Voice Transformation Using Radial Basis Function

  • J. H. Nirmal
  • Suparva Patnaik
  • Mukesh A. Zaveri
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 150)


This paper presents novel technique of voice transformation (VT), which transform the individual acoustic characteristics of the source speaker so that it is perceived as if spoken like target speaker. Using features namely line spectral pairs (LSP) and pitch as spectral and glottal parameters of the source speaker are transformed into target speaker parameters using radial basis function (RBF). The results are evaluated using subjective and objective measures based on voice quality method. The listening tests prove that the proposed algorithm converts speaker individuality while maintaining high speech quality.


Voice transformation Line spectral pairs Long term prediction Radial basis function 


  1. 1.
    Kain A (2001) ’High resolution voice transformation’, PhD dissertation, Oregon Health and Science UniversityGoogle Scholar
  2. 2.
    Daniel, erro. eslava (2008) Intra-lingual and cross-lingual voice conversion using Harmonic plus stochastic models. PhD dissertation universitat politècnica decatalunyaGoogle Scholar
  3. 3.
    Turk O (2007) Cross-lingual voice conversion. PhD dissertation Bogazii UniversityGoogle Scholar
  4. 4.
    Sreenivasa Rao K (2010) Voice conversion by mapping the speaker-specific features using pitch synchronous approach. Computer speech and language, Elsevier, vol. 24, pp 474–494Google Scholar
  5. 5.
    Abe M, Nakamura S, Shikano K, Kuwabara H (1988) Voice conversion through vector quantization. International conference on acoustics, speech, and signal processing, ICASSP. p 655Google Scholar
  6. 6.
    Abe MA (1999) Segment-based approach to voice conversion. International conference acoustics, speech, and signal processing, ICASSP. p 765Google Scholar
  7. 7.
    Arslan LM, Talkin D (1999) Voice conversion by codebook mapping of line spectra frequencies and excitation spectrum. International proceedings Eurospeech. Rhodes, vol. 3, pp 1347–1350Google Scholar
  8. 8.
    Shikano K, Nakamura S, Abe M (1999) Speaker adaptation and voice conversion by codebook mapping. IEEE international symposium on circuits and systems, vol. 1, pp 594–597Google Scholar
  9. 9.
    Arslan LM (1999) Speaker transformation algorithm using segmental codebooks. STASC Speech Commun 28(3):211–226, 469–471Google Scholar
  10. 10.
    Valbret H, Moulines E, Tubach JP (1992) Voice transformation using PSOLA technique. Acoustics, speech, and signal processing, ICASSP pp I145–I148Google Scholar
  11. 11.
    Shuang ZW, Bakis R, Shechtman S, Chazan D, Qin Y (2006) Frequency warping based on mapping formant parameters. In: Proceedings of international conference spoken language processGoogle Scholar
  12. 12.
    Stylianou Y, Cappa O (1998) A system for voice conversion based on probabilistic classification and harmonic plus noise model. International conference acoustics, speech and signal processing, Proceedings pp 281–285Google Scholar
  13. 13.
    Kain A, Macon MW (1998) Spectral voice conversion for text-to-speech synthesis. Proceedings ICASSP, Seattle, pp 285–288Google Scholar
  14. 14.
    Toda T, Saruwatari H, Shikano K (2001) Voice conversion algorithm based on Gaussian mixture model with dynamic frequency warping of STRAIGHT spectrum. International conference on acoustics, speech, and signal processing, Proceedings. ICASSP. pp 841–844Google Scholar
  15. 15.
    Ye H, Young S (2006) Quality-enhanced voice morphing using maximum likelihood transformations. IEEE transactions audio, speech, language process, vol. 14, no. 4, pp 1301–1312Google Scholar
  16. 16.
    Ohtani Y, Toda T, Saruwatari H, Shikano K (2006) ‘Maximum likelihood voice conversion based on GMM with straight mixed excitation’. In: Proceedings InterspeechGoogle Scholar
  17. 17.
    Desai S, Raghavendra EV, Yegnanarayana B, Black AW, Prahallad K (2009) Voice conversion using artificial neural networks. In: Proceedings of IEEE international conference acoust, speech, and signal processing, pp 3893–3897Google Scholar
  18. 18.
    Chen W-Q, Zhang JL, Xiuguo B (2010) An improved method for voice conversion based on Gaussian mixture model. International conference on computer application and system modelling, PP V4-404-408Google Scholar
  19. 19.
    Narendranath H, Murthy A, Rajendran S, Yegnanarayana B (1995)‘Transformation of formants for voice conversion using artificial neural networks’, Speech communication, vol. 16, pp 207–216Google Scholar
  20. 20.
    Chen Z, Zhang LH (2010) A ANN base high quality method for voice conversion’. International conference on wireless communications networking and mobile computing (WiCOM)Google Scholar
  21. 21.
    Grassi S (1997) Dufaux, Ansorge; Pellandini, ‘Efficient algorithm to compute LSP parameters From 10th-order lpc coefficients’. International conference on acoustics, speech, and signal processing, vol. 3, pp 1707–1710Google Scholar
  22. 22.
    Lan Vince McLoughlin (2008) Line spectral pairs. Elesevier signal processing, pp 448–467Google Scholar
  23. 23.
    Lan Mcloughlin (2009) Applied speech and audio processing with matlab examples (1st edn). Cambridge Publication, CambridgeGoogle Scholar
  24. 24.
    Vergin R, Azarshid F, Shahguansy D (2006) Robust gender dependent acoustic phonetic modeling in continous speech recognition based on new automatic Male Female classification. International conference spoken language processing, pp 1–4Google Scholar
  25. 25.
    Pawan K, Jakhanwal N, Bhowmick A, Chandra M (2011) Gender classification using pitch and formant. International conference on communication, computing & security pp 319–324Google Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  • J. H. Nirmal
    • 1
  • Suparva Patnaik
    • 2
  • Mukesh A. Zaveri
    • 3
  1. 1.Department of Electronics EngineeringK.J.Somaiya College of EngineeringMumbaiIndia
  2. 2.Department of Electronics EngineeringS V National Institute of TechnologySuratIndia
  3. 3.Department of Computer EngineeringS V National Institute of TechnologySuratIndia

Personalised recommendations