All for one: feature combination for highly channel-degraded speech activity detection

Graciarena, Martin; Alwan, Abeer; Ellis, Dan; Franco, Horacio; Ferrer, Luciana; Hansen, John H. L.; Janin, Adam; Lee, Byung Suk; Lei, Yun; Mitra, Vikramjit; Morgan, Nelson; Sadjadi, Seyed Omid; Tsai, TJ; Scheffer, Nicolas; Tan, Lee Ngee; Williams, Benjamin J.

doi:10.21437/interspeech.2013-199

Cited by 24 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The VAD needs to work accurately in challenging environments, including noisy conditions, reverberant environments and environments with competing speech. Significant research has been devoted to finding the optimal VAD features and models [1,2,3,4,5]. In the literature, LSTM based VAD is a popular architecture for sequential modeling of the VAD task, showing state-of-the-art performance [3,5].…”

Section: Introductionmentioning

confidence: 99%

Personal VAD: Speaker-Conditioned Voice Activity Detection

Moreno¹,

Wan²,

Wang³

et al. 2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

View full text Add to dashboard Cite

In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery consumption. We achieve this by training a VAD-alike neural network that is conditioned on the target speaker embedding or the speaker verification score. For every frame, personal VAD outputs the scores for three classes: non-speech, target speaker speech, and non-target speaker speech. With our optimal setup, we are able to train a 130KB model that outperforms a baseline system where individually trained standard VAD and speaker recognition network are combined to perform the same task.

show abstract

Section: Introductionmentioning

confidence: 99%

Personal VAD: Speaker-Conditioned Voice Activity Detection

Moreno¹,

Wan²,

Wang³

et al. 2020

The Speaker and Language Recognition Workshop (Odyssey 2020)

View full text Add to dashboard Cite

show abstract

“…Several prior works have focused on find-ing better discriminative features for supervised classification [14]- [20]. For instance in [17] the authors suggest a combination of MFCCs and Gabor features. In [21] the authors suggest the use of source and filter based features and perform a score level fusion.…”

Section: Related Work On Supervised Speech Activity Detectionmentioning

confidence: 99%

Temporarily-Aware Context Modeling Using Generative Adversarial Networks for Speech Activity Detection

Fernando

Sridharan

McLaren

et al. 2020

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This paper presents a novel framework for Speech Activity Detection (SAD). Inspired by the recent success of multitask learning approaches in the speech processing domain, we propose a novel joint learning framework for SAD. We utilise generative adversarial networks to automatically learn a loss function for joint prediction of the frame-wise speech/ nonspeech classifications together with the next audio segment. In order to exploit the temporal relationships within the input signal, we propose a temporal discriminator which aims to ensure that the predicted signal is temporally consistent. We evaluate the proposed framework on multiple public benchmarks, including NIST OpenSAT' 17, AMI Meeting and HAVIC, where we demonstrate its capability to outperform state-of-the-art SAD approaches. Furthermore, our cross-database evaluations demonstrate the robustness of the proposed approach across different languages, accents, and acoustic environments.

show abstract

“…Traditionally, SAD is formulated as a statistical hypothesis test employing probabilistic models, such as Gaussians, mixtures of Gaussians, or Laplacian distributions [6,10,11,12]. During the last decade, however, deep neural networks (DNNs) have achieved impressive results on some of the more taxing SAD tasks, outperforming the traditional approaches [8,13,14].…”

Section: Introductionmentioning

confidence: 99%

Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments

2020

View full text Add to dashboard Cite

Speech activity detection (SAD), which often rests on the fact that the noise is "more" stationary than speech, is particularly challenging in non-stationary environments, because the time variance of the acoustic scene makes it difficult to discriminate speech from noise. We propose two approaches to SAD, where one is based on statistical signal processing, while the other utilizes neural networks. The former employes sophisticated signal processing to track the noise and speech energies and is meant to support the case for a resource efficient, unsupervised signal processing approach. The latter introduces a recurrent network layer that operates on short segments of the input speech to do temporal smoothing in the presence of non-stationary noise. The systems are tested on the Fearless Steps challenge, which consists of the transmission data from the Apollo-11 space mission. The statistical SAD achieves comparable detection performance to earlier proposed neural network based SADs, while the neural network based approach leads to a decision cost function of 1.07 % on the evaluation set of the 2020 Fearless Steps Challenge, which sets a new state of the art.

show abstract

All for one: feature combination for highly channel-degraded speech activity detection

Cited by 24 publications

References 11 publications

Personal VAD: Speaker-Conditioned Voice Activity Detection

Personal VAD: Speaker-Conditioned Voice Activity Detection

Temporarily-Aware Context Modeling Using Generative Adversarial Networks for Speech Activity Detection

Statistical and Neural Network Based Speech Activity Detection in Non-Stationary Acoustic Environments

Contact Info

Product

Resources

About