High performance personal adaptation speech recognition framework by incremental learning with plural language models

Yukino Ikegami, Rainer Knauf, Ernesto Damiani, Setsuo Tsuruta, Yoshitaka Sakurai, Eriko Sakurai, Andrea Kutics, Akihiko Nakagawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper introduces a speech recognition framework for high performance personalized adaption. It is based on plural language models and personalized incremental learning interface for error correction. If an error in a recognition result is detected by a bidirectional neural language model, it generates a corrected sentence by a majority decision among multiple n-gram language models considering several aspects. Moreover, we introduce a speaker adaptation by updating language models through incremental learning, which can adjust the parameter from training data. The experiments show that our framework improves word-error rate to 78% compared with Google Chrome's Speech Recognition API. Our framework can be used for improving one-to-one human-machine dialogue systems such as intelligent (counseling) agents.

Original languageEnglish
Title of host publicationProceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019
EditorsKokou Yetongnon, Albert Dipanda, Gabriella Sanniti di Baja, Luigi Gallo, Richard Chbeir
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages470-474
Number of pages5
ISBN (Electronic)9781728156866
DOIs
Publication statusPublished - Nov 2019
Event15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019 - Sorrento, Italy
Duration: 26 Nov 201929 Nov 2019

Publication series

NameProceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019

Conference

Conference15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019
CountryItaly
CitySorrento
Period26/11/1929/11/19

Keywords

  • Error correction
  • Language model
  • Personalized adaptation
  • Speach recognition

Fingerprint Dive into the research topics of 'High performance personal adaptation speech recognition framework by incremental learning with plural language models'. Together they form a unique fingerprint.

  • Cite this

    Ikegami, Y., Knauf, R., Damiani, E., Tsuruta, S., Sakurai, Y., Sakurai, E., Kutics, A., & Nakagawa, A. (2019). High performance personal adaptation speech recognition framework by incremental learning with plural language models. In K. Yetongnon, A. Dipanda, G. Sanniti di Baja, L. Gallo, & R. Chbeir (Eds.), Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019 (pp. 470-474). [9067874] (Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SITIS.2019.00081