Semi-Supervised Training of DNN-Based Acoustic Model for ATC Speech Recognition

被引：12

作者：

Smidl, Lubos ^{[1
]}

Svec, Jan ^{[2
]}

Prazak, Ales ^{[1
]}

Trmal, Jan ^{[3
]}

机构：

[1] Univ West Bohemia, Dept Cybernet, Plzen, Czech Republic

[2] SpeechTech Sro, Plzen, Czech Republic

[3] Johns Hopkins Univ, Ctr Language & Speech Proc, Baltimore, MD USA

来源：

SPEECH AND COMPUTER (SPECOM 2018) | 2018年 / 11096卷

关键词：

Semi-supervised training; Data selection; Acoustic modelling; ATC speech recognition;

D O I：

10.1007/978-3-319-99579-3_66

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we describe a semi-supervised training method used to generalize the Air Traffic Control (ATC) speech recognizer. The paper introduces the problems and challenges in ATC English recognition, describes available datasets and ongoing research projects. The baseline recognition model is then used to recognize the unlabelled data from a publicly available source. We used the LiveATC community portal which records and archives the recordings of ATC communication near the airports. The recognized unlabelled data are filtered using the data selection procedure based on confidence scores and the recognition acoustic model is retrained to obtain a more general model. The results on accented Czech and French data are reported.

引用

页码：646 / 655

页数：10

共 50 条

[1] SEMI-SUPERVISED ENSEMBLE DNN ACOUSTIC MODEL TRAINING
Li, Sheng
Lu, Xugang
Sakai, Shinsuke
Mimura, Masato
Kawahara, Tatsuya
2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5270 - 5274
[2] Semi-Supervised Speech Recognition Acoustic Model Training Using Policy Gradient
Chung, Hoon
Lee, Sung Joo
Jeon, Hyeong Bae
Park, Jeon Gue
APPLIED SCIENCES-BASEL, 2020, 10 (10):
[3] Semi-supervised acoustic model training for speech with code-switching
Yilmaz, Emre
McLaren, Mitchell
van den Heuvel, Henk
van Leeuwen, David A.
SPEECH COMMUNICATION, 2018, 105 : 12 - 22
[4] Lithuanian Broadcast Speech Transcription using Semi-supervised Acoustic Model Training
Lileikyte, Rasa
Gorin, Arseniy
Lamel, Lori
Gauvain, Jean-Luc
Fraga-Silva, Thiago
SLTU-2016 5TH WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGIES FOR UNDER-RESOURCED LANGUAGES, 2016, 81 : 107 - 113
[5] Semi-supervised and unsupervised discriminative language model training for automatic speech recognition
Dikici, Erinc
Saraclar, Murat
SPEECH COMMUNICATION, 2016, 83 : 54 - 63
[6] Exploiting Eigenposteriors for Semi-supervised Training of DNN Acoustic Models with Sequence Discrimination
Dighe, Pranay
Asaei, Afsaneh
Bourlard, Nerve
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3552 - 3556
[7] Semi-supervised DNN training with word selection for ASR
Vesely, Karel
Burget, Lukas
Cernocky, Jan Honza
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 3687 - 3691
[8] LANGUAGE DIARIZATION FOR SEMI-SUPERVISED BILINGUAL ACOUSTIC MODEL TRAINING
Yilmaz, Emre
McLaren, Mitchell
van den Heuvel, Henk
van Leeuwen, David A.
2017 IEEE AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING WORKSHOP (ASRU), 2017, : 91 - 96
[9] SEMI-SUPERVISED AND POPULATION BASED TRAINING FOR VOICE COMMANDS RECOGNITION
Elibol, Oguz H.
Keskin, Gokce
Thomas, Anil
2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6371 - 6375
[10] Investigation of Semi-supervised Acoustic Model Training based on the Committee of Heterogeneous Neural Networks
Kanda, Naoyuki
Harada, Shoji
Lu, Xugang
Kawai, Hisashi
17TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2016), VOLS 1-5: UNDERSTANDING SPEECH PROCESSING IN HUMANS AND MACHINES, 2016, : 1325 - 1329

← 1 2 3 4 5 →