603 or)%. 5% oE) NSN RSN-different speech representational structures. A speech seg
ment selector selects from the speech segment database a sequence of speech segment …

One of the most serious challenges for speech synthesis is the systematic treatment of
events in language and speech that are known to have low frequencies of occurrence. The …

Thiss chapter deals with the marking of'prominent'parts in speech utterances. Prominencee
marking looks easy, but it is rather complex. The notion of prominence iss not clearly defined …

This paper describes a new open source architecture for unit-selection based speech
synthesis called BOSS (Bonn Open Synthesis System). It is built up modularly, with …

The research presented in this thesis was carried out in the framework of the 'Language and
Speech Technology'Priority Programme of NWO (the Netherlands Organisation for Scientific …

The intellegibility and naturalness of synthetic speech strongly depends on its prosodic
quality. Departing from works by Mixdorff on a linguistically motivated model of German …

This paper proposes a new text-to-speech (TTS) system that utilizes large numbers of
speech segments to produce very natural and intelligible synthetic speech. There are two …

Motivation für die Arbeit war die Beobachtung, daß sich phonologische Theorien zur
Vorhersage von Betonungsmustern meist auf zweifelhafte, introspektiv gewonnene Daten …

The perceived quality of synthetic speech strongly depends on its prosodic naturalness.
Departing from earlier works by Mixdorff on a linguistically motivated model of German …

The prosodic quality of a text-to-speech system is important for the intellegibility and
perceived naturalness of synthetic speech. In earlier works the author developed a …