Abstract | ||
---|---|---|
Gesture typing is an efficient input method for phones and tablets using continuous traces created by a pointed object (e.g., finger or stylus). Translating such continuous gestures into textual input is a challenging task as gesture inputs exhibit many features found in speech and handwriting such as high variability, co-articulation and elision. In this work, we address these challenges with a hybrid approach, combining a variant of recurrent networks, namely Long Short Term Memories [1] with conventional Finite State Transducer decoding [2]. Results using our approach show considerable improvement relative to a baseline shape-matching-based system, amounting to 4% and 22% absolute improvement respectively for small and large lexicon decoding on real datasets and 2% on a synthetic large scale dataset. |
Year | Venue | Keywords |
---|---|---|
2015 | 2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP) | Long-short term memory, LSTM, gesture typing, keyboard |
Field | DocType | ISSN |
Handwriting,Pattern recognition,Computer science,Gesture,Input method,Recurrent neural network,Gesture recognition,Speech recognition,Artificial intelligence,Decoding methods,Hidden Markov model,Artificial neural network | Conference | 1520-6149 |
Citations | PageRank | References |
7 | 0.46 | 14 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ouais Alsharif | 1 | 49 | 4.65 |
Tom Yu Ouyang | 2 | 42 | 2.69 |
Françoise Beaufays | 3 | 341 | 27.76 |
Shumin Zhai | 4 | 4106 | 400.66 |
Thomas M. Breuel | 5 | 2362 | 219.10 |
Johan Schalkwyk | 6 | 461 | 40.80 |