Advertisement

Towards Cross-Lingual Emotion Transplantation

  • Jaime Lorenzo-Trueba
  • Roberto Barra-Chicote
  • Junichi Yamagishi
  • Juan M. Montero
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8854)

Abstract

In this paper we introduce the idea of cross-lingual emotion transplantation. The aim is to lean the nuances of emotional speech in a source language for which we have enough data to adapt an acceptable quality emotional model by means of CSMAPLR adaptation, and then convert the adaptation function so it can be applied to a target language in a different target speaker while maintaining the speaker identity but adding emotional information. The conversion between languages is done at state level by measuring the KLD distance between the Gaussian distributions of all the states and linking the closest ones. Finally, as the cross-lingual transplantation of spectral emotions (mainly anger) was found out to introduce significant amounts of spectral noise, we show the results of applying three different techniques related to adaptation parameters that can be used to reduce the noise. The results are measured in an objective fashion by means of a bi-dimensional PCA projection of the KLD distances between the considered models (neutral models of both languages, reference emotion for both languages and transplanted emotional model for the target language).

Keywords

Statistical Parametric Speech Synthesis Expressive Speech Synthesis Emotion Transplantation Cross-lingual 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barra-Chicote, R., Montero, J.M., Macias-Guarasa, J., Lufti, S., Lucas, J.M., Fernandez, F., D’haro, L.F., San-Segundo, R., Ferreiros, J., Cordoba, R., Pardo, J.M.: Spanish expressive voices: Corpus for emotion research in spanish. In: Proc. of LREC (2008)Google Scholar
  2. 2.
    Barra-Chicote, R.: Contributions to the analysis, design and evaluation of strategies for corpus-based emotional speech synthesis. Ph.D. thesis, ETSIT-UPM (2011)Google Scholar
  3. 3.
    Gales, M.J.: Cluster adaptive training of hidden markov models. IEEE Transactions on Speech and Audio Processing 8(4), 417–428 (2000)CrossRefGoogle Scholar
  4. 4.
    Liang, H., Dines, J.: Phonological knowledge guided hmm state mapping for cross-lingual speaker adaptation. In: INTERSPEECH, pp. 1825–1828 (2011)Google Scholar
  5. 5.
    Lorenzo-Trueba, J., Barra-Chicote, R., Yamagishi, J., Watts, O., Montero, J.M.: Towards speaking style transplantation in speech synthesis. In: 8th ISCA Speech Synthesis Workshop (2013)Google Scholar
  6. 6.
    Nose, T., Kato, Y., Kobayashi, T.: Style estimation of speech based on multiple regression hidden semi-markov model. In: INTERSPEECH, pp. 2285–2288 (2007)Google Scholar
  7. 7.
    Oura, K., Yamagishi, J., Wester, M., King, S., Tokuda, K.: Analysis of unsupervised cross-lingual speaker adaptation for hmm-based speech synthesis using kld-based transform mapping. Speech Communication 54(6), 703–714 (2012)CrossRefGoogle Scholar
  8. 8.
    Qian, Y., Xu, J., Soong, F.K.: A frame mapping based hmm approach to cross-lingual voice transformation. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5120–5123. IEEE (2011)Google Scholar
  9. 9.
    Shichiri, K., Sawabe, A., Yoshimura, T., Tokuda, K., Masuko, T., Kobayashi, T., Kitamura, T.: Eigenvoices for hmm-based speech synthesis. In: INTERSPEECH (2002)Google Scholar
  10. 10.
    Takeda, S., Kabuta, Y., Inoue, T., Hatoko, M.: Proposal of a japanese-speech-synthesis method with dimensional representation of emotions based on prosody as well as voice-quality conversion. International Journal of Affective Engineering 12(2), 79–88 (2013)CrossRefGoogle Scholar
  11. 11.
    Togneri, R., Pullella, D.: An overview of speaker identification: Accuracy and robustness issues. IEEE Circuits and Systems Magazine 11(2), 23–61 (2011)CrossRefGoogle Scholar
  12. 12.
    Toman, M., Pucher, M., Schabus, D.: Multi-variety adaptive acoustic modeling in hsmm-based speech synthesis. In: 8th ISCA Speech Synthesis Workshop (2013)Google Scholar
  13. 13.
    Toman, M.E., Pucher, M.: Structural kld for cross-variety speaker adaptation in hmm-based speech synthesis. In: Proc. SPPRA, Innsbruck, Austria (2013)Google Scholar
  14. 14.
    Wu, Y.J., Nankaku, Y., Tokuda, K.: State mapping based method for cross-lingual speaker adaptation in hmm-based speech synthesis. In: INTERSPEECH, pp. 528–531 (2009)Google Scholar
  15. 15.
    Yamagishi, J., Kobayashi, T., Nakano, Y., Ogata, K., Isogai, J.: Analysis of speaker adaptation algorithms for hmm-based speech synthesis and a constrained smaplr adaptation algorithm. IEEE Transactions on Audio, Speech, and Language Processing 17(1), 66–83 (2009)CrossRefGoogle Scholar
  16. 16.
    Yoshimura, T., Hashimoto, K., Oura, K., Nankaku, Y., Tokuda, K.: Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for hmm-based speech synthesis. In: 8th ISCA Speech Synthesis Workshop (2013)Google Scholar
  17. 17.
    Zen, H., Braunschweiler, N., Buchholz, S., Knill, K., Krstulovic, S., Latorre, J.: Hmm-based polyglot speech synthesis by speaker and language adaptive training. In: Seventh ISCA Workshop on Speech Synthesis (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jaime Lorenzo-Trueba
    • 1
  • Roberto Barra-Chicote
    • 1
  • Junichi Yamagishi
    • 2
  • Juan M. Montero
    • 1
  1. 1.Speech Technology Group, ETSI TelecomunicacionUniversidad Politecnica de MadridSpain
  2. 2.National Institute of InformaticsTokyoJapan

Personalised recommendations