The sound samples were horrible. I couldn't understand the "singing" voice at all. I think this would be more distracting due to the uncanny valley ("Was that directions or road noise or the actual song?").
As the author, I certainly agree that this isn't useful yet in anything like its current form.
Intelligibility was one of my biggest concerns while making the hack: singing can be harder to understand than speech. On the other hand, the vocabulary is limited. Phrases like "turn left" and "turn right" are easily distinguishable, and other unobtrusive audio cues could make it clear that the words came from the GPS. Over the course of the hack day, intelligibility improved dramatically as I tweaked parameters.
Mainly, this is an experiment, and there are lots of ways to improve on the first day's results to make it more practical. Instead of following the melody exactly, the pitches could be chosen from a limited range to be consonant with the song. That would split some of the difference between traditional GPS speech and these results. Also, Yamaha has apparently withheld their higher-quality Vocaloid voices from the free Canoris API, so there's potential for improvement there as well. (The documentation warns that the initial release of the free voices works better in Spanish.)
Even more practically, the GPS could use the timing information to slip in spoken directions at less distracting moments, like a human companion might.
>> Even more practically, the GPS could use the timing information to slip in spoken directions at less distracting moments, like a human companion might.
I really like that idea. Of course, the GPS tends to be a bit of a nag, so it might be hard for it to find enough pauses.
I don't have my GPS integrated with the car, so I can just let the GPS audio compete with the car audio, and adjust GPS volume to mess with the intrusiveness factor. After listening to the original sample... wow that would annoy me a lot.
Definitely agree. Even if there was a normal sounding human voice, people generally don't sing driving instructions to each other. If you're going to deliver driving instructions using a speaking voice, it's probably best to turn down the music prior to listening to it.
It does sound uncanny, but has potential to be awesome. The issue isn't the pitch bend but the synthetic voice. Auto-tune the news is pretty awesome, for example.
I really like the new Jaguar XJ (not that I've driven it, but I've seen pictures) where the dials in front of you are a screen, and when you approach a turn one of the low-priority dials (fuel and temperature, I guess) becomes a little round GPS screen to tell you which way to go.
