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
  • [1] Pretraining by Backtranslation for End-to-end ASR in Low-Resource Settings
    Wiesner, Matthew
    Renduchintala, Adithya
    Watanabe, Shinji
    Liu, Chunxi
    Dehak, Najim
    Khudanpur, Sanjeev
    INTERSPEECH 2019, 2019, : 4375 - 4379
  • [2] ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion
    Casanova, Edresson
    Shulby, Christopher
    Korolev, Alexander
    Candido Junior, Arnaldo
    Soares, Anderson da Silva
    Aluisio, Sandra
    Ponti, Moacir Antonelli
    INTERSPEECH 2023, 2023, : 1244 - 1248
  • [3] Trying to Improve Sepsis Care in Low-Resource Settings
    Machado, Flavia R.
    Angus, Derek C.
    JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2017, 318 (13): : 1225 - 1227
  • [4] Biomarkers to improve rational antibiotic use in low-resource settings
    Keitel, Kristina
    LANCET GLOBAL HEALTH, 2019, 7 (01): : E14 - E15
  • [5] Developing nephrology programs in very low-resource settings: challenges in sustainability
    Yeates, Karen
    Ghosh, Sudakshina
    Kilonzo, Kajiru
    KIDNEY INTERNATIONAL SUPPLEMENTS, 2013, 3 (02) : 202 - 205
  • [6] Telemedicine in low-resource settings
    Wootton, Richard
    Bonnardot, Laurent
    FRONTIERS IN PUBLIC HEALTH, 2015, 3
  • [7] Appendicitis in Low-Resource Settings
    Bessoff, Kovi E.
    Forrester, Joseph D.
    SURGICAL INFECTIONS, 2020, 21 (06) : 523 - 532
  • [8] Bioengineering for low-resource settings
    Nature Reviews Bioengineering, 2023, 1 (9): : 607 - 607
  • [9] Fine-Tuning ASR models for Very Low-Resource Languages: A Study on Mvskoke
    Mainzinger, Julia
    Levow, Gina-Anne
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 4: STUDENT RESEARCH WORKSHOP, 2024, : 94 - 100
  • [10] Data and ICU registries to improve care delivery in low-resource settings
    Amado, Filipe
    Quintairos, Amanda
    Lanziotti, Vanessa Soares
    Salluh, Jorge I. F.
    INTENSIVE CARE MEDICINE, 2024, 50 (03) : 457 - 458