Live data from Hacker News

Accents in latent spaces: How AI hears accent strength in English

accent-strength.boldvoice.com

81–90 of 131 posts

Re: Accents in latent spaces: How AI hears accent strength in English

#81
post #43

Like others recently, I've been extremely impressed by LLM's ability to play GeoGuessr, or, more generally, to geo-locate random snapshots that you give them, with what seem (to me) to be almost no context clues. (I gave ChatGPT loads of holiday snapshots, screenshotted to remove metadata, and it did amazingly.) I assume that, with enough training, we could get similarly accurate guesses of a person's linguistic hist…

We actually did something like this for non-native English speakers a few months back. Check out https://accentoracle.com (most mind-blowing if you're a non native English speaker)

Wow that was actually accurate

Re: Accents in latent spaces: How AI hears accent strength in English

#82
post #65

Victor's problem isn't really the vowels or pacing. The final consonants are soft or not really audible. I am not hearing the /ŋ/ of "long" as the most marked example. It sounds closer to "law". In his "improved" recording he hasn't fixed this. I sometimes see content on social media encouraging people to sound more native or improve their accent. But IMO it's perfectly ok to have an accent, as long as the speech mee…

Yeah, as long as it’s intelligible an accent is perfectly fine It’s also perfectly fine to want to sound like a native speaker - whether it be because they are self conscious, think it will benefit them in some way, or simply want to feel like they are speaking “correctly” Sorry to pick on you, it’s just amazing to me how sensitive we are to “inclusivity” to the point where we almost discourage people wanting to fit…

That kind of implies that there's a "correct" accent for English, even though many countries and regions natively speak it. Someone from Glasgow is just as much of a native speaker as someone from Los Angeles even though the accents are wildly different.

Re: Accents in latent spaces: How AI hears accent strength in English

#83

Victor's problem isn't really the vowels or pacing. The final consonants are soft or not really audible. I am not hearing the /ŋ/ of "long" as the most marked example. It sounds closer to "law". In his "improved" recording he hasn't fixed this. I sometimes see content on social media encouraging people to sound more native or improve their accent. But IMO it's perfectly ok to have an accent, as long as the speech mee…

It's fascinating that "long" is the biggest tip-off you have, given that Mandarin Chinese (based on the mention of "a noticeably strong Chinese accent") does have words that have the same IPA pronunciation (if you set aside tone) [0] as an American whose speech follows the cot-caught merger [1].

Meanwhile the thing that stood out to me in the initial recording were the vowel sounds: for instance, "young" sounded almost like it rhymed with "long" before training. (That makes sense, since Mandarin similarly has a word with that sound, as can be found in the common last name Yang [2].)

Incidentally, Mandarin has words that sound like "lung" (e.g. the word for "cold" [3]), but if you replace the "l" sound at the front with a "y" sound, depending on which of two transformations you use, it turns the vowel sound into a long o [4] (near rhyme with "lone"). (There is another transformation that you can use that results in a leading "y" in pinyin, but in that specific case, the vowel turns into a long e, and the "y" is largely silent (e.g. the word for "solid" [5]).)

In the last recording, Victor is clearly rushing through the sentence, and you can tell that where he previously had a clear "s" ending for the word "days", it's now slurred into a "th" sound. Agreed that that's actually a net negative for intelligibility.

The wiktionary links below have clips of pronunciation. I will note that not all native speakers have a Standard Chinese accent [6,7], so there are assuredly some differences in pronunciation to be expected depending on exactly which region said individual hails from.

[0] https://en.wiktionary.org/wiki/%E6%B5%AA

[1] https://en.wiktionary.org/wiki/long

[2] https://en.wiktionary.org/wiki/y%C3%A1ng#Mandarin

[3] https://en.wiktionary.org/wiki/%E5%86%B7

[4] https://en.wiktionary.org/wiki/%E7%94%A8

[5] https://en.wiktionary.org/wiki/%E7%A1%AC

[6] https://en.wikipedia.org/wiki/Standard_Chinese

[7] https://en.wikipedia.org/wiki/Help:IPA/Mandarin

Re: Accents in latent spaces: How AI hears accent strength in English

#84
post #6

Earlier quoted context omitted.

> something language learners have never had throughout all of human history .. unless they had access to a native speaker and/or vocal coach? While an automated Henry Higgins is nifty, it's not something humans haven't been able to do themselves.

