A Recurrent Neural Network-Based Approach to Automatic Language Identification from Speech

被引：1

作者：

Mukherjee, Himadri ^{[1
]}

Dhar, Ankita ^{[1
]}

Obaidullah, Sk Md ^{[2
]}

Santosh, K. C. ^{[3
]}

Phadikar, Santanu ^{[4
]}

Roy, Kaushik ^{[1
]}

机构：

[1] West Bengal State Univ, Dept Comp Sci, Kolkata, India

[2] Aliah Univ, Dept Comp Sci & Engn, Kolkata, India

[3] Univ South Dakota, Dept Comp Sci, Brookings, SD USA

[4] Maulana Abul Kalam Azad Univ Technol, Dept Comp Sci & Engn, Kolkata, India

来源：

PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON COMMUNICATION, DEVICES AND COMPUTING | 2020年 / 602卷

关键词：

Language identification; Recurrent neural network; Long short-term memory; Line spectral frequency;

D O I：

10.1007/978-981-15-0829-5_43

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

The task of automatically identifying the used language from speech signals is known as automatic language identification. It is very much important prior to speech recognition in multilingual scenarios where speakers use more than a single language in course of communication. In this paper, a recurrent neural network (RNN)-based system with long short-term memory (LSTM) along with handcrafted line spectral frequency-based features is proposed for language identification. Experiments were performed on as many as 21908 clips (more than 30 h of data) from the top three spoken languages of the world, namely, English, Chinese, and Spanish, and a highest average accuracy of 95.22% has been obtained.

引用

页码：441 / 450

页数：10

共 50 条

[21] Investigating Modulation Spectrogram Features for Deep Neural Network-based Automatic Speech Recognition
Baby, Deepak
Van Hamme, Hugo
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2479 - 2483
[22] Recurrent Neural Network Based Language Model Adaptation for Accent Mandarin Speech
Ni, Hao
Yi, Jiangyan
Wen, Zhengqi
Tao, Jianhua
PATTERN RECOGNITION (CCPR 2016), PT II, 2016, 663 : 607 - 617
[23] Graph neural network-based topological relationships automatic identification of geological boundaries
Han, Shuyang
Zhang, Yichi
Wang, Jiajun
Tong, Dawei
Lyu, Mingming
COMPUTERS & GEOSCIENCES, 2024, 188
[24] A Recurrent Neural Network-Based Method for Dynamic Load Identification of Beam Structures
Yang, Hongji
Jiang, Jinhui
Chen, Guoping
Mohamed, M. Shadi
Lu, Fan
MATERIALS, 2021, 14 (24)
[25] Recurrent neural network speech predictor based on dynamical systems approach
Varoglu, E
Hacioglu, K
IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 2000, 147 (02): : 149 - 156
[26] An Attentional Recurrent Neural Network-Based Automatic Diagnosis Method for Machine Translation Errors
Huang, Yan
Yu, Xiaofang
Cheng, Xiaoli
Wang, Rujie
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2024, 33 (16)
[27] A recurrent neural network speech predictor based on dynamical systems approach
Varoglu, E
Hacioglu, K
PROCEEDINGS OF THE IEEE-EURASIP WORKSHOP ON NONLINEAR SIGNAL AND IMAGE PROCESSING (NSIP'99), 1999, : 316 - 320
[28] Recurrent Neural Network-Based Video Compression
Montajabi, Zahra
Ghassab, Vahid Khorasani
Bouguila, Nizar
2022 21ST IEEE INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, ICMLA, 2022, : 925 - 930
[29] Neural network-based automatic factor construction
Fang, Jie
Lin, Jianwu
Xia, Shutao
Xia, Zhikang
Hu, Shenglei
Liu, Xiang
Jiang, Yong
QUANTITATIVE FINANCE, 2020, 20 (12) : 2101 - 2114
[30] MFCC-based Recurrent Neural Network for automatic clinical depression recognition and assessment from speech
Rejaibi, Emna
Komaty, Ali
Meriaudeau, Fabrice
Agrebi, Said
Othmani, Alice
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2022, 71

← 1 2 3 4 5 →