Accessible open textbooks in math-heavy disciplines

> Switch the language on foreign terms and names so that screen readers can pronounce them in the right voice.

Screen reader user here. Don't actually do this, this is bad advice.

Just like a lecturer won't suddenly switch to a German accent when saying words like "schadenfreude" or names like "Friedrich Nietzsche", neither should a screen reader. Having your voice constantly change under you for no apparent reason is distracting more than anything else.

What you should do this for are longer pieces of text in a foreign language, like a multi-paragraph piece of text to analyze in a foreign language textbook.

A lecturer who is fluently multilingual might indeed smoothly switch accents when pronouncing foreign words. But it's still the same voice, and (if they're well practiced at it) they don't have to pause in mid-sentence to switch languages, as text-to-speech systems usually do. And eSpeak can switch languages while still being the same voice, since it's a rule-based, parametric synthesizer. But, at least with NVDA, a mid-sentence HTML span with a different lang attribute still causes a (short) break in the intonation on either side. That's too bad, because a multilingual parametric synthesizer like eSpeak could be like the ultimate polyglot speaker, impressing us all with how smoothly it switches languages.

Out of curiosity, are there models for speech synthesis which generate speech parametrically and then refine neurally?