Index of /~bryan/papers2/ai/speech-recognition

[ICO]NameLast modifiedSizeDescription
[PARENTDIR]Parent Directory  -  
[ ]Speech recognition system robustness to microphone variations - 1995.pdf1999-05-25 13:10 713K 
[ ]Landmark detection for distinctive feature‐based speech recognition - 1996.pdf2005-09-20 17:38 280K 
[ ]Why are spectrograms hard to read?.pdf2006-05-17 12:17 720K 
[ ]Recent progress in the MIT spoken lecture processing project - 2007.pdf2007-09-21 07:34 189K 
[ ]An overview of speech recognition and synthesis.pdf2010-08-12 04:26 2.7M 
[ ]Intrinsic spectral analysis for zero and high resource speech recognition.pdf2012-07-03 06:04 95K 
[ ]Improving searchability of automatically transcribed lectures through dynamic language modelling - dissertation - wikipedia - 2012.pdf2012-12-11 00:36 2.7M 
[ ]Leveraging large amounts of loosely transcribed corporate videos for acoustic model training - 2011.pdf2013-01-18 15:43 92K 
[ ]Intrinsic spectral analysis - 2013.pdf2013-03-20 12:36 1.9M 
[ ]The speech recognition and machine translation system of IOIT for IWSLT 2013 - ted talks.pdf2013-12-19 05:16 240K 
[ ]Kaldi+PDNN: Building DNN-based ASR systems with kaldi and PDNN - 2014.pdf2014-01-27 17:18 157K 
[ ]A bottom-up modular search approach to large vocabulary continuous speech recognition - 2013.pdf2014-02-09 19:57 1.3M 
[ ]Speech recognition using Kaldi - 2014.pdf2014-06-12 08:38 1.6M 
[ ]A lecture transcription system combining neural network acoustic and language models - slides - 2013.pdf2014-10-20 05:44 2.2M 
[ ]End-to-end continuous speech recognition using attention-based recurrent NN: first results - 2014.pdf2014-12-04 17:30 425K 
[ ]Semi-supervised training for lecture transcription in resource-scarce environments - 2014.pdf2014-12-19 00:28 95K 
[ ]Deep speech: Scaling up end-to-end speech recognition - Baidu - 2014.pdf2014-12-22 17:33 514K 
[ ]Librispeech: an ASR corpus based on public domain audiobooks - 2015.pdf2015-01-27 23:21 95K 
[ ]Automatic speech recognition and machine translation system for MIT english lectures using MIT and TED corpus - 2013.pdf2015-02-23 05:37 651K 
[ ]Using keyword spotting to help humans correct captioning faster - 2015.pdf2015-03-28 08:25 432K 
[ ]Introducing CURRENNT: The Munich open-source CUDA recurrent neural network toolkit - 2015.pdf2015-04-12 08:58 286K 
[ ]The IBM 2015 English conversational telephone speech recognition system - 2015.pdf2015-05-24 17:34 180K 
[ ]Fast and accurate recurrent neural network acoustic models for speech recognition - 2015.pdf2015-07-26 17:23 322K 
[ ]Knowledge-based approach to consonant recognition.pdf2015-07-28 19:16 44K 
[ ]Scalable distributed DNN training using commodity GPU cloud computing - 2015.pdf2015-09-20 15:32 1.1M 
[ ]Effective approaches to attention-based neural machine translation - 2015.pdf2015-09-21 17:33 244K 
[ ]Character-based neural machine translation - 2015.pdf2015-11-16 18:09 370K 
[ ]Deep speech 2: End-to-end speech recognition in English and Mandarin - 2015.pdf2015-12-08 17:28 857K 
[ ]pyAudioAnalysis: An open-source python library for audio signal analysis - 2015.pdf2015-12-11 10:32 3.2M 
[ ]The IOIT english ASR system for IWSLT 2015 - ted talks.pdf2015-12-19 04:46 82K 
[ ]Environmental noise embeddings for robust speech recognition - 2016.pdf2016-01-11 17:41 1.1M 
[ ]Character-level incremental speech recognition with recurrent neural networks - 2016.pdf2016-01-28 18:15 125K 
[ ]An empirical exploration of CTC acoustic models - 2016.pdf2016-01-29 13:38 148K 
[ ]The effects of automatic speech recognition quality on human transcription latency - 2015.pdf2016-03-04 07:34 1.3M 
