We present the first known empirical study on speech summarization without lexical features for Mandarin broadcast news. We evaluate acoustic, lexical and structural features as ...
In this paper, we investigate the use of words and subwords (including both characters and syllables) in audio indexing for Mandarin Chinese spoken document retrieval. Two retrieva...
Lattice-based approaches have been widely used in spoken document retrieval to handle the speech recognition uncertainty and errors. Position Specific Posterior Lattices (PSPL) an...
Spoken document retrieval (SDR) has been extensively studied in recent years because of its potential use in navigating large multimedia collections in the near future. This paper...
We propose new methods to exploit contemporaneous text, such as on-line news articles, to improve language models for automatic speech recognition and other natural language proce...