| 1 |
Syntactic Reanalysis in Language Models for Speech Recognition
|
|
|
|
In: 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob) ; https://hal.inria.fr/hal-01558462 ; 2017 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob), Sep 2017, Lisbon, Portugal ; http://icdl-epirob.org/ (2017)
|
|
Abstract:
International audience ; State-of-the-art speech recognition systems steadily increase their performance using different variants of deep neural networks and postprocess the results by employing N-gram statistical models trained on a large amount of data coming from the general-purpose domain. While achieving an excellent performance regarding Word Error Rate (17.343% on our Human-Robot Interaction data set), state-of-the-art systems generate hypotheses that are grammatically incorrect in 57.316% of the cases. Moreover, if employed in a restricted domain (e.g. Human-Robot Interaction), around 50% of the hypotheses contain out-of-domain words. The latter are confused with similarly pronounced in-domain words and cannot be interpreted by a domain-specific inference system. The state-of-the-art speech recognition systems lack a mechanism that addresses syntactic correctness of hypotheses. We propose a system that can detect and repair grammatically incorrect or infrequent sentence forms. It is inspired by a computational neuroscience model that we developed previously. The current system is still a proof-of-concept version of a future neurobiologically more plausible neural network model. Hence, the resulting system postprocesses sentence hypotheses of state-of-the-art speech recognition systems, producing in-domain words in 100% of the cases, syntactically and grammatically correct hypotheses in 90.319% of the cases. Moreover, it reduces the Word Error Rate to 11.038%.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]; [INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO]; [SCCO.LING]Cognitive science/Linguistics; [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]; domain-specific; grapheme; Human-Robot Interaction; N-gram; natural language processing; phoneme; speech recognition; syntactic reanalysis; syntax
|
|
URL: https://hal.inria.fr/hal-01558462v2/document
https://hal.inria.fr/hal-01558462v2/file/twiefel_ICDL_EpiRob_2017__generated_by_xav.pdf
https://hal.inria.fr/hal-01558462
|
|
BASE
|
|
Hide details
|
|
|
|
|
