Castsearch - Context Based Spoken Document Retrieval

TLDR

The paper presents a system for retrieving relevant stories from broadcast news. The system combines audio processing—segmentation into speech and music, speaker segmentation, and automatic speech recognition—with text mining, using non‑negative matrix factorization to cluster transcribed speech into semantic topics for evaluation. Using these topics, the authors demonstrate that a novel query expansion improves search results and reduces errors introduced by automatic transcription.

Abstract

The paper describes our work on the development of a system for retrieval of relevant stories from broadcast news. The system utilizes a combination of audio processing and text mining. The audio processing consists of a segmentation step that partitions the audio into speech and music. The speech is further segmented into speaker segments and then transcribed using an automatic speech recognition system, to yield text input for clustering using non-negative matrix factorization (NMF). We find semantic topics that are used to evaluate the performance for topic detection. Based on these topics we show that a novel query expansion can be performed to return more intelligent search results. We also show that the query expansion helps overcome errors of the automatic transcription.