HQSYN16

We have proposed a 2-stage iterative correction procedure:
1) The correction of phrase boundaries by the detection/correction of pauses, it also includes a correction of the neighboring phones, e.g. changes of the voicedness, insertion/deletion of glottal stops etc.
2) The correction of the phrase type (prosodeme).
The properties of speech are modeled by hidden Markov models with large context description.

Trochu jsem to upravil a zkrátil. Je to OK?

We have proposed a 2-stage iterative speech corpus prosodic annotation correction procedure based on HMMs with large context description: (i) correction of phrase boundaries by the detection/correction of pauses (including also a correction of neighboring phones, e.g. changes of voicedness, insertion/deletion of glottal stops, etc.; (ii) correction of the phrase (prosodeme) type.

Ano. Takle je to perfektní.