Title :
Speech recognition for spontaneously spoken German dialogues
Author :
Hübener, Kai ; Jost, Uwe ; Heine, Henrik
Author_Institution :
Siemens AG, Germany
Abstract :
The paper presents a HMM speech recognition system for spontaneously spoken dialogues. It has been developed as part of the German Verbmobil project whose aim is the development of a translation support system for face-to-face conversations. The HTK based decoder deals successfully with some of the hard problems of recognizing fluent speech and reaches quite competitive recognition results
Keywords :
decoding; hidden Markov models; language translation; natural languages; speech recognition; German Verbmobil project; HMM speech recognition system; HTK based decoder; competitive recognition results; face-to-face conversations; fluent speech recognition; spontaneously spoken German dialogues; translation support system; Automatic speech recognition; Cepstral analysis; Decoding; Hidden Markov models; Natural languages; Speech recognition; Testing; Tin; Topology; Vector quantization;
Conference_Titel :
Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on
Conference_Location :
Philadelphia, PA
Print_ISBN :
0-7803-3555-4
DOI :
10.1109/ICSLP.1996.607079
