Topic and Stylistic Adaptation for Speech Summarisation

Abstract

Contemporary approaches to automatic speech summarisation comprise several components, among them a linguistic model (LiM) component, which is unrelated to the language model used during the recognition process. This LiM component assigns a probability to word sequences from the source text according to their likelihood of appearing in the summarised text. In this paper we investigate LiM topic and stylistic adaptation using combinations of LiMs each trained on different adaptation data. Experiments are performed on 9 talks from the TED corpus of Eurospeech conference presentations, as well as 5 news stories from CNN broadcast news data, for all of which human (TRS) and speech recogniser (ASR) transcriptions along with human summaries were used. In all ASR cases, summarisation accuracy (SumACCY) of automatically generated summaries was significantly improved by automatic LiM adaptation, with relative improvements of at least 2.5% in all experiments.

Class model adaptation for speech summarisation

“…Three sets of experiments were made: in the first experiment (referred to as Word), LiM B and both component models are word models, as introduced in (Chatain et al, 2006). For the second one (Class), both LiM B and the component models are class models built using exactly the same data as the word models.…”

“…Spontaneous speech is characterised by disfluencies, repetitions, repairs, and fillers, all of which make recognition and consequently speech summarisation more difficult (Zechner, 2002). In a previous study (Chatain et al, 2006), linguistic model (LiM) adaptation using different types of word models has proved useful in order to improve summary quality. However sparsity of the data available for adaptation makes it difficult to obtain reliable estimates of word n-gram probabilities.…”