Heinrich Niemann

Detection of phrase boundaries and accents

On a large speech database read by untrained speakers experiments for the recognition of phrase boundaries and phrase accents were performed. We used durational features as well as features derived from pitch and energy contours and pause information. Different sets of features were compared. For distinguishing three different boundary classes a recognition rate of 75.7% and for distinguishing accentuated from unaccentuated syllables a recognition rate of 88.7% could be achieved.

A flexible control strategy with multilevel judgements for a knowledge based speech understanding system

A flexible control strategy for a speech understanding and dialog system is presented. The system is organized around a homogeneous knowledge base. The used knowledge representation language is based on semantic networks. It does not only cover declarative but also procedural knowledge. The inference processes can be described by five problem-independent rules which form the procedural semantics of the network language. The control strategy itself is the well-known A*-algorithm, but for scoring purposes complex judgement vectors are used. It is shown that these vectors are admissible for the control algorithm and that they reflect the quality, the certainty, and the priority of both bottom-up and top-down hypotheses. So far, the system has been tested in a rough prototype version, and an efficient realization is being built.<<ETX>>

Classification of boundaries and accents in spontaneous speech

Das diesem Bericht zugrundeliegende Forschungsvorhaben wurde mit Mitteln des Bundesministers f ur Bildung, Wissenschaft, Forschung und Technologie unter dem F orderkennzeichen 01 IV 102 H/0 und 01 IV 102 F/4 gef ordert. Die Verantwortung f ur den Inhalt dieser Arbeit liegt bei den Autoren.

Topic spotting using subword units

In this paper we present a new approach for topic spotting based on subword units and feature vectors instead of words. In our first approach, we only use vector quantized feature vectors and polygram language models for topic representation. In the second approach, we use phonemes instead of the vector quantized feature vectors and model the topics again using polygram language models. We trained and tested the two methods on two different corpora. The first is a part of a media corpus which contains data from TV shows for three different topics. The second is the VERBMOBIL-corpus where we used 18 dialog acts as topics. Each corpus was splitted into disjunctive test and training sets. We achieved recognition rates up to 82% for the three topics of the media corpus and up to 64% using 18 dialog acts of the VERBMOBIL-corpus as topics.

Ein wissensbasiertes System zur automatischen Auswertung von Bildsequenzen des menschlichen Herzens

Der Artikel beschreibt ein System zur automatischen Auswertung nuklearmedizinisch gewonnener Bildfolgen des menschlichen Herzens. Aus der eingegebenen Bildsequenz wird wahrend des Analyseprozesses eine vollstandige diagnostische Beschreibung erzeugt. Das System arbeitet wissensbasiert. Das zur Analyse notwendige a priori Wissen wird in einem assoziativen Netzwerk gespeichert. Die Umsetzung von Bewegungsverlaufen zu diagnostischen Aussagen erfolgt mit Produktionsregeln auf der Basis der Fuzzy-Set Theorie.

Contrastive accents : how to get them and what do they look like

Automatic dialog systems tested with naive users are often confronted with spe cial speaking styles as e g words pro duced with emphatic or contrastive ac cent Such utterances usually cause prob lems for word recognizers because they were not included in the training data It is thus important for the improvement of future systems to be able to collect utterances containing contrastive accents produced as natural as possible We de scribe in this paper an automatic simula tion system for provoking and collecting contrastive accents With this system recording sessions were conducted in total word tokens produced either with de fault or with contrastive accent were col lected We discuss the results of an au tomatic classi cation as well as the rele vance of extracted prosodic features for the marking of contrastive accents