English»Natural Language Processing and Computational Linguistics»Speech Recognition | searchivarius.org
log in | contact | about 

Acoustic modeling

End-to-end neural network systems



A Statistical Model for Word Discovery in Transcribed Speech  Anand Venkataraman
Exploring Neural Transducers for End-to-End Speech Recognition.  Eric Battenberg, Jitong Chen, Rewon Child, Adam Coates, Yashesh Gaur, Yi Li, Hairong Liu, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu
First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs  Andrew L. Maas, Awni Y. Hannun, Daniel Jurafsky, Andrew Y. Ng
Lexicon-Free Conversational Speech Recognition with Neural Networks  Andrew L. Maas , Ziang Xie , Dan Jurafsky, Andrew Y. Ng
Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition  Haşim Sak, Andrew Senior, Françoise Beaufays
Purely sequence-trained neural networks for ASR based on lattice-free MMI  Daniel Povey, Vijayaditya Peddinti, Daniel Galvez, Pegah Ghahremani, Vimal Manohar, Xingyu Na, Yiming Wang, Sanjeev Khudanpur:
Sentence boundary detection in broadcast speech transcripts  Yoshihiko Gotoh, Steve Renals
Speech recognition with deep recurrent neural networks  A Graves, A Mohamed, G Hinton