This shows you the differences between two versions of the page.
Both sides previous revision Previous revision | Next revision Both sides next revision | ||
publications [2020/07/09 04:50] admin |
publications [2020/07/09 04:52] admin |
||
---|---|---|---|
Line 1: | Line 1: | ||
===== Publications ==== | ===== Publications ==== | ||
- | Notable achievements: | + | === Notable achievements: === |
* 1986: First implementation of Deep Neural Networks ([[https://www.researchgate.net/publication/338188874_Speech_Recognition_with_Associative_Networks|Speech Recognition with Associative Networks.]]) - these had the form o<sub>i</sub> = f(∑<sup>i-1</sup> w<sub>ij</sub> o<sub>j</sub>) and so were very deep having yet trained well using all possible skip connections. | * 1986: First implementation of Deep Neural Networks ([[https://www.researchgate.net/publication/338188874_Speech_Recognition_with_Associative_Networks|Speech Recognition with Associative Networks.]]) - these had the form o<sub>i</sub> = f(∑<sup>i-1</sup> w<sub>ij</sub> o<sub>j</sub>) and so were very deep having yet trained well using all possible skip connections. | ||
* 1987: First publication of Real Time Recurrent Learning ([[https://www.academia.edu/30351853/The_utility_driven_dynamic_error_propagation_network|The utility driven dynamic error propagation network.]] also [[https://papers.nips.cc/paper/42-static-and-dynamic-error-propagation-networks-with-application-to-speech-coding|Static and dynamic error propagation networks with application to speech coding.]]) | * 1987: First publication of Real Time Recurrent Learning ([[https://www.academia.edu/30351853/The_utility_driven_dynamic_error_propagation_network|The utility driven dynamic error propagation network.]] also [[https://papers.nips.cc/paper/42-static-and-dynamic-error-propagation-networks-with-application-to-speech-coding|Static and dynamic error propagation networks with application to speech coding.]]) | ||
Line 9: | Line 10: | ||
* 1996: First end-to-end training of neural nets and HMMs [[ftp://mi.eng.cam.ac.uk/pub/reports/auto-pdf/senior_fbrnn.pdf|Forward-backward retraining of recurrent neural networks]] | * 1996: First end-to-end training of neural nets and HMMs [[ftp://mi.eng.cam.ac.uk/pub/reports/auto-pdf/senior_fbrnn.pdf|Forward-backward retraining of recurrent neural networks]] | ||
* 1999: The time-first decoder ([[http://patft1.uspto.gov/netacgi/nph-Parser?patentnumber=5983180|Recognition of sequential data using finite state sequence models organized in a tree structure.]] and [[https://www.semanticscholar.org/paper/Time-first-search-for-large-vocabulary-speech-Robinson-Christie/123dbf5729b147abba09a5fe59dda454f09be0d2|Time-first search for large vocabulary speech recognition.]]) | * 1999: The time-first decoder ([[http://patft1.uspto.gov/netacgi/nph-Parser?patentnumber=5983180|Recognition of sequential data using finite state sequence models organized in a tree structure.]] and [[https://www.semanticscholar.org/paper/Time-first-search-for-large-vocabulary-speech-Robinson-Christie/123dbf5729b147abba09a5fe59dda454f09be0d2|Time-first search for large vocabulary speech recognition.]]) | ||
- | * As supervisor to MPHil students: | + | * As supervisor to MPhil students: |
* First speech editor - edit audio as text | * First speech editor - edit audio as text | ||
* First editor for correcting speech recognition transcripts | * First editor for correcting speech recognition transcripts | ||
Line 15: | Line 16: | ||
- | Full list: | + | === Full list: === |
* [[https://patents.google.com/patent/WO2017077330A1/en|Speech processing system and method.]] T. W. J. Ash and A. J. Robinson. Patent application PCT/GB2016/053456. November 2016. | * [[https://patents.google.com/patent/WO2017077330A1/en|Speech processing system and method.]] T. W. J. Ash and A. J. Robinson. Patent application PCT/GB2016/053456. November 2016. | ||
* [[https://arxiv.org/abs/1502.00512|Scaling Recurrent Neural Network Language Models.]] Will Williams, Niranjani Prasad, David Mrva, Tom Ash and Tony Robinson. In Proc. ICASSP, pages 5391-5395, 2015. | * [[https://arxiv.org/abs/1502.00512|Scaling Recurrent Neural Network Language Models.]] Will Williams, Niranjani Prasad, David Mrva, Tom Ash and Tony Robinson. In Proc. ICASSP, pages 5391-5395, 2015. |