ABSTRACT
Early speech retrieval experiments focused on news broadcasts, for which adequate Automatic Speech Recognition (ASR) accuracy could be obtained. Like newspapers, news broadcasts are a manually selected and arranged set of stories. Evaluation designs reflected that, using known story boundaries as a basis for evaluation. Substantial advances in ASR accuracy now make it possible to build search systems for some types of spontaneous conversational speech, but present evaluation designs continue to rely on known topic boundaries that are no longer well matched to the nature of the materials. We propose a new class of measures for speech retrieval based on manual annotation of points at which a user with specific topical interests would wish replay to begin.
- Arons, B., SpeechSkimmer: A System for Interactively Skimming Recorded Speech, ACM TOCHI, 4(1)3--98, 1997. Google ScholarDigital Library
- Garofolo, J. et al., The TREC Spoken Document Retrieval Track: A Success Story, in TREC-8, 2000.Google Scholar
- Gustman, S. et al., Supporting Access to Large Digital Oral History Archives, in JCDL 2002, pp.18--27. Google ScholarDigital Library
- Kekäläinen, J. et al., Using Graded Relevance Assessments in IR evaluation, JASIST, 53(13), pp.1120--1129. Google ScholarDigital Library
- Voorhees, E., Variations in Relevance Judgments and the Measurement of Retrieval Effectiveness, in SIGIR 1998. Google ScholarDigital Library
Index Terms
- One-sided measures for evaluating ranked retrieval effectiveness with spontaneous conversational speech
Recommendations
Combining LVCSR and vocabulary-independent ranked utterance retrieval for robust speech search
SIGIR '09: Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrievalWell tuned Large-Vocabulary Continuous Speech Recognition (LVCSR) has been shown to generally be more effective than vocabulary-independent techniques for ranked retrieval of spoken content when one or the other approach is used alone. Tuning LVCSR ...
Characterizing and detecting spontaneous speech: Application to speaker role recognition
Processing spontaneous speech is one of the many challenges that automatic speech recognition systems have to deal with. The main characteristics of this kind of speech are disfluencies (filled pause, repetition, false start, etc.) and many studies have ...
Detecting laughter in spontaneous speech by constructing laughter bouts
Laughter frequently occurs in spontaneous speech (e.g. conversational speech, meeting speech). Detecting laughter is quite important for semantic analysis, highlight extraction, spontaneous speech recognition, etc. In this paper, we first analyze the ...
Comments