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
Convolutional Neural Networks for Raw Speech Recognition
Vishal Passricha,Rajesh Kumar Aggarwal +1 more
- 12 Dec 2018
TL;DR: CNN-based acoustic model for raw speech signal is discussed, which establishes the relation between rawspeech signal and phones in a data-driven manner and performs better than traditional cepstral fea- ture-based systems.
Real-time price discovery via verbal communication: Method and application to Fedspeak
TL;DR: This article studied the price discovery process on FOMC days and found that price movements around the post-meeting statement release are strong predictors of price movement around the subsequent press conference.
32
Speech Dereverberation With Context-Aware Recurrent Neural Networks
João Felipe Santos,Tiago H. Falk +1 more
TL;DR: The proposed model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart outperforms a recently proposed model that uses different context information depending on the reverberation time, without requiring any sort of additional input.
32
Multimodal Large Language Models in Healthcare: Applications, Challenges, and Future Outlook (Preprint)
Rawan AlSaad,Alaa Abd‐Alrazaq,Sabri Boughorbel,Arfan Ahmed,Max-Antoine Renault,Rafat Damseh,Javaid I. Sheikh +6 more
TL;DR: This preprint explores the applications, challenges, and future outlook of multimodal large language models in healthcare, highlighting the need for integrating diverse data modalities to inform clinical decisions and drive a paradigm shift toward multimodal data-driven medical practice.
32
•Proceedings Article
Are Neural Rankers still Outperformed by Gradient Boosted Decision Trees
Zhen Qin,Le Yan,Honglei Zhuang,Yi Tay,Rama Kumar Pasumarthi,Xuanhui Wang,Michael Bendersky,Marc Najork +7 more
- 03 May 2021
TL;DR: This paper showed that neural LTR models are inferior to the best publicly available Gradient Boosted Decision Trees (GBDT) in terms of their reported ranking accuracy on benchmark datasets and proposed a unified framework comprising of counter strategies to ameliorate the existing weaknesses of neural models.
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