Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?

  title={Autosegmental Neural Nets: Should Phones and Tones be Synchronous or Asynchronous?},
  author={Jiachen Li and M. Hasegawa-Johnson},
  • Jiachen Li, M. Hasegawa-Johnson
  • Published 2020
  • Computer Science, Engineering
  • ArXiv
  • Phones, the segmental units of the International Phonetic Alphabet (IPA), are used for lexical distinctions in most human languages; Tones, the suprasegmental units of the IPA, are used in perhaps 70%. Many previous studies have explored cross-lingual adaptation of automatic speech recognition (ASR) phone models, but few have explored the multilingual and cross-lingual transfer of synchronization between phones and tones. In this paper, we test four Connectionist Temporal Classification (CTC… CONTINUE READING
    1 Citations

    Figures, Tables, and Topics from this paper.


    Phonemic Transcription of Low-Resource Tonal Languages
    • 12
    • Highly Influential
    • PDF
    Universal Phone Recognition with a Multilingual Allophone System
    • 11
    • PDF
    Tone recognition in continuous Cantonese speech using supratone models.
    • 17
    Syllable-based acoustic modeling with CTC-SMBR-LSTM
    • 12
    • Highly Influential
    Using tone information in Cantonese continuous speech recognition
    • 57
    Multilingual Training and Cross-lingual Adaptation on CTC-based Acoustic Model
    • 18
    • PDF
    Models of tone for tonal and non-tonal languages
    • 48
    • PDF
    An empirical exploration of CTC acoustic models
    • 65
    • PDF
    Consistency of Tone-Syllable Alignment across Different Syllable Structures and Speaking Rates
    • Y Xu
    • Computer Science, Medicine
    • Phonetica
    • 1998
    • 254