Automatic Speech Activity Detection, Source Localization, and Speech Recognition on the Chil Seminar Corpus

Macho, Dušan; Padrell, Jaume; Abad, Alberto; Nadeu, Climent; Hernando, Javier; McDonough, John; Wölfel, Matthias; Klee, Ulrich; Omologo, Maurizio; Brutti, Alessio; Svaizer, Piergiorgio; Potamianos, Gerasimos; Chu, Stephen M.

doi:10.1109/icme.2005.1521563

Cited by 23 publications

(14 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To check if our SAD system is light enough, we compute the real-time factor as expressed in equation (1). …”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Speech is indeed one of the preferred and most natural communication channels in human to human interactions, and sounds are revealing of human activity. This is why many perceptual environments, such as in the CHIL project [1], are equipped with speech detection, speech recognition and acoustic localization systems. One requirement in such perceptive environments is to be able to process multiple and various microphones in parallel while fitting real time constraints.…”

Section: Introductionmentioning

confidence: 99%

“…Within the CHIL project [1], we are developing a speech detection system that fulfills the requirements of these perceptual environments. Although much research has already been conducted on this point and different approaches have been proposed (such as [2] and [3]), the problem is still open.…”

Section: Introductionmentioning

confidence: 99%

“…Section 3 then presents evaluations that were conducted and the results obtained in the NIST 06s evaluation 1 . Finally we will give a conclusion and some further works to be carried out in order to improve our system.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Lightweight Speech Detection System for Perceptive Environments

Vaufreydaz

Emonet

Reignier

2006

Machine Learning for Multimodal Interaction

View full text Add to dashboard Cite

Abstract. In this paper, we address the problem of speech activity detection in multimodal perceptive environments. Such space may contain many different microphones (lapel, distant or table top). Thus, we need a generic speech activity detector in order to cope with different speech conditions (from closetalking to noisy distant speech). Moreover, as the number of microphones in the room can be high, we also need a very light system. The speech activity detector presented in this article works efficiently on dozens of microphones in parallel. We will see that even if its absolute score of the evaluation is not perfect (30% and 40% of error rate respectively on the two tasks), its accuracy is good enough in the context we are using it.

show abstract

“…To check if our SAD system is light enough, we compute the real-time factor as expressed in equation (1). …”

Section: Evaluation Metricsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Lightweight Speech Detection System for Perceptive Environments

Vaufreydaz

Emonet

Reignier

2006

Machine Learning for Multimodal Interaction

View full text Add to dashboard Cite

show abstract

“…Still according to (Dey, 2001), a "system is context-aware if it uses context to provide relevant information and/or services to the user, where relevancy depends on the user's task". In a context-aware multimodal interaction system, perceived contextual information is often used to complement or disambiguate an active mode of interaction, such as speech (Stillman & Essa, 2001;Macho et al, 2005). For example, (Yoshimi & Pingali, 2002) describe a video conferencing application, which combines carefully placed multiple distributed microphone pairs with calibrated cameras to identify the current speaker and their location, in order to achieve a finer control of the speech recognition process.…”

Section: Context-aware Multimodal Interaction Systemsmentioning

confidence: 99%