×
The speech recognition systems based on deep neural networks have obtained the state-of-the-art performance on various speech recognition tasks. These systems ...
We compare the proposed multi-scale features and traditional features at various number of configurations. Experimental results show that the proposed model ...
Deep learning has brought a breakthrough to the performance of speech recognition. The speech recognition systems based on deep neural networks have ...
Bibliographic details on Multi-scale feature based convolutional neural networks for large vocabulary speech recognition.
People also ask
Feb 13, 2018 · We proposed an approach to build a robust automatic speech recognizer using deep convolutional neural networks (CNNs). Deep CNNs have achieved a ...
A robust automatic speech recognizer using deep convolutional neural networks (CNNs) and a Recognizer Output Voting Error Reduction (ROVER) algorithm for ...
Oct 22, 2024 · We used a convolutional neural network (CNN), which is well suited for identifying spoken words from 2D features in audio spectrograms [42] .
Jul 10, 2018 · In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between ...
Missing: vocabulary | Show results with:vocabulary
Abstract. We present our work on constructing multi-scale deep convolu- tional neural networks for automatic speech recognition. Sev-.
We investigate which aspects of DNN acoustic model design are most important for speech recognition system performance, focusing on feed-forward networks.