The Story of Speech Synthesis: From Talking Tubes to Neural Networks, Part 1/3

chris

What would we do without the helpful voices in our GPS systems guiding us to our destinations? How would we look up esoteric facts without the silky voices of the virtual assistants on our phones? And how would we remember our belongings as we leave the train without a considerate voice reminding us to do so? Artificial voices suffuse our day-to-day worlds and fulfill practical functions, but where do these voices come from, and how do you ‘synthesise’ speech?

    The first stones of the story of speech synthesis were laid over 200 years ago where mechanical devices produced speech sounds by emulating the complex structure of the human articulatory system. Technological innovations in the early 20th century then allowed for

Can sounds have meaning? The peculiar case of West-Flemish tj and dj

Unknown 10 1

As linguists, we investigate all sorts of building bocks of language, such as sentences, predicates, prefixes and suffixes, and even individual sounds like p and z. Most of these building blocks have some kind of meaning. For example, a sentence like The cat sat on the mat means something, a predicate like is crazy in John is crazy means something, and even prefixes and suffixes mean something, such as pre- in pre-heated, which means something like ‘done in advance’, so that pre-heated means ‘heated in advance’. But, you may ask, do sounds like p and z also have meaning?

We know that sounds may distinguish meaning, but it is not so obvious that they have meaning. For example, …