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

doi:10.1109/SITIS.2019.00081

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

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

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 language	British English
Title of host publication	Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019
Editors	Kokou Yetongnon, Albert Dipanda, Gabriella Sanniti di Baja, Luigi Gallo, Richard Chbeir
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	470-474
Number of pages	5
ISBN (Electronic)	9781728156866
DOIs	https://doi.org/10.1109/SITIS.2019.00081
State	Published - Nov 2019
Event	15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019 - Sorrento, Italy Duration: 26 Nov 2019 → 29 Nov 2019

Publication series

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

Conference

Conference	15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019
Country/Territory	Italy
City	Sorrento
Period	26/11/19 → 29/11/19

Keywords

Error correction
Language model
Personalized adaptation
Speach recognition

Access to Document

10.1109/SITIS.2019.00081

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). Article 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

Ikegami, Yukino ; Knauf, Rainer ; Damiani, Ernesto et al. / High performance personal adaptation speech recognition framework by incremental learning with plural language models. Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019. editor / Kokou Yetongnon ; Albert Dipanda ; Gabriella Sanniti di Baja ; Luigi Gallo ; Richard Chbeir. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 470-474 (Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019).

@inproceedings{c7236db7a81f45d295673a9ec127084f,

title = "High performance personal adaptation speech recognition framework by incremental learning with plural language models",

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.",

keywords = "Error correction, Language model, Personalized adaptation, Speach recognition",

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

note = "Funding Information: This work was supported by Artificial Intelligence Research Promotion Foundation. Funding Information: ACKNOWLEDGMENT This work was supported by Artificial Research Promotion Foundation. Publisher Copyright: {\textcopyright} 2019 IEEE.; 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019 ; Conference date: 26-11-2019 Through 29-11-2019",

year = "2019",

month = nov,

doi = "10.1109/SITIS.2019.00081",

language = "British English",

series = "Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "470--474",

editor = "Kokou Yetongnon and Albert Dipanda and {Sanniti di Baja}, Gabriella and Luigi Gallo and Richard Chbeir",

booktitle = "Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019",

address = "United States",

}

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., 9067874, Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 470-474, 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019, Sorrento, Italy, 26/11/19. https://doi.org/10.1109/SITIS.2019.00081

High performance personal adaptation speech recognition framework by incremental learning with plural language models. / Ikegami, Yukino; Knauf, Rainer; Damiani, Ernesto et al.
Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019. ed. / Kokou Yetongnon; Albert Dipanda; Gabriella Sanniti di Baja; Luigi Gallo; Richard Chbeir. Institute of Electrical and Electronics Engineers Inc., 2019. p. 470-474 9067874 (Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - High performance personal adaptation speech recognition framework by incremental learning with plural language models

AU - Ikegami, Yukino

AU - Knauf, Rainer

AU - Damiani, Ernesto

AU - Tsuruta, Setsuo

AU - Sakurai, Yoshitaka

AU - Sakurai, Eriko

AU - Kutics, Andrea

AU - Nakagawa, Akihiko

N1 - Funding Information: This work was supported by Artificial Intelligence Research Promotion Foundation. Funding Information: ACKNOWLEDGMENT This work was supported by Artificial Research Promotion Foundation. Publisher Copyright: © 2019 IEEE.

PY - 2019/11

Y1 - 2019/11

N2 - 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.

AB - 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.

KW - Error correction

KW - Language model

KW - Personalized adaptation

KW - Speach recognition

UR - http://www.scopus.com/inward/record.url?scp=85084819206&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2019.00081

DO - 10.1109/SITIS.2019.00081

M3 - Conference contribution

AN - SCOPUS:85084819206

T3 - Proceedings - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019

SP - 470

EP - 474

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

A2 - Yetongnon, Kokou

A2 - Dipanda, Albert

A2 - Sanniti di Baja, Gabriella

A2 - Gallo, Luigi

A2 - Chbeir, Richard

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th International Conference on Signal Image Technology and Internet Based Systems, SISITS 2019

Y2 - 26 November 2019 through 29 November 2019

ER -

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

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this