments. key words: speech recognition, feature extraction, discriminative training
منابع مشابه
دو روش تبدیل ویژگی مبتنی بر الگوریتم های ژنتیک برای کاهش خطای دسته بندی ماشین بردار پشتیبان
Discriminative methods are used for increasing pattern recognition and classification accuracy. These methods can be used as discriminant transformations applied to features or they can be used as discriminative learning algorithms for the classifiers. Usually, discriminative transformations criteria are different from the criteria of discriminant classifiers training or their error. In this ...
متن کاملSequential maximum mutual information linear discriminant analysis for speech recognition
Linear discriminant analysis (LDA) is a simple and effective feature transformation technique that aims to improve discriminability by maximizing the ratio of the between-class variance to the within-class variance. However, LDA does not explicitly consider the sequential discriminative criterion which consists in directly reducing the errors of a speech recognizer. This paper proposes a simple...
متن کاملFeature reduction of hyperspectral images: Discriminant analysis and the first principal component
When the number of training samples is limited, feature reduction plays an important role in classification of hyperspectral images. In this paper, we propose a supervised feature extraction method based on discriminant analysis (DA) which uses the first principal component (PC1) to weight the scatter matrices. The proposed method, called DA-PC1, copes with the small sample size problem and has...
متن کاملDiscriminant Training of Front-End and Acoustic Modeling Stages to Heterogeneous Acoustic Environments for Multi-stream Automatic Speech Recognition
Automatic Speech Recognition (ASR) still poses a problem to researchers. In particular, most ASR systems have not been able to fully handle adverse acoustic environments. Although a large number of modi cations have resulted in increased levels of performance robustness, ASR systems still fall short of human recognition ability in a large number of environments. A possible shortcoming of the ty...
متن کاملFeature transformations and combinations for improving ASR performance
In this work, linear and nonlinear feature transformations have been experimented in ASR front end. Unsupervised transformations were based on principal component analysis and independent component analysis. Discriminative transformations were based on linear discriminant analysis and multilayer perceptron networks. The acoustic models were trained using a subset of HUB5 training data and they ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- IEICE Transactions
دوره 93-D شماره
صفحات -
تاریخ انتشار 2010