A scenic-spot introduction-task-oriented 3Dvirtual human spoken dialogue system—EasyGuide is introduced.The system includes five modules:natural language processing,task domain knowledge database,dialogue management,voice processing and 3Dvirtual human text-to-visual speech synthesis.In the first module,dictionary construction along with sentence analysis and semantic representation are illustrated specifically.A tree-structured knowledge database is designed for the task domain.A novel framework based on the keyword analysis and context constraints is proposed as the dialogue management.As for voice processing module,a software development kit which performs speech recognition and synthesis is introduced briefly.In the last module,3Dviseme synthesis is explained with examples and a text-driven facial animation system is presented.Evaluation results show that the system can achieve satisfactory performance.
A novel spectral representation based on fractional Fourier transform (FrFT) is proposed and applied to birdcall analysis. The FrFT-based spectrogram of a signal is derived and compared with its FT-based counterpart,and the spectrum gathering method is used to show the energy distribution related to the pitch frequency. The fixed transform order and adaptive orders for FrFT are tested. The fixed order can be obtained empirically or calculated according to the known chirp rate. The adaptive optimal orders are determined by using ambiguity function. Experimental results with birdcalls show that the FrFT-based spectrogram with an optimal transform order has higher resolution than its STFT-based counterpart,and the better performance can be achieved if adaptive orders are used.
