Concept Extraction from Conversational Speech using Segment Graphs
- 1 October 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 262-267
Abstract
In this paper, a concept extraction method, an important element in spoken dialog systems when the nature of users' spoken queries are unstructured, is proposed and tested in a Thai automated international telephone call inquiry service. The method unifies concept constraints with other constraints, ranging from acoustic to language constraints, in a single segment-based probabilistic framework. With concept knowledge available, un-recalled keywords are reduced by 37%. Regarding concept extraction and goal identification, the proposed method is shown to be superior to the baseline system. Concepts are extracted at more than 80% of both recall and precision rates.Keywords
This publication has 7 references indexed in Scilit:
- Thai Speech Keyword Spotting using Heterogeneous Acoustic Modeling2007
- A multi-stage approach for Thai spoken language understandingSpeech Communication, 2006
- The AT&T spoken language understanding systemIEEE Transactions on Audio, Speech, and Language Processing, 2005
- Detecting and extracting named entities from spontaneous speech in a mixed-initiative spoken dialogue context: How May I Help You?sm,tmSpeech Communication, 2004
- A probabilistic framework for segment-based speech recognitionComputer Speech & Language, 2003
- JUPlTER: a telephone-based conversational interface for weather informationIEEE Transactions on Speech and Audio Processing, 2000
- Expanding the scope of the ATIS task1994