Statistical lattice-based spoken document retrieval

Abstract

Recent research efforts on spoken document retrieval have tried to overcome the low quality of 1-best automatic speech recognition transcripts, especially in the case of conversational speech, by using statistics derived from speech lattices containing multiple transcription hypotheses as output by a speech recognizer. We present a method for lattice-based spoken document retrieval based on a statistical n-gram modeling approach to information retrieval. In this statistical lattice-based retrieval (SLBR) method, a smoothed statistical model is estimated for each document from the expected counts of words given the information in a lattice, and the relevance of each document to a query is measured as a probability under such a model. We investigate the efficacy of our method under various parameter settings of the speech recognition and lattice processing engines, using the Fisher English Corpus of conversational telephone speech. Experimental results show that our method consistently achieves better retrieval performance than using only the 1-best transcripts in statistical retrieval, outperforms a recently proposed lattice-based vector space retrieval method, and also compares favorably with a lattice-based retrieval method based on the Okapi BM25 model. Permission to make digital/hard copy of all or part of this material without fee for personal or classroom use provided that the copies are not made or distributed for profit or commercial advantage, the ACM copyright/server notice, the title of the publication, and its date appear, and notice is given that copying is by permission of the ACM, Inc. To copy otherwise, to republish, to post on servers, or to redistribute to lists requires prior specific permission and/or a fee.

Spoken Document Retrieval Leveraging Unsupervised and Supervised Topic Modeling Techniques

“…Furthermore, the various WTM models have also been demonstrated to work effectively in the SDR task. As to future work, we envisage the following three directions: 1) utilizing speech summarization techniques to help better estimate the query and document models [26], 2) integrating the document model with other more elaborate representations of the speech recognition output [10], and 3) further confirming our observations on larger-scale experiments.…”

“…More recently, language modeling (LM) for SDR has received great attention due to its inherent neat formulation and clear probabilistic meaning, as well as state-of-the-art performance [7]- [10]. In practice, the relevance measure for various LM approaches is usually computed by two distinct matching strategies, namely, literal term matching and concept matching [11].…”

Automatic Summarization

“…The lack of information about term frequencies compromises the performance of the BIM and led to the development of the extension of the BIM referred to as the Okapi or BM25 model [227,228]. This extension introduces a sensitivity to term frequency and document length into the original BIM and has been demonstrated to yield good performance for many IR tasks including SCR [47,137].…”

“…In Equation 2.7, the contributions from terms are represented in the log domain to prevent underflow and they are combined using a simple sum. SCR work that has made use of the language modeling framework includes [47].…”

Using n-best recognition output for extractive summarization and keyword extraction in meeting speech

“…For machine translation, [11] used n-best list for reranking by optimizing interpolation weights for ASR and translation, and [12] used confusion network, but without much improvement over n-best. Lattices have been studied intensively for spoken document retrieval and indexing [13,14], with reported better performance than just using 1-best ASR output. For named entity recognition on speech data, [15] used n-best lists and obtained small improvement.…”