Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech

Gillick, Larry; Baker, James K.; Bridle, John S.; Hunt, Melvyn J.; Ito, Yoshiko; Lowe, Stephen A.; Orloff, J.; Peskin, Barbara; Roth, Robert; Scattone, Francesco

doi:10.1109/icassp.1993.319343

Cited by 30 publications

(17 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In (Gillick et al 1993), a large vocabulary word recognition approach was used on a 10-class topic identification task of recorded telephone conversations from the Switchboard corpus (Godfrey et al 1992). To classify a speech message, a large vocabulary, speakerindependent, speech recognizer is first used to produce an errorful transcription of the speech message.…”

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

“…In more constrained speech recognition tasks, the use of statistical language models for constraining and weighting the possible transitions between words has a significant effect on recognition performance (Rabiner & Juang, 1993). Previous studies have shown that statistical language models can also be used to improve performance on the less constrained Switchboard word spotting task (Weintraub, 1993;Gillick et al, 1993;Rohlicek et al, 1993). However, it was not clear from these studies whether the language model served to improve the model of non-vocabulary utterances, or simply constrained the possible word transitions in the vicinity of keywords.…”

Section: Keyword Detection In Conversational Speechmentioning

confidence: 93%

Keyword detection in conversational speech utterances using hidden Markov model based continuous speech recognition

Rose

1995

Computer Speech & Language

View full text Add to dashboard Cite

“…The importance of forming audio and topical segments has long been recognized in management of speech content. Early work on this subject was conducted on topic and speaker identification using HMM-based speech recognition in studies such as [85]. Segmentation using the audio content prior to recognition can help to improve the quality of the ASR transcripts.…”

Section: Segmentationmentioning

confidence: 99%

Automatic Summarization

Larson

2012

FNT in Information Retrieval

View full text Add to dashboard Cite

Application of large vocabulary continuous speech recognition to topic and speaker identification using telephone speech

Cited by 30 publications

References 8 publications

Subword-based approaches for spoken document retrieval

Subword-based approaches for spoken document retrieval

Keyword detection in conversational speech utterances using hidden Markov model based continuous speech recognition

Automatic Summarization

Contact Info

Product

Resources

About