Development and evaluation of julius-compatible interface for Kaldi ASR

Yusuke Yamada; Takashi Nose; Yuya Chiba; Akinori Ito; Takahiro Shinozaki

doi:10.1007/978-3-319-63859-1_12

Development and evaluation of julius-compatible interface for Kaldi ASR

Yusuke Yamada, Takashi Nose, Yuya Chiba, Akinori Ito, Takahiro Shinozaki

ENG - Communications Engineering

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

Abstract

In recent years, the use of Kaldi has rapidly grown because it has adopted various technologies of DNN-based speech recognition in succession and has shown high recognition performance. On the other hand, the speech recognition engine, Julius, has been widely used especially in Japan. Julius is also attracting attention since DNN-HMM is implemented in it. In this paper, we describe the design plan of interfaces that make Kaldi speech recognition engine be compatible with Julius, a system overview, and the details of the speech input unit and the recognition result output unit. We also refer to the functions that we are planning to implement.

Original language	English
Title of host publication	Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,
Editors	Junzo Watada, Lakhmi C. Jain, Jeng-Shyang Pan, Pei-Wei Tsai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	91-96
Number of pages	6
ISBN (Print)	9783319638584
DOIs	https://doi.org/10.1007/978-3-319-63859-1_12
Publication status	Published - 2018 Jan 1
Event	13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017 - Matsue, Shimane, Japan Duration: 2017 Aug 12 → 2017 Aug 15

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	82
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Other

Other	13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017
Country	Japan
City	Matsue, Shimane
Period	17/8/12 → 17/8/15

Keywords

DNN-based speech recognition
Julius
Kaldi

ASJC Scopus subject areas

Decision Sciences(all)
Computer Science(all)

Access to Document

10.1007/978-3-319-63859-1_12

Fingerprint Dive into the research topics of 'Development and evaluation of julius-compatible interface for Kaldi ASR'. Together they form a unique fingerprint.

Cite this

Yamada, Y., Nose, T., Chiba, Y., Ito, A., & Shinozaki, T. (2018). Development and evaluation of julius-compatible interface for Kaldi ASR. In J. Watada, L. C. Jain, J-S. Pan, & P-W. Tsai (Eds.), Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, (pp. 91-96). (Smart Innovation, Systems and Technologies; Vol. 82). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-319-63859-1_12

Development and evaluation of julius-compatible interface for Kaldi ASR. / Yamada, Yusuke; Nose, Takashi; Chiba, Yuya; Ito, Akinori; Shinozaki, Takahiro.

Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,. ed. / Junzo Watada; Lakhmi C. Jain; Jeng-Shyang Pan; Pei-Wei Tsai. Springer Science and Business Media Deutschland GmbH, 2018. p. 91-96 (Smart Innovation, Systems and Technologies; Vol. 82).

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

Yamada, Y, Nose, T, Chiba, Y, Ito, A & Shinozaki, T 2018, Development and evaluation of julius-compatible interface for Kaldi ASR. in J Watada, LC Jain, J-S Pan & P-W Tsai (eds), Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,. Smart Innovation, Systems and Technologies, vol. 82, Springer Science and Business Media Deutschland GmbH, pp. 91-96, 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017, Matsue, Shimane, Japan, 17/8/12. https://doi.org/10.1007/978-3-319-63859-1_12

Yamada Y, Nose T, Chiba Y, Ito A, Shinozaki T. Development and evaluation of julius-compatible interface for Kaldi ASR. In Watada J, Jain LC, Pan J-S, Tsai P-W, editors, Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,. Springer Science and Business Media Deutschland GmbH. 2018. p. 91-96. (Smart Innovation, Systems and Technologies). https://doi.org/10.1007/978-3-319-63859-1_12

Yamada, Yusuke ; Nose, Takashi ; Chiba, Yuya ; Ito, Akinori ; Shinozaki, Takahiro. / Development and evaluation of julius-compatible interface for Kaldi ASR. Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,. editor / Junzo Watada ; Lakhmi C. Jain ; Jeng-Shyang Pan ; Pei-Wei Tsai. Springer Science and Business Media Deutschland GmbH, 2018. pp. 91-96 (Smart Innovation, Systems and Technologies).

@inproceedings{3cc8824a2bca43dbbbddc9db7e841ea5,

title = "Development and evaluation of julius-compatible interface for Kaldi ASR",

abstract = "In recent years, the use of Kaldi has rapidly grown because it has adopted various technologies of DNN-based speech recognition in succession and has shown high recognition performance. On the other hand, the speech recognition engine, Julius, has been widely used especially in Japan. Julius is also attracting attention since DNN-HMM is implemented in it. In this paper, we describe the design plan of interfaces that make Kaldi speech recognition engine be compatible with Julius, a system overview, and the details of the speech input unit and the recognition result output unit. We also refer to the functions that we are planning to implement.",

keywords = "DNN-based speech recognition, Julius, Kaldi",

author = "Yusuke Yamada and Takashi Nose and Yuya Chiba and Akinori Ito and Takahiro Shinozaki",

year = "2018",

month = jan,

day = "1",

doi = "10.1007/978-3-319-63859-1_12",

language = "English",

isbn = "9783319638584",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "91--96",

editor = "Junzo Watada and Jain, {Lakhmi C.} and Jeng-Shyang Pan and Pei-Wei Tsai",

booktitle = "Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,",

address = "Germany",

note = "13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017 ; Conference date: 12-08-2017 Through 15-08-2017",

}

TY - GEN

T1 - Development and evaluation of julius-compatible interface for Kaldi ASR

AU - Yamada, Yusuke

AU - Nose, Takashi

AU - Chiba, Yuya

AU - Ito, Akinori

AU - Shinozaki, Takahiro

PY - 2018/1/1

Y1 - 2018/1/1

N2 - In recent years, the use of Kaldi has rapidly grown because it has adopted various technologies of DNN-based speech recognition in succession and has shown high recognition performance. On the other hand, the speech recognition engine, Julius, has been widely used especially in Japan. Julius is also attracting attention since DNN-HMM is implemented in it. In this paper, we describe the design plan of interfaces that make Kaldi speech recognition engine be compatible with Julius, a system overview, and the details of the speech input unit and the recognition result output unit. We also refer to the functions that we are planning to implement.

AB - In recent years, the use of Kaldi has rapidly grown because it has adopted various technologies of DNN-based speech recognition in succession and has shown high recognition performance. On the other hand, the speech recognition engine, Julius, has been widely used especially in Japan. Julius is also attracting attention since DNN-HMM is implemented in it. In this paper, we describe the design plan of interfaces that make Kaldi speech recognition engine be compatible with Julius, a system overview, and the details of the speech input unit and the recognition result output unit. We also refer to the functions that we are planning to implement.

KW - DNN-based speech recognition

KW - Julius

KW - Kaldi

UR - http://www.scopus.com/inward/record.url?scp=85026650752&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85026650752&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-63859-1_12

DO - 10.1007/978-3-319-63859-1_12

M3 - Conference contribution

AN - SCOPUS:85026650752

SN - 9783319638584

T3 - Smart Innovation, Systems and Technologies

SP - 91

EP - 96

BT - Advances in Intelligent Information Hiding and Multimedia Signal Processing - Proceedings of the 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing,

A2 - Watada, Junzo

A2 - Jain, Lakhmi C.

A2 - Pan, Jeng-Shyang

A2 - Tsai, Pei-Wei

PB - Springer Science and Business Media Deutschland GmbH

T2 - 13th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2017

Y2 - 12 August 2017 through 15 August 2017

ER -