Explicit estimation of speech boundaries

Taboada, J.; Feijóo, Sara; Balsa, R.; Ramos-Hernández, Cristina

doi:10.1049/ip-smt:19949700

Cited by 11 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It uses advanced coefficients computed on the input frames as input: band-crossing [12], Energy and 16 predictor coefficients extracted from a speech analysis method called Linear Predictive Coding (LPC) [10]. This module is the only sub-system that needs to be trained.…”

Section: Neural Netmentioning

confidence: 99%

Unsupervised Segmentation of Meeting Configurations and Activities using Speech Activity Detection

Brdiczka

Vaufreydaz

Maisonnasse

et al. 2006

IFIP International Federation for Information Processing

View full text Add to dashboard Cite

This paper addresses the problem of segmenting small group meetings in order to detect different group configurations and activities in an intelligent environment. Our approach takes speech activity detection of individuals attending a meeting as input. The goal is to separate distinct distributions of speech activity observation corresponding to distinct group configurations and activities. We propose an unsupervised method based on the calculation of the Jeffrey divergence between histograms of speech activity observations. These histograms are generated from adjacent windows of variable size slid from the beginning to the end of a meeting recording. The peaks of the resulting Jeffrey divergence curves are detected using successive robust mean estimation. After a merging and filtering process, the retained peaks are used to select the best model, i.e. the best speech activity distribution allocation for a given meeting recording. These distinct distributions can be interpreted as distinct segments of group configuration and activity. To evaluate, we recorded 6 small group meetings. We measured the correspondence between detected segments and labeled group configurations and activities. The obtained results are promising, in particular as our method is completely unsupervised.

show abstract

Section: Neural Netmentioning

confidence: 99%

Unsupervised Segmentation of Meeting Configurations and Activities using Speech Activity Detection

Brdiczka

Vaufreydaz

Maisonnasse

et al. 2006

IFIP International Federation for Information Processing

View full text Add to dashboard Cite

show abstract

“…It uses as input coefficients computed on the input frames: − Zero crossing: number of time the signal goes from a negative to a positive value and vice versa. Actually, we use a variant called band-crossing [5] that does not count oscillations in a band around 0. − Energy: the sum of the square values of samples.…”

Section: Neural Networkmentioning

confidence: 99%

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