Adaptiver stochastischer Sprache/Pause-Detektor

Beham, M. Parisa; Ruske, Günther

doi:10.1007/978-3-642-79980-8_7

Cited by 2 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…pants for completeness. 1 The main result to note from Table 1 is that overall word error rates are not dramatically worse than for Switchboard-style data. This is particularly impressive since, as described earlier, no meeting data were used in training, and no modifications of the acoustic or language models were made.…”

Section: Recognition Results and Discussionmentioning

confidence: 91%

“…Segment boundary times were determined either by an automatic segmentation of the mixed signal followed by hand-correction, or by hand-correction alone. For the automatic case, the data was segmented with a speech/nonspeech detector consisting of an extension of an approach using an ergodic hidden Markov model (HMM) [1]. In this approach, the HMM consists of two main states, one representing "speech" and one representing "nonspeech" and a number of intermediate states that are used to model the time constraints of the transitions between the two main states.…”

Section: Speech Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

The meeting project at ICSI

Morgan

Baron

Edwards

et al. 2001

Proceedings of the First International Conference on Human Language Technology Research - HLT '01

View full text Add to dashboard Cite

In collaboration with colleagues at UW, OGI, IBM, and SRI, we are developing technology to process spoken language from informal meetings. The work includes a substantial data collection and transcription effort, and has required a nontrivial degree of infrastructure development. We are undertaking this because the new task area provides a significant challenge to current HLT capabilities, while offering the promise of a wide range of potential applications. In this paper, we give our vision of the task, the challenges it represents, and the current state of our development, with particular attention to automatic transcription. D: There's a-there are-there's a whole bunch of tools J: Yes. / D: web page, where they have a listing. D: like 10 of them or something. J: Are you speaking about Mississippi State per se? or D: No no no, there's some .. I mean, there just-there arethere are a lot of / J: Yeah. J: Actually, I wanted to mention-/ D: (??) J: There are two projects, which are .. international .. huge projects focused on this kind of thing, actually .. one of them's MATE, one of them's EAGLES .. and um. D: Oh, EAGLES. D: (??) / J: And both of them have J: You know, I shou-, I know you know about the big book. E: Yeah. J: I think you got it as a prize or something. E: Yeah. / D: Mhm. J: Got a surprise. flaughg f J. thought "as a prize" sounded like "surprise"g Note that interruptions are quite frequent; this is, in our experience, quite common in informal meetings, as is acoustic overlap

show abstract

Section: Recognition Results and Discussionmentioning

confidence: 91%

Section: Speech Segmentationmentioning

confidence: 99%

The meeting project at ICSI

Morgan

Baron

Edwards

et al. 2001

Proceedings of the First International Conference on Human Language Technology Research - HLT '01

View full text Add to dashboard Cite

show abstract

“…The S/NS detection module is based on a hidden Markov model (HMM) S/NS detector designed for automatic speech recognition on close-talking microphone data of a single speaker [2]. The baseline detector is similar to the one used in [3], and consists of an ergodic HMM with two main states -"speech" and "nonspeech" -and a number of intermediate state pairs to impose time constraints on transitions between the two main states.…”

Section: Baseline Architecturementioning

confidence: 99%

“…The peak normalized short-time crosscorrelation, (2) between the active channels i and j are used to estimate the similarity between the two signals. For "real" overlaps (two speakers speaking at the same time) the crosscorrelation is expected to be lower than for "false" overlaps (one speaker coupled into both microphones).…”

Section: Crosscorrelation Analysismentioning

confidence: 99%

Multispeaker speech activity detection for the ICSI meeting recorder

Pfau

Ellis

Stolcke

IEEE Workshop on Automatic Speech Recognition and Understanding, 2001. ASRU '01.

View full text Add to dashboard Cite

As part of a project into speech recognition io meeting envimn-men% we have collected a corpus of m u l t i z h l meeting recordings. We expccted the identification of speaker activity to be straightfonvard given that the participants had individual microphones, but simplc approaches yielded unacceptably erroneous labelings, mainly due to crosstalk between nearby speakers and wide variations in channel characteristics. Therefore, we have developed a more sophisticated approach for multichannel speech activity detection using a simple hidden Markov model (HMM) A baseline HMM speech activity detector has been extended to use mixtures of Gaussianr to achieve robustness for different speaken under different conditions. Feature normalition and crosscornlalion processing are used to increase the channel independence and to detect crosstalk. W e use of both energy normalization and crosscorrelation based postprocessing results in a 35% relative reduction of the frame error rate. Speech recognition experiments show that it is beneficial in this multispeaker setting to use the output of the speech activity detector for presegmenting the recognizer input, achieving word mor rates within 10% of those achieved with manual turn labeling. [8] Shr~nberg, E.. Stolckc. A , and Baron. D.. "Observations on avcrlsp' Findings and rmplicationr for n~t o r n i l t i~ processing ofmulti-pany c w w~t i o n " . Proc Ewospeah-2001, Aalburg. 0-7803-7343-X/02/$17.00 Q 2002 IEEE I10

show abstract

Adaptiver stochastischer Sprache/Pause-Detektor

Cited by 2 publications

References 1 publication

The meeting project at ICSI

The meeting project at ICSI

Multispeaker speech activity detection for the ICSI meeting recorder

Contact Info

Product

Resources

About