Speech Recognition Using Semantic Hidden Markov Networks
Fink GA, Kummert F, Sagerer G, Schukat-Talamazzini EG (1993)
In: Proc. European Conf. on Speech Communication and Technology., 3. Berlin: 1571-1574.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Fink, Gernot A.;
Kummert, FranzUniBi;
Sagerer, GerhardUniBi;
Schukat-Talamazzini, E. G.
Einrichtung
Abstract / Bemerkung
Semantic Hidden Markov Networks (SHMNs) were introduced as a new technique of interfacing between linguistic analysis and word recognition in speech understanding systems. The main difference between SHMNs and the use of traditional language models is that SHMNs always refer to a linguistic concept and impose the linguistic structure as closely as possible on its acoustic counterpart — a hierarchically structured HMM. Normally the result of decoding a HMM is merely the sequence of best fitting elementary acoustic concepts, e.g. phonemes or words. Taking into account the structure of the recognition task a structured instance can be computed. This complex acoustic instance can easily be transformed into a linguistic instance by a recursive computation but without any searching. In this paper we present an algorithm for generating linguistic instances from word recognition results based on SHMNs. Additionally, we present recognition results obtained when evaluating a set of SHMNs for the task domain of train schedule information.
Erscheinungsjahr
1993
Titel des Konferenzbandes
Proc. European Conf. on Speech Communication and Technology
Band
3
Seite(n)
1571-1574
Page URI
https://pub.uni-bielefeld.de/record/2619467
Zitieren
Fink GA, Kummert F, Sagerer G, Schukat-Talamazzini EG. Speech Recognition Using Semantic Hidden Markov Networks. In: Proc. European Conf. on Speech Communication and Technology. Vol 3. Berlin; 1993: 1571-1574.
Fink, G. A., Kummert, F., Sagerer, G., & Schukat-Talamazzini, E. G. (1993). Speech Recognition Using Semantic Hidden Markov Networks. Proc. European Conf. on Speech Communication and Technology, 3, 1571-1574
Fink, Gernot A., Kummert, Franz, Sagerer, Gerhard, and Schukat-Talamazzini, E. G. 1993. “Speech Recognition Using Semantic Hidden Markov Networks”. In Proc. European Conf. on Speech Communication and Technology, 3:1571-1574. Berlin.
Fink, G. A., Kummert, F., Sagerer, G., and Schukat-Talamazzini, E. G. (1993). “Speech Recognition Using Semantic Hidden Markov Networks” in Proc. European Conf. on Speech Communication and Technology, vol. 3, (Berlin), 1571-1574.
Fink, G.A., et al., 1993. Speech Recognition Using Semantic Hidden Markov Networks. In Proc. European Conf. on Speech Communication and Technology. no.3 Berlin, pp. 1571-1574.
G.A. Fink, et al., “Speech Recognition Using Semantic Hidden Markov Networks”, Proc. European Conf. on Speech Communication and Technology, vol. 3, Berlin: 1993, pp.1571-1574.
Fink, G.A., Kummert, F., Sagerer, G., Schukat-Talamazzini, E.G.: Speech Recognition Using Semantic Hidden Markov Networks. Proc. European Conf. on Speech Communication and Technology. 3, p. 1571-1574. Berlin (1993).
Fink, Gernot A., Kummert, Franz, Sagerer, Gerhard, and Schukat-Talamazzini, E. G. “Speech Recognition Using Semantic Hidden Markov Networks”. Proc. European Conf. on Speech Communication and Technology. Berlin, 1993.Vol. 3. 1571-1574.
Google Scholar