A MULTI-GENRE URDU BROADCAST SPEECH RECOGNITION SYSTEM

被引：3

作者：

Khan, Erbaz ^{[1
]}

Rauf, Sahar ^{[1
]}

Adeeba, Farah ^{[2
]}

Hussain, Sarmad ^{[1
]}

机构：

[1] Univ Engn & Technol, Al Khawarizmi Inst Comp Sci, Ctr Language Engn, Lahore, Pakistan

[2] Univ Engn & Technol, Dept Comp Sci, New Campus, Ksk, Pakistan

来源：

2021 24TH CONFERENCE OF THE ORIENTAL COCOSDA INTERNATIONAL COMMITTEE FOR THE CO-ORDINATION AND STANDARDISATION OF SPEECH DATABASES AND ASSESSMENT TECHNIQUES (O-COCOSDA) | 2021年

关键词：

BC; multi-genre; Urdu; corpus; speech recognition;

D O I：

10.1109/O-COCOSDA202152914.2021.9660552

中图分类号：

R36 [病理学]; R76 [耳鼻咽喉科学];

学科分类号：

100104 ; 100213 ;

摘要：

This paper reports the development of a multi-genre Urdu Broadcast (BC) corpus and a Large Vocabulary Continuous Speech Recognition (LVCSR) system. BC speech corpus of 98 hours from 453 speakers is collected and annotated. For acoustic modeling, Time-delay Neural Network (TDNN) is developed with prior Gaussian Mixture Model-Hidden Markov Model (GMM-HMM) training and alignments. For the language model, 3-gram, 4-gram and Recurrent Neural Network (RNN) based models are developed on a text corpus of 188 million words. The developed models are tested on 4.3 hours of unseen BC multi-genre speech dataset and the best Word Error Rate (WER) 18.59% is achieved using RNN based Language Model (LM). Moreover, a detailed word error analysis is carried out to compare the errors made by humans and the Automatic Speech Recognition (ASR) System. The results showed a similar behavior of word misrecognitions by both humans and ASR.

引用

页码：25 / 30

页数：6

共 18 条

[1]

Adeeba F., 2014, C LANG TECHN KAR

[2]

[Anonymous], 2002, 7 INT C SPOK LANG PR

[3]

[Anonymous], 2019, ACM WORKSH AI4TV

[4]

Bada I., 2017, ICNLSSP INT C NATURA

[5]

Baker J., 2006, HISTORICAL DEV FUTUR

[6]

Farooq M. U., 2020, O COCOSDA

[7]

Farooq M. U., 2019, INTERSPEECH

[8]

Glenn ML, 2009, INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, P2827

[9]

Jurafsky Daniel, 2009, Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

[10]

Jyothi P, 2015, 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, P3164

← 1 2 →