Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin

Keywords

Computer science, End-to-end principle, Mandarin Chinese, Speedup, Speech recognition

References

• The Fisher Corpus: a Resource for the Next Generations of Speech-to-TextChristopher Cieri, David Miller, Kevin Walker — 2004
• On the importance of initialization and momentum in deep learningIlya Sutskever, James Martens, George E. Dahl — 2013
• An Empirical Exploration of Recurrent Network ArchitecturesRafał Józefowicz, Wojciech Zaremba, Ilya Sutskever — 2015
• Project Adam: Building an Efficient and Scalable Deep Learning Training SystemTrishul Chilimbi, Yutaka Suzue, Johnson Apacible — 2014
• Fast and accurate recurrent neural network acoustic models for speech recognitionHaşim Sak, Andrew Senior, Kanishka Rao — 2015
• Librispeech: An ASR corpus based on public domain audio booksVassil Panayotov, Guoguo Chen, Daniel Povey — 2015
• Connectionist Speech Recognition: A Hybrid ApproachHervé Bourlard, Nelson Morgan — 1993
• Learning to ExecuteWojciech Zaremba, Ilya Sutskever — 2014
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First ResultsJan Chorowski, Dzmitry Bahdanau, Kyunghyun Cho — 2014
• Convolutional, Long Short-Term Memory, fully connected Deep Neural NetworksTara N. Sainath, Oriol Vinyals, Andrew Senior — 2015
• cuDNN: Efficient Primitives for Deep LearningSharan Chetlur, Cliff Woolley, Philippe Vandermersch — 2014
• First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNsAwni Hannun, Andrew L. Maas, Daniel Jurafsky — 2014
• EESEN: End-to-end speech recognition using deep RNN models and WFST-based decodingYajie Miao, Mohammad Gowayyed, Florian Metze — 2015
• On the difficulty of training recurrent neural networksRazvan Pascanu, Tomáš Mikolov, Yoshua Bengio — 2012
• A Fast Data Collection and Augmentation Procedure for Object RecognitionBenjamin Sapp, Ashutosh Saxena, Andrew Y. Ng — 2008
• Listen, attend and spell: A neural network for large vocabulary conversational speech recognitionWilliam Chan, Navdeep Jaitly, Quoc V. Le — 2015
• Deep Speech: Scaling up end-to-end speech recognitionAwni Hannun, Carl Case, Jared Casper — 2014
• Acoustic Modeling Using Deep Belief NetworksAbdelrahman Mohamed, George E. Dahl, Geoffrey E. Hinton — 2012
• A fast storage allocatorKenneth C. Knowlton — 1965
• Joint training of convolutional and non-convolutional neural networksHagen Soltau, George Saon, Tara N. Sainath — 2014

Cited by

• A real-world test of artificial intelligence infiltration of a university examinations system: A “Turing Test” case studyИсламов Уткиржон Хосилжонович — 2024
• Deep Speech: Scaling up end-to-end speech recognitionAwni Hannun, Carl Case, Jared Casper — 2014
• Online Keyword Spotting with a Character-Level Recurrent Neural NetworkKyuyeon Hwang, Minjae Lee, Wonyong Sung — 2015
• Question Answering on Linked Data: Challenges and Future DirectionsSaeedeh Shekarpour, Kemele M. Endris, Ashwini Jaya Kumar — 2016
• Advances in Very Deep Convolutional Neural Networks for LVCSRTom Sercu, Vaibhava Goel — 2016
• Optimizing Performance of Recurrent Neural Networks on GPUsJeremy Appleyard, Tomáš Kočiský, Phil Blunsom — 2016
• Convolutional neural network based sensor fusion for forward looking ground penetrating radarRayn Sakaguchi, Miles Crosskey, David Chen — 2016
• Review of state-of-the-arts in artificial intelligence with application to AI safety problemVladimir Shakirov — 2016
• Variational hybridization and transformation for large inaccurate noisy-or networksYusheng Xie, Nan Du, Wei Fan — 2016
• Large Scale Distributed Hessian-Free Optimization for Deep Neural NetworkXi He, Dheevatsa Mudigere, Mikhail Smelyanskiy — 2016
• Boda-RTC: Productive generation of portable, efficient code for convolutional neural networks on mobile computing platformsMatthew W. Moskewicz, Forrest Iandola, Kurt Keutzer — 2016
• EvoNet: Evolutionary Synthesis of Deep Neural NetworksMohammad Javad Shafiee, Akshaya Mishra, Alexander Wong — 2016
• Recognition of radio signals with deep learning Neural NetworksGültekin Işık, Harun Artuner — 2016
• Concrete Problems in AI SafetyRicky Aliae — 2016
• Visual Analysis of Hidden State Dynamics in Recurrent Neural NetworksHendrik Strobelt, Sebastian Gehrmann, Bernd Huber — 2016
• Deep Learning with Darwin: Evolutionary Synthesis of Deep Neural NetworksMohammad Javad Shafiee, Akshaya Mishra, Alexander Wong — 2016
• Improved Recurrent Neural Networks for Session-based RecommendationsYong Tan, Xinxing Xu, Yong Liu — 2016
• Persistent RNNs: Stashing Recurrent Weights On-ChipGregory Diamos, Shubho Sengupta, Bryan Catanzaro — 2016
• Playing Atari Games with Deep Reinforcement Learning and Human Checkpoint ReplayIonel-Alexandru Hosu, Traian Rebedea — 2016
• Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learnerEmmanuel Dupoux — 2016

Related papers

• Another view on parallel speedupXian‐He Sun, Lionel M. Ni — 1990
• Shared virtual memory and generalized speedupXian‐He Sun, Jianping Zhu — 1994
• An Investigation of Enhancing CTC Model for Triggered Attention-based Streaming ASRHuaibo Zhao, Yosuke Higuchi, Tetsuji Ogawa — 2021
• Identifying the Challenges in Reducing Latency in GSN using PredictorsAndreas Benzing, Klaus Herrmann, Boris Koldehofe — 2009
• On the performance of IoT LPWAN technologies: the case of Sigfox, LoRaWAN and NB-IoTGiovanni Stanco, Alessio Botta, Flavio Frattini — 2022
• Online Control of Two-Step Random Access: A Step Towards uMTCShilun Song, Jun-Bae Seo, Hu Jin — 2023
• Analysis of Methods for Reducing Latency in Internet TVAndrei A. Klinovskii, Evgeniya I. Tumanova — 2021
• When they go high, we go low: low-latency live streaming in dash.js with LoLMay Lim, Mehmet N. Akcay, Abdelhak Bentaleb — 2020
• The Role of Bidirectional VLC Systems in Low-Latency 6G Vehicular Networks and Comparison with IEEE802.11p and LTE/5G C-V2XStefano Caputo, Lorenzo Mucchi, Muhammad Ali Umair — 2022