Summarized Speech Sentence Generation Based on Word Extraction and Its Evaluation

概要

論文の詳細を見る
This paper proposes a new automatic speech summarization method. In this method, a set of words maximizing a summarization score is extracted from automatic speech transcription results. This extraction is performed according to a target compression ratio using a dynamic programming technique. The extracted set of words is then connected to build a summarization sentence. The summarization score consists of a word significance measure, linguistic likelihood and a confidence measure. This paper also proposes a new method for measuring the summarization accuracy based on a word network expressing manual summarization results. The summarization accuracy of each automatic summarization result is calculated using the most similar word string in the network. Japanese broadcast news speech transcribed using a large-vocabulary continuous-speech recognition (LVCSR) system is summarized and evaluated using our method. Experimental results show that the proposed method effectively extracts relatively important information by removing redundant and irrelevant information.
社団法人電子情報通信学会の論文
2002-02-01