In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9% character error rate.
Peng FAN
Sichuan University
Xiyao HUA
Sichuan University
Yi LIN
Sichuan University
Bo YANG
Sichuan University
Jianwei ZHANG
Sichuan University
Wenyi GE
Chengdu University of Information Technology
Dongyue GUO
Sichuan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Peng FAN, Xiyao HUA, Yi LIN, Bo YANG, Jianwei ZHANG, Wenyi GE, Dongyue GUO, "Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 4, pp. 538-544, April 2023, doi: 10.1587/transinf.2022EDP7151.
Abstract: In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9% character error rate.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022EDP7151/_p
Copy
@ARTICLE{e106-d_4_538,
author={Peng FAN, Xiyao HUA, Yi LIN, Bo YANG, Jianwei ZHANG, Wenyi GE, Dongyue GUO, },
journal={IEICE TRANSACTIONS on Information},
title={Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training},
year={2023},
volume={E106-D},
number={4},
pages={538-544},
abstract={In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9% character error rate.},
keywords={},
doi={10.1587/transinf.2022EDP7151},
ISSN={1745-1361},
month={April},}
Copy
TY - JOUR
TI - Speech Recognition for Air Traffic Control via Feature Learning and End-to-End Training
T2 - IEICE TRANSACTIONS on Information
SP - 538
EP - 544
AU - Peng FAN
AU - Xiyao HUA
AU - Yi LIN
AU - Bo YANG
AU - Jianwei ZHANG
AU - Wenyi GE
AU - Dongyue GUO
PY - 2023
DO - 10.1587/transinf.2022EDP7151
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2023
AB - In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block, recurrent neural network (RNN), and connectionist temporal classification loss to build an end-to-end ASR model. Facing the complex environments of ATC speech, instead of the handcrafted features, a learning block is designed to extract informative features from raw waveforms for acoustic modeling. Both the SincNet and 1D convolution blocks are applied to process the raw waveforms, whose outputs are concatenated to the RNN layers for the temporal modeling. Thanks to the ability to learn representations from raw waveforms, the proposed model can be optimized in a complete end-to-end manner, i.e., from waveform to text. Finally, the multilingual issue in the ATC domain is also considered to achieve the ASR task by constructing a combined vocabulary of Chinese characters and English letters. The proposed approach is validated on a multilingual real-world corpus (ATCSpeech), and the experimental results demonstrate that the proposed approach outperforms other baselines, achieving a 6.9% character error rate.
ER -