Corpus ID: 220831108

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
  • Engineering, Computer Science
  • 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

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Phonemic Transcription of Low-Resource Tonal Languages
    • 12
    • Highly Influential
    • PDF
    Universal Phone Recognition with a Multilingual Allophone System
    • 6
    • PDF
    Using tone information in Cantonese continuous speech recognition
    • 56
    Tone recognition in continuous Cantonese speech using supratone models.
    • 17
    Consistency of Tone-Syllable Alignment across Different Syllable Structures and Speaking Rates
    • Y Xu
    • Computer Science, Medicine
    • 1998
    • 251
    Syllable-based acoustic modeling with CTC-SMBR-LSTM
    • 10
    • Highly Influential
    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
    • 64
    • PDF
    Learning acoustic frame labeling for speech recognition with recurrent neural networks
    • 138
    • PDF