Detection of Singing Mistakes from Singing Voice

  • Isao Miyagawa
  • Yuya Chiba
  • Takashi Nose
  • Akinori ItoEmail author
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 82)


We investigate a method of detecting the wrong lyrics from the singing voice. In the proposed method, we compare the input singing voice and the reference singing voice using dynamic time warping, and then observe the frame-by-frame distance to find the error location. However, the absolute value of the distance is affected by the singer individuality of the reference and input singing voice. Thus, we attempted to adapt the singer individuality into the reference singer’s one by a linear transformation. The results of the experiment showed that we could detect the wrong lyrics with high accuracy when the different part of the lyrics was long. In addition, we investigated the effect of iterative linear transformation, and we could not find any benefit from the second or third linear transformations.


Singing voice Lyrics mistake Dynamic time warping 


  1. 1.
    Takeuchi, H., Hoguro, M., Umezaki, T.: A KARAOKE system singing evaluation method that more closely matches human evaluation. Trans. Inst. Electr. Eng. Jpn. C 130(6), 1042–1053 (2010)Google Scholar
  2. 2.
    Nakano, T., Goto, M., Hiraga, Y.: An automatic singing skill evaluation method for unknown melodies. Inf. Process. Soc. Jpn. 48(1), 227–236 (2007)Google Scholar
  3. 3.
    Daido, R., Ito, M., Makino, S., Ito, A.: Automatic evaluation of singing enthusiasm for karaoke. Comput. Speech Lang. 28, 501–517 (2014)CrossRefGoogle Scholar
  4. 4.
    Mesaros, A., Virtanen, T.: Automatic recognition of lyrics in singing. EURASIP J. Audio Speech Music Process. 2010, article No. 4 (2014)Google Scholar
  5. 5.
    Suzuki, M., Hosoya, T., Ito, A., Makino, S.: Music information retrieval from a singing voice using lyrics and melody information. EURASIP J. Adv. Signal Process. 2007, 038727 (2006)CrossRefzbMATHGoogle Scholar
  6. 6.
    Panasonic: KARAOKE machine, Patent JP-A-2001-42879 (2001)Google Scholar
  7. 7.
    Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, vol. 10(16), pp. 359–370 (1994)Google Scholar
  8. 8.
    Matsumoto, H., Inoue, H.: A piece wise linear special mapping for supervised speaker adaptation. In: Proceedings of ICASSP, vol. 1, pp. 449–452 (1992)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Isao Miyagawa
    • 1
  • Yuya Chiba
    • 1
  • Takashi Nose
    • 1
  • Akinori Ito
    • 1
    Email author
  1. 1.Graduate School of EngineeringTohoku UniversitySendaiJapan

Personalised recommendations