Native speakers are less helpful at this than you might think. Speech coaches are absolutely the way to go, but they're outside the price range for most people ($200+/hr for a good coach). BoldVoice gives coach-level feedback and instruction at a price point that everyone can access, on demand.

You can take a language class rather than have a personal instructor. Although accents are a sensitive topic so I don't remember mine going into it much.

Re: Accents in latent spaces: How AI hears accent strength in English

#85

Oh pssh. There's no such thing as accent strength. There's only accent distance. Accent strength is just an artefact of distance from the accent of a socially dominant group.

> Accent strength is just ... distance from the accent of a socially dominant group. Yes, that is a good definition of accent strength. > There's no such thing as accent strength. ??! You literally just defined it.

Which "socially dominant group" would you pick in the United States? Or the UK?

Re: Accents in latent spaces: How AI hears accent strength in English

#86
post #74

Earlier quoted context omitted.

Being legible also means to cater to your audience. I work in an English-speaking company in a country where English isn't the native language, with loads of non-native speakers from around the world. Sometimes the native/best English speakers are the ones being misunderstood, because they use idioms or advanced words. None of us are bad at English, and I don't mean that I need to "dumb it down" (if anything, verball…

Generalizing from my own experience, it’s easier for me to understand a non-native Spanish speaker than a native Spanish speaker and I would guess that the same applies with ESL speakers. One thing I found really fascinating is that even though I’d never studied French¹, I actually had an easier time understanding a conversation between my ex-wife and her aunt in French than when they spoke Spanish in which I was fun…

>Generalizing from my own experience, it’s easier for me to understand a non-native Spanish speaker than a native Spanish speaker and I would guess that the same applies with ESL speakers.

You guessed right -- it's /usually/ easier to understand other non-native speakers, both because of accent and less idioms. That is unless the accent is really heavy and doesn't match your own.

Re: Accents in latent spaces: How AI hears accent strength in English

#87

Earlier quoted context omitted.

Native speakers are less helpful at this than you might think. Speech coaches are absolutely the way to go, but they're outside the price range for most people ($200+/hr for a good coach). BoldVoice gives coach-level feedback and instruction at a price point that everyone can access, on demand.

You can take a language class rather than have a personal instructor. Although accents are a sensitive topic so I don't remember mine going into it much.

As someone who took English classes for years growing up, I wish that were the case. In fact, most teachers don't really know how to teach pronunciation. Also, in a typical group class setting, it's challenging to give each student one-on-one feedback. On BoldVoice, we solve that with 1) unlimited instant feedback from sound-level AI - your most patient coach. 2) in-depth video lessons from the best coaches in the world (Hollywood accent coaches). I'm a cofounder of BoldVoice, by the way. :)

Re: Accents in latent spaces: How AI hears accent strength in English

#88

Earlier quoted context omitted.

Native speakers are less helpful at this than you might think. Speech coaches are absolutely the way to go, but they're outside the price range for most people ($200+/hr for a good coach). BoldVoice gives coach-level feedback and instruction at a price point that everyone can access, on demand.

You can take a language class rather than have a personal instructor. Although accents are a sensitive topic so I don't remember mine going into it much.

Language class and accent coaching are very different things.

Re: Accents in latent spaces: How AI hears accent strength in English

#89
Scammers around here calling me saying my tax number is blocked will be happy to mask their accent with the one they are supposed to have. They will probably buy a premium subscription for this too.

Best kind of AI in the best kind of a free market.

Re: Accents in latent spaces: How AI hears accent strength in English

#90

Victor's problem isn't really the vowels or pacing. The final consonants are soft or not really audible. I am not hearing the /ŋ/ of "long" as the most marked example. It sounds closer to "law". In his "improved" recording he hasn't fixed this. I sometimes see content on social media encouraging people to sound more native or improve their accent. But IMO it's perfectly ok to have an accent, as long as the speech mee…

A very important part of people trusting you is them being able to understand what you say without making extra efforts compared to a native speaker.

An easy way to improve intonation and fluency is to imitate a native speaker. Copying things like the intervocalic T and D is a consequence of that. It would be easier for a native Spanish speaker to say the Spanish /t/ and /d/ but intonation and fluency would be impaired.

The sounds don't "flow" as they should.

Post reply on HN