In this episode of Future Tense, reporter Jon Gordon takes a look at Vocaloid, a music software that synthesizes human voice to produce musical results.
In this episode of Future Tense, reporter Jon Gordon takes a look at Vocaloid, a music software that synthesizes human voice to produce musical results.
JON GORDON: And on lead vocals, a piece of software? This is Future Tense from American Public Media. I'm Jon Gordon. Vocaloid is a software package that turns your lyrics and musical notes into a song with synthesized vocals. You can choose from three singers, Lola, Miriam, and Leon. The software taps a library of vocal performances from three real singers, so it produces songs that sound somewhat realistic.
[ELECTRONIC MUSIC]
(SINGING) Sing to me baby
When you're alone
When you're alone
Yeah check it out
Be on the floor now
Brent Hoover is a Los Angeles area musician who reviewed Vocaloid in the online publication distributed by electronic music gear retailer Audiomidi.com He says Vocaloid is an interesting product, but ultimately falls short.
BRENT HOOVER: It comes really, really close. But the way it is with people hearing a voice, close is not good enough. It just doesn't sound as if the machine understands the words that it's saying.
JON GORDON: Which, of course it doesn't.
BRENT HOOVER: Which, of course it doesn't. But supposedly, you could manipulate it so that it would seem like it does. But either I don't understand enough about how that's done, or it doesn't understand enough about how it's done.
JON GORDON: So yes, it doesn't sound perfectly real yet, but do you think it has any uses in the world of music?
BRENT HOOVER: The main thing is to try to look at it differently, as if, OK, it doesn't sound like a real person, but it talks, and it sings. And that's an interesting phenomenon all in itself. And yet, it doesn't sound exactly like a real person, but maybe that's good. What if you were to have this other sort of entity singing?
(SINGING) My name is Lola
Lola Uh-huh
I need to do for you
Lola Uh-huh
Anything you want me to
Lola
Baby what you want to hear
Lola
And I'll be there for you
Because it's very-- I mean, it's very intelligible. It isn't like a vocoder, that sort of an effect. I mean, you could definitely get it to say and sing things that you could understand. And certainly, for somebody who can't sing at all, which I'm close to, but for somebody who can't sing at all, it would be a way to get that out of your heart, to express that without being able to sing.
JON GORDON: If this technology were perfected, could that be a really bad thing for music?
BRENT HOOVER: I personally would say no. I mean, everybody says that every advent of the sampler or a recording is the end of civilization as we know it in terms of music expression. And in my opinion, it's all good. Because the more you can get where people-- the closer you can get where I can just visualize an idea, a musical idea, in my head, and it happens, the better off we are. And I think that this is a tool that would bring you closer in that direction.
JON GORDON: Musician Brent Hoover reviewed Vocaloid for Audiomidi.com. Future Tense is online at futuretenseweb.org. I'm Jon Gordon.
(SINGING) I'm hurting to be with you tonight baby
I'll never let you out of my life baby yeah.
You don't you give up on me baby
Oh yeah baby
Never give up
Don't give up on me baby
Don't give up on me baby
Don't give up on me baby
Don't give up on me baby yeah
[ELECTRONIC MUSIC]
Views and opinions expressed in the content do not represent the opinions of APMG. APMG is not responsible for objectionable content and language represented on the site. Please use the "Contact Us" button if you'd like to report a piece of content. Thank you.
Transcriptions provided are machine generated, and while APMG makes the best effort for accuracy, mistakes will happen. Please excuse these errors and use the "Contact Us" button if you'd like to report an error. Thank you.