In this paper a new method for detection of focus is developed. Speech data consists of German spontaneous speech from several speakers. At present the algorithm uses only the fundamental frequency values. By computing a nonlinear reference line through significant anchor points in the F_{0} course, points of highest prominence are determined. The global recognition rate is 78,5% and the mean recognition rate is 66,6%
We propose Multi-level Semantic Classication Trees to combine different information sources for pred...
We show in this paper that the labeling of sentence modality in German, esp. of questions vs. non-qu...
Signal processing tools are developed to help automati-cally detect significant events or focal poin...
A method to extract and classify focus accents has been developed. It works for German spontaneous s...
In this paper a new method for detection of focus is developed. Speech data consists of German spont...
A large corpus has been created automatically and read by speakers. Phrase boundaries were labeled i...
In order to cope with the problems of spontaneous speech (including, for example, hesitations and no...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting ...
In this paper detectors for accents, phrase boundaries, and sentence modality are described which de...
Prosody falls between several established fields as e.g. phonetics, phonology, syntax, and dialogue ...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting ...
In automatic speech understanding, the division of continuously running speech into syntactic chunks...
A frequent phenomenon in spoken dialogs of the information seeking type are short elliptic utterance...
Detectors for accents and phrase boundaries have been developed which derive prosodic features from ...
Filled pauses as, e.g., uh, eh, signal disfluencies, i.e. hesitations or repairs. They do normally n...
We propose Multi-level Semantic Classication Trees to combine different information sources for pred...
We show in this paper that the labeling of sentence modality in German, esp. of questions vs. non-qu...
Signal processing tools are developed to help automati-cally detect significant events or focal poin...
A method to extract and classify focus accents has been developed. It works for German spontaneous s...
In this paper a new method for detection of focus is developed. Speech data consists of German spont...
A large corpus has been created automatically and read by speakers. Phrase boundaries were labeled i...
In order to cope with the problems of spontaneous speech (including, for example, hesitations and no...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting ...
In this paper detectors for accents, phrase boundaries, and sentence modality are described which de...
Prosody falls between several established fields as e.g. phonetics, phonology, syntax, and dialogue ...
Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting ...
In automatic speech understanding, the division of continuously running speech into syntactic chunks...
A frequent phenomenon in spoken dialogs of the information seeking type are short elliptic utterance...
Detectors for accents and phrase boundaries have been developed which derive prosodic features from ...
Filled pauses as, e.g., uh, eh, signal disfluencies, i.e. hesitations or repairs. They do normally n...
We propose Multi-level Semantic Classication Trees to combine different information sources for pred...
We show in this paper that the labeling of sentence modality in German, esp. of questions vs. non-qu...
Signal processing tools are developed to help automati-cally detect significant events or focal poin...
DOI
Add to ORKG