Martin Emele

SmartKom-Home: The Interface to Home Entertainment

SmartKom-Home demonstrates the use and benefit of an intelligent multimodal interface when controlling entertainment devices like a TV, a recorder, and a jukebox, and when accessing entertainment services like an electronic program guide combining speech and a handheld display with touch input. One important point is emphasizing the functional aspect, i.e., the user’s needs, conveyed to the system in a natural way by speech and gesture, are satisfied. The user does not need to know device-specific features or service idiosyncrasies. The function modeling component in SmartKom-Home has the necessary knowledge to transform the abstract user request into device commands and service queries.

The Dynamic Lexicon

The dynamic lexicon is one of the central knowledge sources in SmarTkom that provides the whole system with the capabability to dynamically update the vocabulary. The corresponding multilingual pronunciations, which are needed by all speech-related components, are automatically generated.

Class-Based Language Model Adaptation

In this paper we introduce and evaluate two class-based language model adaptation techniques for adapting general n-gram-based background language models to a specific spoken dialogue task. The required background language models are derived from available newspaper corpora and Internet newsgroup collections. We followed a standard mixture-based approach for language model adaptation by generating several clusters of topic-specific language models and combined them into a specific target language model using different weights depending on the chosen application domain. In addition, we developed a novel word n-gram pruning technique for domain adaptation and proposed a new approach for thematic text clustering. This method relies on a new discriminative n-gram-based key term selection process for document clustering. These key terms are then used to automatically cluster the whole document collection. By selecting only relevant text clusters for language model training, we addressed the problem of generating task-specific language models. Different key term selection methods are investigated using perplexity as the evaluation measure. Automatically computed clusters are compared with manually labeled genre clusters, and the results provide a significant performance improvement depending on the chosen key term selection method.

Thematic text clustering for domain specific language model adaptation

We propose a new approach for thematic text clustering. The text clusters are used to generate domain specific language models in order to address the problem of language model adaptation. The method relies on a new discriminative n-gram based term selection process (n>l), which reduces the influence of the corpus inhomogeneity, and outputs only semantically focused n-grams as being the most representative key terms in the corpus. These key terms are then used to automatically cluster the whole document collection and generate LM out of these text clusters. Different key term selection methods are evaluated using perplexity as a measure. Automatically computed clusters are compared with manually assigned labelling according to genre information. The results of these experimental studies are presented and discussed. Compared to the manual clustering a significant performance improvement between 21.87 % and 53.12 % is observed depending on the chosen key term selection method.