A Comparison of Acoustic Models Based on Neural Networks and Gaussian Mixtures

2009 ◽  
pp. 291-298 ◽  
Author(s):  
Tomáš Pavelka ◽  
Kamil Ekštein
Keyword(s):  
Neural Networks ◽  
Gaussian Mixtures ◽  
Acoustic Models

scholarly journals Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition

Computers ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 36
Author(s):  
Tessfu Geteye Fantaye ◽  
Junqing Yu ◽  
Tulu Tilahun Hailu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Speech Recognition ◽  
Convolutional Neural Network ◽  
Network Models ◽  
Neural Network Models ◽  
Feed Forward ◽  
Acoustic Models ◽  
Low Resource

Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recognition task. Of these networks, convolutional neural network (CNN) is an effective network for representing the local properties of the speech formants. However, CNN is not suitable for modeling the long-term context dependencies between speech signal frames. Recently, the recurrent neural networks (RNNs) have shown great abilities for modeling long-term context dependencies. However, the performance of RNNs is not good for low-resource speech recognition tasks, and is even worse than the conventional feed-forward neural networks. Moreover, these networks often overfit severely on the training corpus in the low-resource speech recognition tasks. This paper presents the results of our contributions to combine CNN and conventional RNN with gate, highway, and residual networks to reduce the above problems. The optimal neural network structures and training strategies for the proposed neural network models are explored. Experiments were conducted on the Amharic and Chaha datasets, as well as on the limited language packages (10-h) of the benchmark datasets released under the Intelligence Advanced Research Projects Activity (IARPA) Babel Program. The proposed neural network models achieve 0.1–42.79% relative performance improvements over their corresponding feed-forward DNN, CNN, bidirectional RNN (BRNN), or bidirectional gated recurrent unit (BGRU) baselines across six language collections. These approaches are promising candidates for developing better performance acoustic models for low-resource speech recognition tasks.

Classification of Condensing Heat Exchangers Performance Data by Gaussian Mixtures

2009 ◽  
Author(s):  
Arturo Pacheco-Vega ◽  
Gabriela Avila
Keyword(s):  
Experimental Data ◽  
Neural Networks ◽  
Heat Exchangers ◽  
Clustering Algorithm ◽  
Gaussian Mixture ◽  
Film Condensation ◽  
Gaussian Mixtures ◽  
Independent Evaluation ◽  
Condensing Heat Exchanger

We introduce a methodology to extract the regimes of operation from condensing heat exchanger data. The methodology uses a Gaussian mixture clustering algorithm to determine the number of groups from the data, and a maximum likelihood decision rule to classify the data into these clusters. In order to assess the accuracy of clustering technique, experimental data from the literature visually classified as dry-surface, dropwise condensation, and film condensation, are used in the analysis. Though there is a discrepancy between the clustering classification and the visual one, an independent evaluation using artificial neural networks (ANNs) shows that the clustering methodology is able to both find the different regimes of operation and classify the data corresponding to each regime.

I-Vectors and Structured Neural Networks for Rapid Adaptation of Acoustic Models

2017 ◽  
Vol 25 (4) ◽  
pp. 818-828 ◽  
Author(s):  
Penny Karanasou ◽  
Chunyang Wu ◽  
Mark Gales ◽  
Philip C. Woodland
Keyword(s):  
Neural Networks ◽  
Rapid Adaptation ◽  
Acoustic Models
Sign in / Sign up

Export Citation Format

Share Document