A SEGMENT-LEVEL CONFIDENCE MEASURE FOR SPOKEN DOCUMENT RETRIEVAL
Spoken Document Processing
Presented by: Gregory Senay, Author(s): Gregory Senay, Georges Linarès, Benjamin Lecouteux, University of Avignon, France
This paper presents a semantic confidence measure that aims to predict the relevance of automatic transcripts for a task of Spoken Document Retrieval. The proposed predicting method relies on the combination of Automatic speech Recognition (ASR) confidence measure and a local semantic compacity index (SCI), that estimates the relevance of the words regarding the semantic context in which they occurred. Experiments are conducted on the French Broadcast news corpus ESTER, by simulating a classical SDR usage scenario : users submit text-queries to a search engine that is expected to return the most relevant documents regarding the query. Results demonstrate the interest of using semantic level information to predict the transcription indexability.
- A SEGMENT-LEVEL CONFIDENCE MEASURE FOR SPOKEN DOCUMENT RETRIEVAL [PDF], 12.13 MB