Open AccessPosted Content
Deep Speech: Scaling up end-to-end speech recognition
Awni Hannun,Carl Case,Jared Casper,Bryan Catanzaro,Greg Diamos,Erich Elsen,Ryan Prenger,Sanjeev Satheesh,Shubho Sengupta,Adam Coates,Andrew Y. Ng +10 more
TL;DR: Deep Speech, a state-of-the-art speech recognition system developed using end-to-end deep learning, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set.
read more
Abstract: We present a state-of-the-art speech recognition system developed using end-to-end deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need hand-designed components to model background noise, reverberation, or speaker variation, but instead directly learns a function that is robust to such effects. We do not need a phoneme dictionary, nor even the concept of a "phoneme." Key to our approach is a well-optimized RNN training system that uses multiple GPUs, as well as a set of novel data synthesis techniques that allow us to efficiently obtain a large amount of varied data for training. Our system, called Deep Speech, outperforms previously published results on the widely studied Switchboard Hub5'00, achieving 16.0% error on the full test set. Deep Speech also handles challenging noisy environments better than widely used, state-of-the-art commercial speech systems.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Simplified Self-Attention for Transformer-Based end-to-end Speech Recognition
Haoneng Luo,Shiliang Zhang,Ming Lei,Lei Xie +3 more
- 19 Jan 2021
TL;DR: This article proposed a simplified self-attention layer which employs FSMN memory blocks instead of projection layers to form query and key vectors for transformer-based end-to-end speech recognition.
31
•Posted Content
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation
TL;DR: This paper examines the influence of three data augmentation methods on the performance of two S2S model architectures – a time perturbation in the frequency domain and sub-sequence sampling and their own development.
30
•Posted Content
StochasticNet: Forming Deep Neural Networks via Stochastic Connectivity
TL;DR: Experimental results show that a StochasticNet using less than half the number of neural connections as a conventional deep neural network achieves comparable accuracy and reduces overfitting on the CIFAR-10, MNIST, and SVHN data sets.
30
•Proceedings Article
Audio Visual Attribute Discovery for Fine-Grained Object Recognition.
Hua Zhang,Xiaochun Cao,Rui Wang +2 more
- 27 Apr 2018
TL;DR: This paper introduces a novel feature named audio visual attributes via discovering the correlations between the visual and audio representations and proposes a unified framework for training with video-level category label which can be implemented end-to-end in the step of inference.
30
Says Who? Deep Learning Models for Joint Speech Recognition, Segmentation and Diarization
Amitrajit Sarkar,Surajit Dasgupta,Sudip Kumar Naskar,Sivaji Bandyopadhyay +3 more
- 15 Apr 2018
TL;DR: This work proposes a powerful adaptation of the state-of-the-art Speech Recognition models for speech segmentation and diarization, using the Libri Speech corpus and obtained comparable results with respect to state of theart in both tasks.
30
References
•Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
Alex Krizhevsky,Ilya Sutskever,Geoffrey E. Hinton +2 more
- 03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
- 07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
•Proceedings Article
Sequence to Sequence Learning with Neural Networks
Ilya Sutskever,Oriol Vinyals,Quoc V. Le +2 more
- 08 Dec 2014
TL;DR: The authors used a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
•Proceedings Article
Rectified Linear Units Improve Restricted Boltzmann Machines
Vinod Nair,Geoffrey E. Hinton +1 more
- 21 Jun 2010
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Backpropagation applied to handwritten zip code recognition
Yann LeCun,Bernhard E. Boser,John S. Denker,D. Henderson,Richard Howard,W. Hubbard,Lawrence D. Jackel +6 more
TL;DR: This paper demonstrates how constraints from the task domain can be integrated into a backpropagation network through the architecture of the network, successfully applied to the recognition of handwritten zip code digits provided by the U.S. Postal Service.
12.5K
Related Papers (5)
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014