Slashdot Mirror

← Back to Stories (view on slashdot.org)

Your Computer As Your Singing Coach

Posted by timothy on from the but-my-computer-already-is-my-singing-coach dept.

Roland Piquepaille writes "Israeli researchers have developed an electronic ear to coach vibrato technique. Until now, the quality of a vibrato — the pulsating change of pitch in a singer's voice — could only be judged by voice experts. Now, a Tel Aviv University research team 'has successfully managed to train a computer to rate vibrato quality, and has created an application based on biofeedback to help singers improve their technique.' Interestingly, this research could be used for other applications, such as improving automated help centers, where computers could be trained 'to recognize a range of different emotions, such as anger and nervousness.'"

7 of 127 comments (clear)

  1. new? by JazzyMusicMan · · Score: 2, Interesting

    How is this technology new? I remember hearing many many years ago that they had developed gadgets that you could attach to your phone that could more or less sense if a person was nervous or not and could even function as a lie detector. These devices were probably pretty primitive, and their claims of being able to be used to spot when someone was lying to you were probably a little over the top, however, this technology doesn't strike me as new.

  2. Re:cheaters! by Tirno · · Score: 2, Interesting

    Well, as a cellist, I can say that vibrato definitely has pleasing effect on the ear, and allows for extra expressiveness (through varying types of vibrato, fast/slow, wide/narrow, etc.). And you can't fake intonation, vibrato or not. Of course, I'm no expert in vocal music, but I would think the idea is similar.

  3. Truly impressive by javaman235 · · Score: 4, Interesting

    ...every programmer should work with something like this at least once. I did some audio programming work in college, and its a totally different world than the regular web dev stuff I have done, because you're working with the convergence of acoustics and physics with programming. In true signal processing apps, what you are doing has to happen FAST as well, which makes the guys who work in it true wizards, and that's without even considering the subjective recognition stuff that these researchers had to do. Kudos to them.

    --
    -The art of programming is the pursuit of absolute simplicity.
    1. Re:Truly impressive by jonaskoelker · · Score: 2, Interesting

      every programmer should work with something like this at least once

      Agreed. My pet project of this sort is a wiimote hack, whereby you can play music with the wiimote. And no, it isn't just playing loops, it's indicating a tone with the angle of the wiimote (and nunchuck).

      So, it's really simple, right?
      - You steal the code that gives you the vertical angle of the wiimote from wmgui,
      - quantize it to [-12, 12],
      - raises the twelfth root of two to that power (or do a lookup into a temperament table),
      - multiply it onto the base frequency (say, 441 Hz),
      - generate a wave of that frequency,
      - copy it to the sound card (or the wiimote speaker, if your library supports it).

      Right.

      + Now add two more tones generated similarly; how do you mix them without sounding like shit?
      + Also, when making a wave, you want to start at the last seen elongation to avoid clicky noises.
      + When stopping a wave, you want to cheat and continue the wave with constant frequency until the elongation hits zero, again to avoid clicky noises.
      + And this is assuming that the transfer delay from the wiimote to your code (and from there to the sound card) is essentially zero. Now make some good use of the timestamp value on wiimote events; say, having a fixed small delay on everything.
      + Oh, and minimize battery usage please ;)

      It's an interesting project, to say the least. So far I've learned that I know and remember the necessary bits of physics and music theory; I haven't the faintest clue about the psychology of auditory perception and what would be a reasonable delay, but I can use myself as a test subject.

      I'd recommend doing something like this to everyone who has a wiimote and a bluetooth interface on their box. And if you don't have a wii, buy a wiimote anyways: it's great fun playing tetris, kobo deluxe, mu-cade and other arcade'ish games with a game controller. Especially on the university's big projector screens. Instead of studying.

  4. Re:cheaters! by mrbluze · · Score: 2, Interesting

    Seriously, just pick a note and sing it. What's so wrong about that?

    Many a good choir is ruined by people who sing vibrato. Once a singer learns it, their voice is rarely if ever 'natural' again and many great (usually early) choral works cannot be sung properly.

    --
    Do it yourself, because no one else will do it yourself. [beta blockade 10-17 Feb]
  5. Re:cheaters! by Anonymous Coward · · Score: 2, Interesting

    Many choir directors have a certain conception of good choral singing. This often includes straight toning (singing without vibrato), unnatural vowel modifications to reduce 'brightness', and a number of other things which are foreign to trained singers. More than anything else, these methods are designed to compensate for poor individual voices. If you listen to the early work of the Robert Shaw chorale, particularly his collaborations with Toscanini, it is clear that his choir consists of professional voices singing with a full and truly magnificent vibrant sound, and that the individual singers have vibrato. They also have full and balanced sounds unlike many choirs which by applying the aforementioned choral techniques have an imbalanced sound with insufficient higher-frequency harmonics (in the 2,800 - 4,500 Hz range).

    Many choral directors and choristers in these sorts of choirs make the further mistake of believing that the singing technique that they are using for their choral singing is appropriate for good solo singing. Many young voices have been damaged by following through on this disastrous line of thinking.

    I would also question your use of 'natural', as though this is the ideal. 'Naturally', most tenors for example cannot sing higher than about F#4 and the range between about C#4 and F#4 is marked by a 'shouty' quality that is wholly inconsistent with the rest of the voice. To sing the literature, which regularly goes above F#4, they generally have to resort to the 'unnatural' practice of training and proper vocal technique.

  6. Re:Machine vs. Human by dodecalogue · · Score: 2, Interesting

    I haven't RTFA (never do) but it would be interesting if the biofeedback somehow encouraged you in directions that you felt pleased with. That's the general kind of trajectory I think of when I think of "feedback", so it would make sense in that regards. I'm not sure how that would work, maybe encouraging you when you felt good about your results.

    I just don't understand these singing competitions, their appraisals seem totally random. I've sang in a bunch of choirs and worked on the open vowels and proper articulation, but I prefer the Lou Reed/Leonard Cohen school of singing.