The dramatic piece reader for the blind and visually impaired

The paper presents the concept and realization of t he intelligent audio-book reader for the visually impa ired. The system is capable of presenting personalities of di fferent characters. The synthesizer mimics the way how a puppeteer portrays different characters. A traditional puppet eer generally uses up to a dozen different marionettes in one pie ce. Each of them impersonates a character with its own typical voice manifestation. We studied the techniques the puppet eer uses to change his voice and the acoustical correlates of t hese changes. The results are used to predict appropriat e settings of the parameters of the voice for every character of the piece. The information on the personality features of ever y particular character is inserted manually by a human operator. Similarly to the puppeteer’s show only one speaker’s voice is used in this concept and all the modifications are made usi ng speech synthesis methods.

[1]  John H. L. Hansen,et al.  Analysis and classification of speech mode: whispered through shouted , 2007, INTERSPEECH.

[2]  Milan Rusko,et al.  Multilinguality , singing synthesis , acoustic emoticons , and other extensions of the Slovak speech synthesizer for SMS reading , 2004 .

[3]  Heiga Zen,et al.  Statistical Parametric Speech Synthesis , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[4]  Nadia Magnenat-Thalmann,et al.  Imparting Individuality to Virtual Humans , 2002 .

[5]  Alan W. Black,et al.  Unit selection in a concatenative speech synthesis system using a large speech database , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[6]  Ana Paiva,et al.  Telling Stories with a Synthetic Character: Understanding Inter-modalities Relations , 2007, COST 2102 Workshop.

[7]  Darjaa Sakhia,et al.  Three Generations of Speech Synthesis Systems in Slovakia , 2006 .

[8]  Milan Rusko,et al.  Character Identity Expression in Vocal Performance of Traditional Puppeteers , 2006, TSD.

[9]  Taniya Mishra,et al.  Predicting Character-Appropriate Voices for a TTS-based Storyteller System , 2012, INTERSPEECH.

[10]  Christophe d'Alessandro,et al.  Designing French Tale Corpora for Entertaining Text To Speech Synthesis , 2012, LREC.

[11]  H. A. Buurman,et al.  Virtual Storytelling: Emotions for the narrator , 2007 .

[12]  Milos Cernak,et al.  Slovak Speech Database for Experiments and Application Building in Unit-Selection Speech Synthesis , 2004, TSD.

[13]  John Laver,et al.  The gift of speech , 1991 .

[14]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[15]  John Kane,et al.  Detecting a targeted voice style in an audiobook using voice quality features , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  J. M. Digman.  PERSONALITY STRUCTURE: EMERGENCE OF THE FIVE-FACTOR MODEL , 1990 .

[17]  M. Rusko,et al.  Acoustic, semantic and personality dimensions in the speech of traditional puppeteers , 2012, 2012 IEEE 3rd International Conference on Cognitive Infocommunications (CogInfoCom).

[18]  R. McCrae,et al.  An introduction to the five-factor model and its applications. , 1992, Journal of personality.