An overview of RNN-based mandarin speech recognition approaches

Yuan Fu Liao; Wei Tyng Hong; Wern Jun Wang; Yih-Ru Wang; Sin-Horng Chen

doi:10.1080/02533839.1999.9670492

An overview of RNN-based mandarin speech recognition approaches

Yuan Fu Liao, Wei Tyng Hong, Wern Jun Wang, Yih-Ru Wang, Sin-Horng Chen^*

^*Corresponding author for this work

National Chiao Tung University

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

The ANN-based approach is an alternate to the HMM method which is the currently dominant technology in the field of speech recognition. This paper is an overview of the RNN-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. We find from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition.

Original language	English
Pages (from-to)	535-547
Number of pages	13
Journal	Journal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an
Volume	22
Issue number	5
DOIs	https://doi.org/10.1080/02533839.1999.9670492
State	Published - 1 Jan 1999

Keywords

HMM
Mandarin speech recognition
RNN

Access to Document

10.1080/02533839.1999.9670492

Fingerprint Dive into the research topics of 'An overview of RNN-based mandarin speech recognition approaches'. Together they form a unique fingerprint.

Cite this

@article{311d972c8f3a45248ef3fdfa64d24b33,

title = "An overview of RNN-based mandarin speech recognition approaches",

abstract = "The ANN-based approach is an alternate to the HMM method which is the currently dominant technology in the field of speech recognition. This paper is an overview of the RNN-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. We find from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition.",

keywords = "HMM, Mandarin speech recognition, RNN",

author = "Liao, {Yuan Fu} and Hong, {Wei Tyng} and Wang, {Wern Jun} and Yih-Ru Wang and Sin-Horng Chen",

year = "1999",

month = jan,

day = "1",

doi = "10.1080/02533839.1999.9670492",

language = "English",

volume = "22",

pages = "535--547",

journal = "Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers",

issn = "0253-3839",

publisher = "Taylor and Francis Ltd.",

number = "5",

}

An overview of RNN-based mandarin speech recognition approaches. / Liao, Yuan Fu; Hong, Wei Tyng; Wang, Wern Jun; Wang, Yih-Ru; Chen, Sin-Horng.

In: Journal of the Chinese Institute of Engineers, Transactions of the Chinese Institute of Engineers,Series A/Chung-kuo Kung Ch'eng Hsuch K'an, Vol. 22, No. 5, 01.01.1999, p. 535-547.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - An overview of RNN-based mandarin speech recognition approaches

AU - Liao, Yuan Fu

AU - Hong, Wei Tyng

AU - Wang, Wern Jun

AU - Wang, Yih-Ru

AU - Chen, Sin-Horng

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The ANN-based approach is an alternate to the HMM method which is the currently dominant technology in the field of speech recognition. This paper is an overview of the RNN-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. We find from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition.

AB - The ANN-based approach is an alternate to the HMM method which is the currently dominant technology in the field of speech recognition. This paper is an overview of the RNN-based approaches to Mandarin speech recognition. Some RNN-based approaches proposed previously: syllable-boundary pre-segmentation, broad-class pre-classification, prosodic phrase boundary detection, and isolated and continuous syllable recognitions are discussed. We find from the survey that these approaches are all effective. So the RNN technology is comparable to the conventional HMM method on Mandarin speech recognition.

KW - HMM

KW - Mandarin speech recognition

KW - RNN

UR - http://www.scopus.com/inward/record.url?scp=0033357492&partnerID=8YFLogxK

U2 - 10.1080/02533839.1999.9670492

DO - 10.1080/02533839.1999.9670492

M3 - Article

AN - SCOPUS:0033357492

VL - 22

SP - 535

EP - 547

JO - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

JF - Chung-kuo Kung Ch'eng Hsueh K'an/Journal of the Chinese Institute of Engineers

SN - 0253-3839

IS - 5

ER -

An overview of RNN-based mandarin speech recognition approaches

Abstract

Keywords

Access to Document

Other files and links

Cite this