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

We built voice modulation to mask gender in technical interviews

blog.interviewing.io

Post reply on HN
Print view View original

41–50 of 369 posts

Re: We built voice modulation to mask gender in technical interviews

#41

Post by AndreyErmakov »

So we all realize technical interviews serve no practical purpose and should be quietly abandoned, but instead of looking into the future and discovering better ways of identifying talent, people keep inventing stuff that makes the torturing mechanism even more sophisticated so that the suffering can be prolonged.

I'd like to see the people behind this project apply their technical skills to something more useful to the industry and the society in general.

>> to get to pipeline parity, we actually have to increase the number of women studying computer science by an entire order of magnitude

Any woman who's gone through that process will likely want to get another career, that where people are treated with more respect. And I suppose many men are having the exact same thoughts.

The more you mock your talent pool, the more actively that talent is running in the opposite direction, just to get out of this mess.

Re: We built voice modulation to mask gender in technical interviews

#42

Post by jboy »

benkuhn wrote: post #15

I would really have liked to see them check whether the gender-blinding actually worked. Even if someone's voice is modulated, they may have gendered behavior patterns that could influence someone's performance ratings. I wouldn't be surprised if I could guess the gender of a voice-modulated person pretty accurately from other cues. To combat this, they could have asked the interviewer during the performance assessme…

I think it would be amazing if they could combine this voice-modulation technology with a facial motion capture technology (like in Avatar) to display artificial/shifting faces as well as voices. You could effectively create a computer screen-based version of the "scramble suit" used in A Scanner Darkly! http://www.imdb.com/title/tt0405296/mediaviewer/rm1872861440

I think a combined face+voice system would be even more useful in interviews (since a significant amount of human communication is expressed through facial cues). It would also add another dimension to your proposed voice-modulation gender-blinding experiment.

Re: We built voice modulation to mask gender in technical interviews

#43

Post by dogma1138 »

StavrosK wrote: post #11
vonmoltke wrote: post #7

Earlier quoted context omitted.

The point of the experiment was for the interviewer to think the interviewer was a particular gender to see if they as it based on that impression. Making everyone sound like a robot does not accomplish that goal, so I don't see how it makes the title more accurate.

It makes everyone sound the same. Changing only women's voices is a tell-tale sign. If you get a guy who sounds "computery", or "off", it's a girl.

Did you read the article? They changed both males and females, and had 2 control groups (one that was modulated without gender change, and 1 that was unmodulated).

This is by far one of the best ways to do it.

Re: We built voice modulation to mask gender in technical interviews

#44

Post by kylestlb »

yanilkr wrote: post #35

Sweet that some one is trying new things with ideas. But Oh boy, Life does not revolve around tech interviews. Make peace with it. An old school psychologist would observe us and say that the people obsessed with tech interviews faced an emotional toll of rejection during early career and are trying to get over it. Google, Facebook and other companies are like parents of the tech kids and the kids are seeking some ki…

Maybe interviewing is over-important because of the frequency in which tech workers/engineers change jobs.

Re: We built voice modulation to mask gender in technical interviews

#45

Post by qq66 »

Kevin_S wrote: post #38
ranko wrote: post #34

Gender blinding in orchestral auditions (which usually involves screening the performers from sight and thus is pretty-much foolproof) has been shown to improve the percentage of women who are hired. See, for example, 'Orchestrating Impartiality: The Impact of "Blind" Auditions on Female Musicians', Claudia Goldin, Cecilia Rouse: http://www.nber.org/papers/w5903

That's interesting, I would have thought being able to see actual finger movements to analyze mechanics is a part of the evaluation process. Could be totally off base though I suppose.

Good mechanics are a given at that level of performance. If you can play like Yo-Yo Ma with bad mechanics, more power to you, an orchestra is not going to care.

Re: We built voice modulation to mask gender in technical interviews

#46

Post by Karunamon »

minimaxir wrote: post #26
StavrosK wrote: post #13

Earlier quoted context omitted.

The interviewer is the one grading the interviewee.

Right, which highlights another problem: interview.io's interviewers are presumably trained to be more objective and stringent on the criteria. This may introduce a selection bias. Untrained interviewers, like the ones at startups randomly pulled into interviews and also hiring for culture fit , may have a bias that is more conscious.

>interview.io's interviewers are presumably trained to be more objective and stringent on the criteria.

The common thought is that bias is an unconscious and unavoidable thing, hence the voice masking. If that's truly the case, all the training in the world doesn't help.

Re: We built voice modulation to mask gender in technical interviews

#47

Post by MasterScrat »

jsprogrammer wrote: post #40
Jemmeh wrote: post #25

Earlier quoted context omitted.

This would be a fantastic additional thing to monitor for. It was my first thought after hearing the voice modulation clips-- even in a manly voice, someone saying, "Oh I totally sound like a dude" sounded quite feminine since most guys wouldn't say "totally." Two things I noticed from the clip on the FastCompany article-- it's modulated, but I can hear A.) Vocal Fry B.) Statements that sound like they're ending with…

What evidence do you have that some speaking patterns are more common with women? Can you link to some data? Edit: Lots of opinions here. Still no data.

I don't know about cues in spoken English, but you can find relevant articles about written text from this page:

https://civic.mit.edu/blog/natematias/best-practices-for-eth...

Read under "Inferring Gender from Content".

Re: We built voice modulation to mask gender in technical interviews

#48

Post by blisterpeanuts »

"...it appeared that men who were modulated to sound like women did a bit better than unmodulated men and that women who were modulated to sound like men did a bit worse than unmodulated women..."

The author admits it's not statistically significant, but nonetheless it somewhat makes sense, if you take human nature into account.

If there's any bias in the technology field, it's probably that males are assumed "smarter", but women are still liked and desired.

So, if a female is not answering questions as sharply, but is masked as a male, the bias is to deduct extra points. If a male is answering Q's while masked as a female, the interviewer is pleased and awards extra points.

Just my theory, but it seems to fit. Again, though... a very small sampling.

Re: We built voice modulation to mask gender in technical interviews

#49

Post by smokeyj »

I'd be more interested in quantifying productivity and seeing if there's a systematic discrepancy between productivity and gender. Either the market is accurately pricing talent or there's a delta to be exploited.

I think if a paper was released tomorrow that said "female programmers 30% undervalued as observed by double blind coding challenge" head hunters would fix that problem overnight.

Re: We built voice modulation to mask gender in technical interviews

#50

Post by windust »

jsprogrammer wrote: post #40
Jemmeh wrote: post #25

Earlier quoted context omitted.

This would be a fantastic additional thing to monitor for. It was my first thought after hearing the voice modulation clips-- even in a manly voice, someone saying, "Oh I totally sound like a dude" sounded quite feminine since most guys wouldn't say "totally." Two things I noticed from the clip on the FastCompany article-- it's modulated, but I can hear A.) Vocal Fry B.) Statements that sound like they're ending with…

What evidence do you have that some speaking patterns are more common with women? Can you link to some data? Edit: Lots of opinions here. Still no data.

not quite patterns, but preferences :)

https://blog.xkcd.com/2010/05/03/color-survey-results/

Post reply on HN