Voice Conversion Can Improve ASR in Very Low-Resource Settings

被引:4
|
作者
Baas, Matthew [1 ]
Kamper, Herman [1 ]
机构
[1] Stellenbosch Univ, MediaLab, E&E Engn, Stellenbosch, South Africa
来源
基金
新加坡国家研究基金会;
关键词
voice conversion; data augmentation; low-resource speech processing; speech recognition;
D O I
10.21437/Interspeech.2022-112
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
Voice conversion (VC) could be used to improve speech recognition systems in low-resource languages by using it to augment limited training data. However, VC has not been widely used for this purpose because of practical issues such as compute speed and limitations when converting to and from unseen speakers. Moreover, it is still unclear whether a VC model trained on one well-resourced language can be applied to speech from another low-resource language for the aim of data augmentation. In this work we assess whether a VC system can be used cross-lingually to improve low-resource speech recognition. We combine several recent techniques to design and train a practical VC system in English, and then use this system to augment data for training speech recognition models in several low-resource languages. When using a sensible amount of VC augmented data, speech recognition performance is improved in all four low-resource languages considered. We also show that VC-based augmentation is superior to SpecAugment (a widely used signal processing augmentation method) in the low-resource languages considered.
引用
收藏
页码:3513 / 3517
页数:5
相关论文
共 50 条
  • [31] Respiratory problems in low-resource settings
    Leng, Mhoira E. F.
    Daniel, Sunitha
    Munday, Daniel
    CURRENT OPINION IN SUPPORTIVE AND PALLIATIVE CARE, 2017, 11 (03) : 174 - 178
  • [32] SYNTHETIC DATA AUGMENTATION FOR IMPROVING LOW-RESOURCE ASR
    Thai, Bao
    Jimerson, Robert
    Arcoraci, Dominic
    Prud'hommeaux, Emily
    Ptucha, Raymond
    2019 IEEE WESTERN NEW YORK IMAGE AND SIGNAL PROCESSING WORKSHOP (WNYISPW), 2019,
  • [33] Reduce and Reconstruct: ASR for Low-Resource Phonetic Languages
    Diwan, Anuj
    Jyothi, Preethi
    INTERSPEECH 2021, 2021, : 3445 - 3449
  • [34] Community-based interventions to improve neonatal survival in low-resource settings
    McKenzie, L.
    Ellis, M.
    ANNALS OF TROPICAL PAEDIATRICS, 2011, 31 (03): : 191 - 199
  • [35] Systematic Investigation of Strategies Tailored for Low-Resource Settings for Low-Resource Dependency Parsing
    Sandhan, Jivnesh
    Behera, Laxmidhar
    Goyal, Pawan
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 2164 - 2171
  • [36] TOWARDS LOW-RESOURCE STARGAN VOICE CONVERSION USING WEIGHT ADAPTIVE INSTANCE NORMALIZATION
    Chen, Mingjie
    Shi, Yanpei
    Hain, Thomas
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5949 - 5953
  • [37] MULTILINGUAL SHIFTING DEEP BOTTLENECK FEATURES FOR LOW-RESOURCE ASR
    Quoc Bao Nguyen
    Gehring, Jonas
    Mueller, Markus
    Stueker, Sebastian
    Waibel, Alex
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
  • [38] Management of Empyema Thoracis in Low-Resource Settings
    Bekele, Abebe
    Alayande, Barnabas Tobi
    THORACIC SURGERY CLINICS, 2022, 32 (03) : 361 - 372
  • [39] Challenges in the diagnosis of meningitis in low-resource settings
    Yansouni, Cedric P.
    Lynen, Lut
    Colebunders, Robert
    TROPICAL MEDICINE & INTERNATIONAL HEALTH, 2010, 15 (12) : 1556 - 1557
  • [40] Monitoring mortality trends in low-resource settings
    Pagel, Christina
    Prost, Audrey
    Nair, Nirmala
    Tripathy, Prasanta
    Costello, Anthony
    Utley, Martin
    BULLETIN OF THE WORLD HEALTH ORGANIZATION, 2012, 90 (06) : 474 - 476