[ ]Optimizing performance of recurrent neural networks on GPUs - 2016.pdf2016-04-07 17:37 93K 
[ ]Integrated adaptation with multi-factor joint-learning for far-field speech recognition - 2016.pdf2016-04-11 12:25 304K 
[ ]Robust coherence-based spectral enhancement for speech recognition in adverse real-world environments - 2016.pdf2016-04-13 17:55 327K 
[ ]Convolutional, long short-term memory, fully connected deep neural networks - Google - 2015.pdf2016-04-20 20:17 172K 
[ ]Deep neural networks for acoustic modeling in speech recognition - 2012.pdf2016-04-20 20:17 267K 
[ ]Listen, attend and spell - Google - RNNs without CTC not CLDNN-HMM - 2015.pdf2016-04-20 20:17 2.2M 
[ ]Towards lecture transcription in resource-scarce environments - 2012.pdf2016-04-28 14:24 72K 
[ ]Can neural machine translation do simultaneous translation? - 2016.pdf2016-06-07 17:18 642K 
[ ]Neural machine translation of rare words with subword units - 2015.pdf2016-06-12 22:31 189K 
[ ]Calibration of phone likelihoods in automatic speech recognition - 2016.pdf2016-06-14 17:38 887K 
[ ]Multi-task recurrent model for speech and speaker recognition - 2016.pdf2016-06-14 17:50 333K 
[ ]Segmental recurrent neural networks for end-to-end speech recognition - 2016.pdf2016-06-20 18:18 413K 
[ ]A character-level decoder without explicit segmentation for neural machine translation - 2016.pdf2016-06-21 17:05 671K 
[ ]A segmental framework for fully-unsupervised large-vocabulary speech recognition - 2016.pdf2016-06-22 17:27 1.0M 
[ ]A comprehensive study of deep bidirectional LSTM RNNs for acoustic modeling in speech recognition - 2016.pdf2016-06-24 15:09 218K 
[ ]Directly comparing the listening strategies of humans and machines - 2016.pdf2016-06-27 13:41 6.4M 
[ ]A 6 mW, 5,000-word real-time speech recognizer using WFST models - 2015.pdf2016-07-26 17:12 2.8M 
[ ]Lightly supervised acoustic model training for imprecisely and asynchronously transcribed speech - 2013.pdf2016-07-26 17:19 433K 
[ ]End-to-end deep neural network for automatic speech recognition - 2015.pdf2016-08-06 19:03 7.7K 
[ ]Factored recurrent neural network language model in TED lecture transcription - 2012.pdf2016-08-07 19:15 658K 
[ ]Language model adaptation for academic lectures using character recognition result of presentation slides - 2015.pdf2016-08-07 20:06 9.0K 
[ ]Recurrent support vector machines for speech recognition - 2016.pdf2016-08-08 10:50 110K 
[ ]The Microsoft 2016 conversational speech recognition system - 2016.pdf2016-09-12 17:58 226K 
[ ]Advances in all-neural speech recognition - 2016.pdf2016-09-20 17:37 96K 
[ ]ba_dls_speech2016.pdf2016-09-25 16:23 18M 
[ ]Sonic shapes: visualizing vocal expression - 2013.pdf2016-10-01 16:55 780K 
[ ]Formalizing knowledge used in spectrogram reading: Acoustic and perceptual evidence from stops - 1988.pdf2016-10-16 07:06 14M 
[ ]Achieving human parity in conversational speech recognition - Microsoft - 2016.pdf2016-10-17 17:38 292K 
[ ]The perception of speech under adverse conditions - 2004.pdf2016-10-19 14:22 809K 
[ ]Exploiting deep neural networks for detection-based speech recognition - 2013.pdf2016-10-19 14:35 1.0M 
[TXT]get.txt2016-10-22 10:46 1.3K 
[ ]Deep LSTM for large vocabulary continuous speech recognition - 2017.pdf2017-03-21 17:25 164K 
[ ]A wavenet for speech denoising - 2017.pdf2017-06-22 17:41 685K 
[ ]Generating adversarial examples for speech recognition.pdf2017-06-26 10:59 506K 
[ ]Stimulated deep neural network for speech recognition - 2016.pdf2017-08-08 19:57 1.0M 
[ ]The Microsoft 2017 conversational speech recognition system - 2017.pdf2017-08-20 19:54 160K 
[TXT]url.txt2017-08-21 05:40 1.4K 
Apache/2.4.25 (Debian) Server at diyhpl.us Port 80