TTS · 30% of the score · optional
The least-solved piece of the stack. No dominant Cantonese voice exists, and the reasons are structural rather than a matter of more training data.
Recognition has to tell 6 tones apart. Synthesis has to make them distinguishable in the first place, and the ways that fails do not show up as a bad word — they show up as a voice a Hong Kong listener does not trust. These are the four we hear most.
婦 fu5 → 父 fu6
Low rising collapses into low level under fast speech or at the end of a phrase.
Wife becomes father. The sentence stays fluent and the person changes, and on a call that names a beneficiary there is no context to repair it from.
沒有 → 冇
Output is grammatical Standard Written Chinese pronounced in Cantonese, rather than spoken Cantonese.
Every sentence is correct and nobody talks like that. It is the single most common way a synthesised Hong Kong voice announces itself as one.
你個 claim 已經 approve 咗
The English words are produced with English stress and timing, so the sentence audibly changes speaker mid-phrase.
Hong Kong speakers switch constantly and smoothly. A seam here is more noticeable than a wrong word.
HK 七三二一四五
Numbers read with uniform timing and no grouping, or with the wrong tone on 一 and 七.
A policy number that has to be said twice is a call that takes twice as long, and the caller writes it down wrong the first time.
None of this is captured by asking “does it sound natural?” alone, which is why naturalness and intelligibility are rated separately and why a tonal check runs alongside both. A warm voice that flattens tone five is worse on a claims line than a robotic one that does not.
Naturalness and intelligibility, rated separately by native listeners. They diverge: a flat voice can be perfectly clear, and a warm one can still mangle a policy number.
Minimal pairs such as 買/賣 and 保/報 are synthesised and read back by a recogniser: did the tone that changes the meaning survive.
Did audio arrive, at a plausible length and level, unclipped, inside the deadline. From the Online Challenge it is shown beside the human judgement and not counted.