论文信息 - The NTNU Concatenative Speech Synthesizer

The NTNU Concatenative Speech Synthesizer

This paper describes NTNU’s entry for the Blizzard Challenge 2010. Our system is a conceptually simple variation of an HMM-based unit selection system, which uses diphones as the basic unit and employs a combined selection of units and their join points. The evaluation results of the Blizzard Challenge 2010 show that the system performs well when compared with the other systems.

Dyre Meen | T. Svendsen

[1] Keiichi Tokuda,et al. Duration modeling for HMM-based speech synthesis , 1998, ICSLP.

[2] Robert E. Donovan,et al. A new distance measure for costing spectral discontinuities in concatenative speech synthesizers , 2001, SSW.

[3] Mahesh Viswanathan,et al. Current status of the IBM Trainable Speech Synthesis System , 2001, SSW.

[4] Keiichi Tokuda,et al. Multi-Space Probability Distribution HMM , 2002 .

[5] Heiga Zen,et al. Hidden semi-Markov model based speech synthesis , 2004, INTERSPEECH.

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

[7] Kishore Prahallad,et al. CMU Blizzard 2007: A Hybrid Acoustic Unit Selection System from Statistically Predicted Parameters , 2007 .

[8] Ren-Hua Wang,et al. The USTC System for Blizzard Challenge 2010 , 2008 .

[9] Marcela Charfuelan,et al. The MARY TTS entry in the Blizzard Challenge 2008 , 2008 .