Gisting conversational speech

Rohlíček, Ján; Ayuso, Damaris; Bates, Madeleine; Bobrow, Rusty; Boulanger, A.; Gish, H.; Jeanrenaud, P.; Meteer, Marie; Siu, Man-Hung

doi:10.1109/icassp.1992.226107

Cited by 20 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (Rohlicek et al 1992), a system for extracting information from off-the-air recordings of air traffic control communications is described. The goal of this "gisting" system is to identify flights and to determine whether they are "taking off" or "landing."…”

Section: Topic Identificationmentioning

confidence: 99%

Subword-based approaches for spoken document retrieval

Zue

2000

Speech Communication

148

109

View full text Add to dashboard Cite

This thesis explores approaches to the problem of spoken document retrieval (SDR), which is the task of automatically indexing and then retrieving relevant items from a large collection of recorded speech messages in response to a user specified natural language text query. We investigate the use of subword unit representations for SDR as an alternative to words generated by either keyword spotting or continuous speech recognition. Our investigation is motivated by the observation that word-based retrieval approaches face the problem of either having to know the keywords to search for a priori, or requiring a very large recognition vocabulary in order to cover the contents of growing and diverse message collections. The use of subword units in the recognizer constrains the size of the vocabulary needed to cover the language; and the use of subword units as indexing terms allows for the detection of new user-specified query terms during retrieval.Four research issues are addressed. First, what are suitable subword units and how well can they perform? Second, how can these units be reliably extracted from the speech signal? Third, what is the behavior of the subword units when there are speech recognition errors and how well do they perform? And fourth, how can the indexing and retrieval methods be modified to take into account the fact that the speech recognition output will be errorful?We first explore a range of subword units of varying complexity derived from error-free phonetic transcriptions and measure their ability to effectively index and retrieve speech messages. We find that many subword units capture enough information to perform effective retrieval and that it is possible to achieve performance comparable to that of text-based word units. Next, we develop a phonetic speech recognizer and process the spoken document collection to generate phonetic transcriptions. We then measure the ability of subword units derived from these transcriptions to perform spoken document retrieval and examine the effects of recognition errors on retrieval performance. Retrieval performance degrades for all subword units (to 60% of the clean reference), but remains reasonable for some subword units even without the use of any error compensation techniques. We then investigate a number of robust methods that take into account the characteristics of the recognition errors and try to compensate for them in an effort to improve spoken document retrieval performance when there are speech recognition errors. We study the methods individually and explore the effects of combining them. Using these robust methods improves retrieval performance by 23%. We also propose a novel approach to SDR where the speech recognition and information retrieval components are more tightly integrated. This is accomplished by developing new recognizer and retrieval models where the interface between the two 3 components is better matched and the goals of the two components are consistent with each other and with the overall goal of the combine...

show abstract

Section: Topic Identificationmentioning

confidence: 99%

Subword-based approaches for spoken document retrieval

Zue

2000

Speech Communication

148

109

View full text Add to dashboard Cite

show abstract

“…However, it is possible to use simpler techniques to produce summaries that are of some use. The earliest reported work in speech summarization concerned the generation of crude summaries based on acoustic emphasis [Chen and Withgott 1992] and the classification of parts of dialogue [Rohlicek et al 1992]. More recently, with the advent of large vocabulary speaker-independent continuous ASR, speech summarization research has focused on the application of text-based methods to ASR output [Valenza et al 1999;Hori and Furui 2000;Zechner 2001].…”

Section: Introductionmentioning

confidence: 99%

Automatic summarization of voicemail messages using lexical and prosodic features

Koumpis

Renals

2005

ACM Trans. Speech Lang. Process.

View full text Add to dashboard Cite

This aticle presents trainable methods for extracting principal content words from voicemail messages. The short text summaries generated are suitable for mobile messaging applications. The system uses a set of classifiers to identify the summary words with each word described by a vector of lexical and prosodic features. We use an ROC-based algorithm, Parcel, to select input features (and classifiers). We have performed a series of objective and subjective evaluations using unseen data from two different speech recognition systems as well as human transcriptions of voicemail speech.

show abstract

“…A system attempting to model conversational behavior using supervised machine learning techniques (our own [2], or others mentioned in the introduction, e.g., [4,5,8,20,21,27,30]) requires collection and labeling of training data. Making the labeling task more efficient will speed development time and reduce costs.…”

Section: Tools For Qualitative Analysismentioning

confidence: 99%

“…Automated analysis of multi-party interaction has recently been applied in environments such as co-present meetings [17,27,30], co-present informal interactions [4,8,20], and remote interaction via audio or video links [2,21,32]. This nascent line of research seeks to enable applications such as:…”

Section: Introductionmentioning

confidence: 99%

Where's the "party" in "multi-party"?

Aoki

Szymanski

Plurkowski

et al. 2006

Proceedings of the 2006 20th Anniversary Conference on Computer Supported Cooperative Work

View full text Add to dashboard Cite

Spontaneous multi-party interaction -conversation among groups of three or more participants -is part of daily life. While automated modeling of such interactions has received increased attention in ubiquitous computing research, there is little applied research on the organization of this highly dynamic and spontaneous sociable interaction within small groups. We report here on an applied conversation analytic study of small-group sociable talk, emphasizing structural and temporal aspects that can inform computational models. In particular, we examine the mechanics of multiple simultaneous conversational floors -how participants initiate a new floor amidst an on-going floor, and how they subsequently show their affiliation with one floor over another. We also discuss the implications of these findings for the design of "smart" multi-party applications.

show abstract

Gisting conversational speech

Cited by 20 publications

References 4 publications

Subword-based approaches for spoken document retrieval

Subword-based approaches for spoken document retrieval

Automatic summarization of voicemail messages using lexical and prosodic features

Where's the "party" in "multi-party"?

Contact Info

Product

Resources

About