Interactive toy demo

Whilst the video is playing, click on a line in the transcript to play the video from that point.
00:0500:07 Before getting into all the details, let's just play with some unit selection.
00:0700:15 Here's a interactive example. You can find it on the website speech.zone.
00:1500:28 We're going to try and synthesize my name and so I've found the appropriate diphones from a database. I've used one of the Arctic databases for this, and I've just pulled out a few candidates for each target position.
00:2800:56 So, along the bottom there we have the target diphone sequence, and above it we have the candidates. Each of these candidates is just a little waveform fragment. So, we can listen to those and, to say my name, we need to pick one candidate from each column.
00:5601:20 So, for example ... This is interactive, so if we select ... those will synthesize the waveform. This one this one all of those ones.
01:2001:24 There are many other sequences we can try. Have a go for yourself.
01:2401:54 Try another sequence. I've labeled each of the candidates with the utterance that it comes from, and I've also made sure that any candidates coming from the same utterance were contiguous in that utterance.
01:5402:12 For example, these all came contiguously. And so on.
02:1202:16 See if you can find the best sequence out of all the possible sequences.
02:1602:20 Now, in a real system we can't do this interactively with listeners.
02:2002:38 We have to automate it. We need criteria for choosing between the different candidates for each target position. We also need to decide how well they might concatenate. We're going to see that knowing if units were contiguous in the original database could be very helpful.
02:3802:40 Because, of course we expect those to join perfectly.
02:4002:44 In fact, we won't even cut them up. We'll take them as a larger unit.
02:4402:49 So, I'd like you to go and play with this interactive example and then continue watching the videos.