Method and configuration for determining a representative sound, method for synthesizing speech, and method for speech processing

A method for speech processing by determining a representative sound based on a structure, which comprises:

• forming, from a sound, a structure having a characteristic state criterion;
• providing a set of sound models, each sound model having a representative with a plurality of quality criteria;
• determining, in the structure, a first sound model from the set of sound models matching a first quality criterion;
• determining a second sound model from the set of sound models depending on the characteristic state criterion of the structure;
• forming an overall quality criterion for each representative by assessing representatives of the first and the second sound model with regard to a second quality criterion in addition to the first quality criterion;
• and
• determining a representative having an adequate overall quality criterion with regard to the first and second quality criteria as a representative sound.

A method for synthesizing speech by determining a representative sound based on a structure, which comprises:

• forming, from a sound, a structure having a characteristic state criterion;
• providing a set of sound models, each sound model having a representative with a plurality of quality criterion;
• determining, in the structure, a first sound model from the set of sound models matching a first quality criterion;
• determining a second sound model from the set of sound models depending on the characteristic state criterion of the structure;
• forming an overall quality criterion for each representative by assessing representatives of the first and the second sound model with regard to a second quality criterion in addition to the first quality criterion;
• and
• determining a representative having an adequate overall quality criterion with regard to the first and second quality criteria as a representative sound.

A configuration, comprising a processor unit for determining a representative sound based on a structure including a set of sound models, each sound model having at least one representative for a modeled sound, said processor unit:

• determining, in the structure, a first sound model from the set of sound models by matching a first quality criterion;
• determining at least one second sound model from the set of sound models, dependent on a characteristic state criterion of the structure;
• assessing representatives of the first and the at least one second sound model in addition to the first quality criterion with regard to a second quality criterion;
• and
• selecting a representative sound by determining at least one representative having an adequate overall quality criterion with regard to the first and second quality criteria.