Comment by crazygringo
6 years ago
I was very curious to see how this sounded.
They did a "great" job... for me, it's exactly ambiguous between a high-pitched male voice and a deep-pitched female voice. It's like the old "is it a vase or two faces?" illusion, or "which way is the ballerina spinning?" It keeps flipping in my brain.
But for the same reason, I would never choose it because it sounds so out-of-the-ordinary, an extreme outlier for human voices. When a computerized voice is speaking, I want it to sound "natural" (e.g. common, unexceptional) so that I'm paying attention to the message, not the voice.
Unfortunately a single "gender-neutral" voice turns out to sound quite uncommon, very exceptional. I only know a couple of people who sound like that, out of 1000's. I applaud the intention, but unfortunately I don't think it works in the end.
Regularly or randomly alternating between "average" female and male voices feels like perhaps a better practical solution, matching the two "humps" in the bimodal distribution of actual voice frequencies. [1]
To be honest, it’s not really all that unusual once you start paying attention to it — plenty of women have deeper voices than mine.
I transitioned from male to female some years back and trained my voice from a deep, masculine voice to one solidly in the female range. Pitch is only one aspect of how we gender speech, and I think that’s why it feels off to you.
I would say this voice uses pretty male-coded speech patterns with a higher pitch than you’d normally hear a man speak in. The pattern of clear starts and stops between words and limited range of pitch used sounds “male” to my ears.
>> The pattern of clear starts and stops between words and limited range of pitch used sounds “male” to my ears.
This sounds like an exaggerated stereotype of how men speak. Interestingly, the stereotype is different for men from Southern European countries who are said to speak in a sing-songy voice with vowels flowing together between words like vocal ligatures.
For example, this stereotype is used for satirical effect in the following strip:
https://pbfcomics.com/comics/automatic-business/
I wouldn’t say it’s particularly exaggerated; the “gay voice” is basically male pitch ranges with stereotypically feminine prosody and/or alliteration (I don’t say this as a mockery at all; there’s a documentary on Netflix that goes into the origins of this).
Though I do agree that gender norms are largely cultural — but it doesn’t change the fact that a Spanish man sounds “gay” to most Americans.
5 replies →
I'd guess you're noticing voices a lot more because of your efforts. I don't really notice at all, possibly because I'm not paying attention. I wonder if I heard the Q voice in normal usage (like on a phone system) I'd notice?
I’d actually be interested to see how it performs under heavy voice compression (such as a phone system).
Piggybacking this comment to say, has no one noticed that you can drag the little bubble around to adjust the frequency of the voice? It defaults to 153Hz, and varies about 145-175Hz. Which indeed does seem to be right in the middle, but with the 153Hz being more on the "Male" end to be honest.
I had noticed it, but the voice sounds female to me even when dragging the bubble way down into the "male" region.
Dragging it all the way down left sounds like a woman with a deep voice.
I agree and I don't really see the value in making this a battlefield. Pick a male or female voice, whatever you like best.
Having an AI-voice sound artificial could be an advantage in certain situation but I doubt that was the goal here.