The analysis of spoken language is widely considered to be a more challenging task than
the analysis of written text. All of the difficulties of written language can generally be found in …

This paper establishes a formal foundation for the specification of Geographic Data
Processing (GDP) requirements. The emphasis is placed on modelling data and knowledge …

The development of a practical spoken language dialog system is fraught with difficulties.
This thesis describes the following three problems relating to the natural language parsing …

The control of continuous speech recognition by a context-free based language model
requires a parsing process which may overload the acoustic decoding algorithm. We …

This method is based on the isolated word recognition method using the redundant hash
addressing principle proposed by T. Kohonen et al.(Inf. Sci. vol. 33, p. 3-30 of 1984). The …

This paper classifies distinctive phenomena occurring in Japanese spontaneous speech,
and proposes a grammar and processing techniques for handling them. Parsers using a …

This paper describes a fast word pre-selection method for continuous speech recognition. It
is essential to implement a bottom-up word pre-selection method to a continuous speech …

We present a new approach to integrate a context-free based language model in the
acoustic decoding algorithm of a continuous speech recognizer. This approach extends the …

In this paper, we present a novcl continuous speech recognition algorithm that integrates
three major technologies:(1) hidden Markov models for speech,(2) a generalized LR parser …

対 話 育 声 の 認 臓 枝 術 Page 1 Acoustical Society of Japan NII-Electronic Library Service
Aooustloal SOCIety of Japan 日本音響学会誌 50巻 7 号 (1994), pp .563−567 56謬 小特集 一 …