Speech Synthesis

[Print-friendly version]

Trainable Speech Synthesis With Trended Hidden Markov Models

Work on a trainable speech synthesis system that utilises trended Hidden Markov Models to represent phonetic speech units has been implemented. The performance of this system has been compared with synthesis using the traditional stationary framework and has yielded significant improvement in informal modified rhyme tests. Some examples of speech synthesis are provided below:

Synthesis of isolated word for modified rhyme tests: Male Australian Speaker

• Original Speech
• Synthesis with trended HMM
• Synthesis with stationary HMM

Speech synthesised using a voice from the WSJ1 corpus, speaker 453:

• Example of Original Training Speech
• Sentence 1
• Sentence 2
• Sentence 3

(Ref: J. Dines and S. Sridharan, "Trainable speech synthesis with trended Hidden Markov Models," ICASSP-2001, pp.833 - 837, May 2001.)