Hunt and Black

[Dimitra L]

The system Hunt and Black are describing in the paper is actually the implementation of IFF ?

[Simon]

Hunt & Black use a combination of IFF and ASF target costs – see Section 2.2 of the paper.

[Yuchen F]

Hi, I am still confused about this question.

1. For the ASR part, I can’t find any evidence except feature vector. But it is vague since the features can be linguistic features or acoustic features.

2. In the IFF part, are all the features they described belonging to linguistic features? I am wondering if point of articulation is an acoustic feature. Could you tell me more specific definitions of acoustic features and linguistic features?

3. When using the combination of IFF and ASF, should we assign weights to both acoustic features and linguistic features?

Thanks!

[Korin Richmond]

1. For the ASF features – pitch, power and duration are mentioned (“…each target phoneme has a target pitch, power and duration”)

2. Yes, place of articulation is indeed a linguistic (i.e. articulatory phonetic) feature – it’s a property of a *phone*, which is a linguistic *concept* rather than a physically measurable signal, for example. In contrast, the f0 or power or duration used as ASF feature are something you can directly observe and measure in the acoustic signal (or derivations thereof).

3. Yes, when combining different subcosts (e.g. ASF and/or IFF ones) we would typically want to weight them, so we can balance their influence in the overall cost.

[Author]

Posts