Volker Strom

Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesis

An HMM-based speech synthesis framework is applied to both standard Austrian German and a Viennese dialectal variety and several training strategies for multi-dialect modeling such as dialect clustering and dialect-adaptive training are investigated. For bridging the gap between processing on the level of HMMs and on the linguistic level, we add phonological transformations to the HMM interpolation and apply them to dialect interpolation. The crucial steps are to employ several formalized phonological rules between Austrian German and Viennese dialect as constraints for the HMM interpolation. We verify the effectiveness of this strategy in a number of perceptual evaluations. Since the HMM space used is not articulatory but acoustic space, there are some variations in evaluation results between the phonological rules. However, in general we obtained good evaluation results which show that listeners can perceive both continuous and categorical changes of dialect varieties by using phonological transformations employed as switching rules in the HMM interpolation.

Prosodic Modules for Speech Recognition and Understanding in VERBMOBIL

Within VERBMOBIL, a large project on spoken language research in Germany, two modules for detecting and recognizing prosodic events have been developed. One module operates on speech signal parameters and the word hypothesis graph, whereas the other module, designed for a novel, highly interactive architecture, only uses speech signal parameters as its input. Phrase boundaries, sentence modality, and accents are detected. The recognition rates in spontaneous dialogs are for accents up to 82.5%, for phrase boundaries up to 91.7%.

Optimizing phonetic encoding for viennese unit selection speech synthesis

While developing lexical resources for a particular language variety (Viennese), we experimented with a set of 5 different phonetic encodings, termed phone sets, used for unit selection speech synthesis. We started with a very rich phone set based on phonological considerations and covering as much phonetic variability as possible, which was then reduced to smaller sets by applying transformation rules that map or merge phone symbols. The optimal trade-off was found measuring the phone error rates of automatically learnt grapheme-to-phone rules and by a perceptual evaluation of 27 representative synthesized sentences. Further, we describe a method to semi-automatically enlarge the lexical resources for the target language variety using a lexicon base for Standard Austrian German.

Architectural Considerations for Conversational Systems

Verbmobil1 is a large German joint research project in the area spontaneous speech-to-speech translation systems which is sponsored by the German Federal Ministry for Research and Education. In its first phase (1992–1996) ca. 30 research groups in universities, research institutes and industry were involved, and it entered its second phase in January 1997. The overall goal is develop a system which supports face-to-face negotiation dialogues about the scheduling of meetings as its first domain, which will be enlarged to more general scenarios during the second project phase. For the dialogue situation it is assumed that two speakers with different mother tongues (German and Japanese) have some common knowledge of English. Whenever a speaker’s knowledge of English is not sufficient, the Verbmobil system will serve him as a speech translation device to which he can talk in his native language.