A component by component listening test analysis of the IBM trainable speech synthesis system

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Volumn , Issue , 2001, Pages 329-332

  Donovan, Robert E ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

DECISION TREES; SPEECH; SPEECH SYNTHESIS;

DECISION TREE CLUSTERING; LISTENING TESTS; PROSODIC MODIFICATIONS; RESEARCH EFFORTS; SPEECH QUALITY; SPEECH SYNTHESIS SYSTEM;

SPEECH COMMUNICATION;

EID: 85009090897     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (4)

1. Donovan, R.E., and Eide, E.M. (1998) The IBM Trainable Speech Synthesis System, Proc. ICSLP'98, Sydney.
2. IEEE (1969) IEEE Recommended Practice for Speech Quality Measurements, IEEE Transactions on Audio and Electroacoustics, Vol. AU-17, No. 3, pp. 225-246.
3. Syrdal A.K., Conkie, A. and Stylianou Y. (1998) Exploration of Acoustic Correlates in Speaker Selection for Concatenative Synthesis, Proc. ICSLP'98, Sydney.
4. Odell, J.J. (1995) The Use of Context in Large Vocabulary Speech Recognition, PhD. Thesis, Cambridge University Engineering Department.