Why is a smaller inventory good?

[ann]

Hi,

I was looking at the slides for the module 3, 4 and 5 videos. On page 60, it said that an advantage of having a smaller inventory of units is that there would be a ‘smaller set of possible unit type sequences for any given utterance to be synthesised (possibly a unique sequence; e.g., phonemes, diphones)’. Could you please explain why this is desired?

Thanks

[Simon]

This slide is talking about the most basic form waveform concatenation synthesis in which we store only one example of each unit type:

inventory = the set of stored waveform units

• using phonemes as the type would require only around 45 stored waveform units
• diphones would require ~2000 stored waveform units
• and so on …. larger unit sizes generally have more types

But similar arguments apply to unit selection:

inventory = the set of unique unit types

database = the stored waveforms (usually complete natural utterances) from which units are selected; multiple instances of each unit type are available

Unit selection involves search all possible candidate unit sequences to find the best-sounding sequence. Even using dynamic programming, this will involve significant computation.

As the database of speech to draw candidates from increases in size, the number of available candidates increases in proportion, but the number of possible sequences increases exponentially.

[Author]

Posts