Speech Technology and Linguistics

We finish with some general thoughts about the field of speech technology and linguistics and a discussion of future directions. 

In my opinion, the answer lies in the curse of dimensionality introduced in Section 5.2.1. Often experimental linguistics (and particularly phonetics) is conducted in the framework of a controlled experiment, where some data is collected with the 

Note that in his early work (pre-1970s) Chomsky put considerable emphasis on formally describing his theories, for example The Sound Pattern of English [91] is full of explicit rules and formulas. From this point on, however, the formal side more or less disappeared and recent work is not described in terms familiar to those from a traditional scientific background. 

I will finish, though, by saying that a solid knowledge of the basics of linguistics has been invaluable to me in my own TTS research, and that, in my view, a solid knowledge of acoustic phonetics is one of the key skills required to build a good unit-selection 

---

Paul Taylor is a Visiting Lecturer in Engineering at the University of Cambridge and Chief Executive Officer of Phonetic Arts. He received his Ph.D. in Linguistics from Edinburgh University, where he went on to serve as a lecturer and Director in the Centre for Speech Technology Research. He was also a co-founder and Chief Technical Officer at Rhetorical Systems. 

In fact, my prediction is that just the opposite will occur, and the field of linguistics will sooner or later cease to exist in its current form, and that the rigourous experimental, data-driven, formal, mathematical and statistical techniques developed in speech and language technology will be adopted and start to provide the answers to many of the long... 

Price, P., Luc, J. Using speech and language technology to coach reading. In Proc. HLT 01, Association for Computational Linguistics, pp. 1-2 (2001)... 

---