Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Computers  /  Vol: 9 Par: 2 (2020)  /  Artículo
ARTÍCULO
TITULO

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

Tessfu Geteye Fantaye    
Junqing Yu and Tulu Tilahun Hailu    

Resumen

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.

 Artículos similares

       
 
Xinjing Zhang and Qixun Zhou    
Human pose estimation, as the basis of advanced computer vision, has a wide application perspective. In existing studies, the high-capacity model based on the heatmap method can achieve accurate recognition results, but it encounters many difficulties wh... ver más
Revista: Applied Sciences

 
Priyank Kalgaonkar and Mohamed El-Sharkawy    
Object detection, a more advanced application of computer vision than image classification, utilizes deep neural networks to predict objects in an input image and determine their locations through bounding boxes. The field of artificial intelligence has ... ver más

 
Fawaz Khaled Alarfaj and Jawad Abbas Khan    
The online spread of fake news on various platforms has emerged as a significant concern, posing threats to public opinion, political stability, and the dissemination of reliable information. Researchers have turned to advanced technologies, including ma... ver más
Revista: Algorithms

 
Federico Ricci, Luca Petrucci, Francesco Mariani and Carlo Nazareno Grimaldi    
The control of internal combustion engines is becoming increasingly challenging to the customer?s requirements for growing performance and ever-stringent emission regulations. Therefore, significant computational efforts are required to manage the large ... ver más
Revista: Information

 
Petros Brimos, Areti Karamanou, Evangelos Kalampokis and Konstantinos Tarabanis    
Traffic forecasting has been an important area of research for several decades, with significant implications for urban traffic planning, management, and control. In recent years, deep-learning models, such as graph neural networks (GNN), have shown grea... ver más
Revista: Information