Hierarchical language models for one-stage speech interpretation
نویسندگان
چکیده
This paper presents a robust semantic model for one-stage interpretation of natural speech. Our semantic analysis uses no explicit syntactic and morphologic knowledge, which seems sufficient for narrow application domains. In contrast to previous approaches, our semantic model is embedded in a uniform, hierarchical, stochastic modeling framework together with acoustic-phonetic and lexical knowledge, and semantic representations are computed directly from acoustic observations through a one-stage decoding process. The decoder produces a hierarchical (tree-) structure of words and semantic category symbols by use of the so-called hierarchical language model (HLM). We discuss generation of HLM by mixing rulebased and data-driven language model (LM) generation techniques, namely weighted regular expressions, n-grams and exact LM. Different HLM configurations with varying discounting techniques, n-gram orders and scaling factors are examined. Experiments were conducted with an airport information dialogue application. The evaluation results are based on HLM perplexity and our previously published semantic tree accuracy.
منابع مشابه
A flexible and integrated interface between speech recognition, speech interpretation and dialog management
This paper presents an integrated interface between speech recognition, speech interpretation and dialog control intended for spoken dialog systems coping with natural speech input. During the system design phase the interface co-ordinates corpus acquisition and annotation, grammar development and the construction of stochastic hierarchical language models. During system runtime, it links toget...
متن کاملA Flexible and Integrated Interface be Speech Interpretation and Di
This paper presents an integrated interface between speech recognition, speech interpretation and dialog control intended for spoken dialog systems coping with natural speech input. During the system design phase the interface co-ordinates corpus acquisition and annotation, grammar development and the construction of stochastic hierarchical language models. During system runtime, it links toget...
متن کاملLexical out-of-vocabulary models for one-stage speech interpretation
We present an approach to explicit, statistical, lexical-level out-of-vocabulary (OOV) word modeling for direct integration into the search space of a one-stage speech interpretation system. For this purpose, a generic pronunciation model for unknown words is derived from large pronunciation lexica and, optionally, word frequency knowledge. Known statistical language modeling (LM) methods are u...
متن کاملModels of EFL Learners’ Vocabulary Development: Spreading Activation vs. Hierarchical Network Model
Semantic network approaches view organization or representation of internal lexicon in the form of either spreading or hierarchical system identified, respectively, as Spreading Activation Model (SAM) and Hi- erarchical Network Model (HNM). However, the validity of either model is amongst the intact issues in the literature which can be studied through basing the instruction compatible wi...
متن کامل