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
SD-NeRF: Towards Lifelike Talking Head Animation via Spatially-adaptive Dual-driven NeRFs
TL;DR: This article proposes a fully end-to-end talking head animation method, which implicitly grasps the 3D structures by learning a conditional Neural Radiance Field (NeRF), and develops an audio-motion dual-driven NeRF model to take a step toward more lifelike talking head synthesis.
13
Large margin training for attention-based end-to-end speech recognition
Peidong Wang,Jia Cui,Chao Weng,Dong Yu +3 more
- 15 Sep 2019
TL;DR: A novel large marge training scheme for attention based end-to-end speech recognition that can achieve comparable performance to the minimum Bayes risk based minimum word error rate (MWER) criterion.
13
•Posted Content
Hardware-Guided Symbiotic Training for Compact, Accurate, yet Execution-Efficient LSTM
TL;DR: This work proposes a hardware-guided symbiotic training methodology for compact, accurate, yet execution-efficient inference models based on the observation that hardware may introduce substantial non-monotonic behavior, which it is called the latency hysteresis effect, when evaluating network size vs. inference latency.
13
Scaling Speech Enhancement in Unseen Environments with Noise Embeddings
Gil Keren,Jing Han,Björn Schuller +2 more
- 07 Sep 2018
TL;DR: This work addresses the problem of speech enhancement generalisation to unseen environments by performing two manipulations that reduce word error rates of a pretrained speech recognition system and improve enhancement quality according to a number of performance measures.
13
Artificial Intelligence on Job-Hopping Forecasting: AI on Job-Hopping
Nathan Kosylo,John Smith,Matthew Conover,Leong Chan,Hongtao Zhang,Hanfei Mei,Renzhi Cao +6 more
- 01 Aug 2018
TL;DR: A novel AI technology, Sequential Optimization of Naive Bayesian (SONB), which not only makes predictions, but also learns the underlying pattern and automatically estimates missing or unreliable feature values, which could also be used to estimate missing values in the input data.
13
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