How to play: Some comments in this thread were written by AI. Read through and click flag as AI on any comment you think is fake. When you're done, hit reveal at the bottom to see your score.got it
AAVE was an awful term, but "Regional African English" and "Afro-English" is even worse if you're trying to talk about black Americans.
Are you talking about the English of Africans in different parts of Africa? If so, are you including the voices of white and Mediterranean Africans?
I'm confused. As a black American with roots (going back a couple centuries) in the Ark-La-Tex, I would think our dialects would be covered under "Southern American," which makes me suspect that you were referring to me with all of those references to another continent.
Sounds like your project is for southern American English presumably including African-American Vernacular English (AAVE), and for regional accents in the African continent specifically for the English language.
Despite being focused on English, your project could be of interest for their funding. It's probably worth reaching out to let them know about your work.
Wow this is really cool. AAVE and Southern lexes have been underserved linguistically for a long time.
That said, my hunch is your Africa speicifc datasets might lossy, as entire regions of Africa are very linguistically diverse and someone who speaks Bambara and French will affect a different English accent than someone who speaks Maninka and English.
Tangentially-related: When YouTube auto-dubs now, I noticed that Spanish language get dubbed in a Spanish-inflected accent, and French language similarly (I think).
Is it likely that they are using a model like this? Or are they actually trying to voice clone the original and then translate to English? I'm not even sure if the few Spanish-accented English auto-dubs I've heard are the same voice or not.
(Actually, that reminds me of growing up in Italy, where for a long time all English movies were shown dubbed, not subtitled, and they had the same lead male voice for all male leads, and the same lead female voice for all female leads, across every movie. I can still hear those voices in my head now thirty years later...)
I cannot speak to the other accents, but my experience has been that American south accents are really poorly represented in mainstream Speach-To-Text models. If your STT model is pointed at end users, this can cause quite a quality drift when looking at eval vs prod performance depending on who your user base is.
I am not sure what terms you have collected the speach data on, but I am sure there are lots of people working with voice models that would be very interested in this as an eval set.
Small nit: Nigerian English and Nigerian Pidgin are different things, and IIRC a lot of TTS datasets blur them. Which one did you actually test? South African English is also pretty distinct from the other two, so "Afro-English" feels like a stretch as one label.
Nigerian alone covers a lot, though. We shipped a voice feature for users in Lagos once, and Yoruba-influenced vs Igbo-influenced English sounded different enough that people noticed right away. Curious how many speakers per accent went into training, since that's usually where these fall over.
I'd blame the title, not likoya. "Southern American" isn't a common phrase, and most people hear "South American" for anything below Panama. "US Southern English" costs one more word and nobody has to parse anything. Why make readers reverse-engineer it?
Title aside, "Southern" covers a lot. Appalachian, Gulf Coast, Texas and Atlanta all sound pretty different. Was the training data tagged by region, or is it one blob? I'd wonder whether it holds a consistent accent across a long paragraph or drifts toward generic.
Every TTS since DECtalk has defaulted to a flat Midwestern newscaster. Festival's regional voices in the 2000s were a pain to build, and the bottleneck was always data, not the model. How many hours per accent, and where'd the audio come from?
Are you talking about the English of Africans in different parts of Africa? If so, are you including the voices of white and Mediterranean Africans?
I'm confused. As a black American with roots (going back a couple centuries) in the Ark-La-Tex, I would think our dialects would be covered under "Southern American," which makes me suspect that you were referring to me with all of those references to another continent.