Highly Accurate Mandarin Tone Classification In The Absence of Pitch Information

@inproceedings{Ryant2014HighlyAM,
  title={Highly Accurate Mandarin Tone Classification In The Absence of Pitch Information},
  author={Neville Ryant and M. Slaney and M. Liberman and E. Shriberg and Jiahong Yuan},
  year={2014}
}
  • Neville Ryant, M. Slaney, +2 authors Jiahong Yuan
  • Published 2014
  • Computer Science
    • A deep neural network (DNN) classifier based only on 40 mel-frequency cepstral coefficients (MFCCs) achieved 29.99% frame error rate (FER) and 16.86% segment error rate (SER) in recognizing five tonal categories in Mandarin Chinese broadcast news. With the addition of subband autocorrelation change detection (SACD) pitch-class features [1], the classifier scored 27.58% FER and 15.56% SER. These results are substantially better than the best previously reported results on broadcast news tone… CONTINUE READING
    View via Publisher
    languagelog.ldc.upenn.edu
    20 Citations
    Background Citations
    10
    Methods Citations
    5
    20 Citations
    Citation Type

    Citation Type

    Improving Mandarin Tone Recognition Based on DNN by Combining Acoustic and Articulatory Features Using Extended Recognition Networks
    • 11
    An Investigation of the Target Approximation Model for Tone Modeling and Recognition in Continuous Mandarin Speech
    • PDF
    Pitch Range Estimation with Multi features and MTL-DNN Model
    • 2
    Using tone-based extended recognition network to detect non-native Mandarin tone mispronunciations
    • 4
    Tone Classification in Mandarin Chinese Using Convolutional Neural Networks
    • 12
    • PDF
    Voice quality as a pitch-range indicator
    • 8
    • PDF
    Joint Gender-, Tone-, Vowel- Classification Via Novel Hierarchical Classification for Annotation of Monosyllabic Mandarin Word Tokens
    • Saurabh Garg, G. Hamarneh, A. Jongman, J. Sereno, Yue Wang
    • Computer Science
    • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2018
    • 2
    • PDF
    Improving Mandarin Prosody Boundary Detection by Using Phonetic Information and Deep LSTM Model
    Mandarin tone modeling using recurrent neural networks
    • 1
    • PDF
    The influence of pitch and noise on the discriminability of filterbank features
    • 1
    • PDF

    References

    SHOWING 1-10 OF 35 REFERENCES
    Mandarin tone classification without pitch tracking
    • 24
    • PDF
    Improved tone modeling for Mandarin broadcast news speech recognition
    • 77
    • Highly Influential
    • PDF
    Pitch tracking and tone features for Mandarin speech recognition
    • H. C. Huang, F. Seide
    • Computer Science
    • 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
    • 2000
    • 67
    Decision tree based tone modeling for Chinese speech recognition
    • Pui-Fung Wong, M. Siu
    • Computer Science
    • 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
    • 2004
    • 20
    Prediction of Fundamental Frequency and Voicing From Mel-Frequency Cepstral Coefficients for Unconstrained Speech Reconstruction
    • B. Milner, X. Shao
    • Computer Science
    • IEEE Transactions on Audio, Speech, and Language Processing
    • 2007
    • 53
    Tone and pitch accent classification using auditory attention cues
    • Ozlem Kalinli
    • Computer Science
    • 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
    • 2011
    • 11
    • PDF
    Pitch-gesture modeling using subband autocorrelation change detection
    • 5
    • PDF
    Large vocabulary Mandarin speech recognition with different approaches in modeling tones
    • 86
    • PDF
    Noise Robust Pitch Tracking by Subband Autocorrelation Classification
    • 78
    • PDF
    Temporal and spectral cues in Mandarin tone recognition.
    • 56
    • PDF