Unit-selection synthesis, features

The purpose of all the prosody algorithms described in this chapter is to provide part of the specification which will act as input to the synthesizer proper. In the past, the provision of FO and timing information was uncontested as a vital part of the synthesis specification and most of today s systems still use them. As we shall see in Chapters 15 and 16, however, some third generation systems do not require any acoustic prosody specification at all, making used of higher level prosodic representations instead. Rather than use FO directly, stress, phrasing, and discourse information are used. While such an approach completely bypasses all the problems described in this chapter, it does have the consequence of increasing the dimensionahty of the feature space used in unit selection or HMM synthesis. It is therefore a practical question of tradeoff whether such an approach is better than the traditional approach. 

In all types of data driven synthesis, we not only require data, but require this data to be labelled in some way. As a minimum, this normally means we require the words and phones, but any feature that we require for model building or unit selection must be provided by some means. In this section, we concentrate on one such way of carrying out this labelling, based on the HMM principles introduced above. 

One of the fundamental problems in unit selection is that the specification items lack the acoustic description(s) that would make matching them with units a fairly easy process. We can approach this problem in two ways. Firstly, we can just ignore the fact that the units have acoustic features and just match on the linguistic features alone. Alternatively, we can try and perform a partial synthesis, where we attempt to generate some or all of the acoustic features and then match these with the acoustic features derived by signal processing fi-om the waveforms. 

Tsuzaki, M. Feature extraction by auditory modeling for unit selection in concatenative speech synthesis. n Proceedings of Eurospeech 2001 (2001). 

Clark, R. A. J., Richmond, K., and King, S. Festival 2 build your own general purpose unit selection speech synthesiser. In 5th ISCA Workshop on Speech Synthesis (2004). Clements, G. N. The geometry of phonological features. Phonology Yearbook 2 (1985), pp. 225-252. 

---