Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Removing 'um' from a recording is harder than it sounds

doug.sh

Post reply on HN
Print view View original

91–96 of 96 posts

Re: Removing 'um' from a recording is harder than it sounds

#91

Post by BobbyTables2 »

wzdd wrote: post #10

It’s a nice engineering approach, but I’m interested in the motivation. Um and ah is distracting in a transcript, where you can naturally pause to take in information; in speech however it can serve as a focusing point to indicate the next part is important. See https://medium.com/better-humans/dont-worry-about-saying-um-... for example. The weirdly obsessive zeal that orgs like Toastmasters have about eliminating th…

An occasional “um” is one thing. But utterly exhausting when every response in an interview starts with it…

Re: Removing 'um' from a recording is harder than it sounds

#92

Post by BobbyTables2 »

skrebbel wrote: post #37
bluebarbet wrote: post #36

Earlier quoted context omitted.

The most popular academic theory (IIRC) is that "um" and "uh" are conversational placeholders that say, "don't talk, I'm not finished speaking yet". Which obviously serves no purpose in a monologue. To me they just indicate lack of confidence on the part of the speaker.

There's a correlation between speaking with confidence and bullshitting / corner cutting. Hard, nuanced questions require more thinking time to produce a nuanced answer. But a bullshitter will just confidently answer subtly wrong stuff. But they won't say "uh"! Is that really better?

The gifted ones seem to manage to intelligently babble for the beginning part while simultaneously forming the real answer.

Re: Removing 'um' from a recording is harder than it sounds

#93

Post by thaumasiotes »

Izkata wrote: post #83
thaumasiotes wrote: post #28

Earlier quoted context omitted.

>> It leaves um, uh, er and elongated versions ( ummmm, uhhhhh ) alone. Something's already gone wrong here. Uh and er refer to the same sound. Uh is the American spelling. Er is British; to them a following "r" like that is just a kind of vowel.

"Er" is definitely distinct as an interjection, it's usually used instead of "um" to indicate a correction and does sound different.

Are you claiming that a rhotic "er" exists in American English, or that the British particle "er" is distinct from the British particle "erm"?

> it's usually used instead of "um" to indicate a correction and does sound different

Obviously people can hear the difference between vocalizing with your mouth open and vocalizing with your mouth closed. But there is no systematic difference in use, similarly to how there is no systematic difference in use between "uh-huh" and "mhm".

Re: Removing 'um' from a recording is harder than it sounds

#94

Post by watchlight »

Transcription is a portion of my own pipeline, and I was a bit surprised to learn at how many of the short words were cut out as a result of VAD (voice activity detection) being overly sensitive. It wasn't like the models were bad, rather just the activity detection wasn't tuned correctly for background noise. The start and end of words would also occasionally get truncated, "um" and "uh" just often happen to be something that folks mutter. They're sufficiently short that the blips aren't considered "real enough speech" to get flagged.

Faster-whisper does allow for VAD tuning via API. I don't think it's exposed natively for Whisper though.

Re: Removing 'um' from a recording is harder than it sounds

#95

Post by Izkata »

thaumasiotes wrote: post #93
Izkata wrote: post #83

Earlier quoted context omitted.

"Er" is definitely distinct as an interjection, it's usually used instead of "um" to indicate a correction and does sound different.

Are you claiming that a rhotic "er" exists in American English, or that the British particle "er" is distinct from the British particle "erm"? > it's usually used instead of "um" to indicate a correction and does sound different Obviously people can hear the difference between vocalizing with your mouth open and vocalizing with your mouth closed. But there is no systematic difference in use, similarly to how there is…

> Are you claiming that a rhotic "er" exists in American English, or that the British particle "er" is distinct from the British particle "erm"?

Neither. In Amrican English we're fully pronouncing the "r" when we say "er" instead of "um".

> Obviously people can hear the difference between vocalizing with your mouth open and vocalizing with your mouth closed.

That would be "uh" vs "um", not "er".

Re: Removing 'um' from a recording is harder than it sounds

#96

Post by CGMthrowaway »

wzdd wrote: post #10

It’s a nice engineering approach, but I’m interested in the motivation. Um and ah is distracting in a transcript, where you can naturally pause to take in information; in speech however it can serve as a focusing point to indicate the next part is important. See https://medium.com/better-humans/dont-worry-about-saying-um-... for example. The weirdly obsessive zeal that orgs like Toastmasters have about eliminating th…

You are almost certainly listening to a lot of audio with um's and ah's removed from it, without even realizing it. Via various methods including automated, manual, direction (re-takes), and talent-led (speaker consciously suppressing).

If you knew how much, you might not feel the same way.

Post reply on HN