Deep belief networks based voice activity detection
Fusing the advantages of multiple acoustic features is important for the robustness of voice
activity detection (VAD). Recently, the machine-learning-based VADs have shown a …
activity detection (VAD). Recently, the machine-learning-based VADs have shown a …
DeepMMSE: A deep learning approach to MMSE-based noise power spectral density estimation
Q Zhang, A Nicolson, M Wang… - … /ACM Transactions on …, 2020 - ieeexplore.ieee.org
An accurate noise power spectral density (PSD) tracker is an indispensable component of a
single-channel speech enhancement system. Bayesian-motivated minimum mean-square …
single-channel speech enhancement system. Bayesian-motivated minimum mean-square …
Boosting contextual information for deep neural network based voice activity detection
Voice activity detection (VAD) is an important topic in audio signal processing. Contextual
information is important for improving the performance of VAD at low signal-to-noise ratios …
information is important for improving the performance of VAD at low signal-to-noise ratios …
Features for voice activity detection: a comparative analysis
S Graf, T Herbig, M Buck, G Schmidt - EURASIP Journal on Advances in …, 2015 - Springer
In many speech signal processing applications, voice activity detection (VAD) plays an
essential role for separating an audio stream into time intervals that contain speech activity …
essential role for separating an audio stream into time intervals that contain speech activity …
End-to-end active speaker detection
Recent advances in the Active Speaker Detection (ASD) problem build upon a two-stage
process: feature extraction and spatio-temporal context aggregation. In this paper, we …
process: feature extraction and spatio-temporal context aggregation. In this paper, we …
A study of voice activity detection techniques for NIST speaker recognition evaluations
MW Mak, HB Yu - Computer Speech & Language, 2014 - Elsevier
Since 2008, interview-style speech has become an important part of the NIST speaker
recognition evaluations (SREs). Unlike telephone speech, interview speech has lower …
recognition evaluations (SREs). Unlike telephone speech, interview speech has lower …
Voice activity detection based on an unsupervised learning framework
How to construct models for speech/nonspeech discrimination is a crucial point for voice
activity detectors (VADs). Semi-supervised learning is the most popular way for model …
activity detectors (VADs). Semi-supervised learning is the most popular way for model …
Enabling voice-accompanying hand-to-face gesture recognition with cross-device sensing
Gestures performed accompanying the voice are essential for voice interaction to convey
complementary semantics for interaction purposes such as wake-up state and input …
complementary semantics for interaction purposes such as wake-up state and input …
An end-to-end multimodal voice activity detection using wavenet encoder and residual networks
I Ariav, I Cohen - IEEE Journal of Selected Topics in Signal …, 2019 - ieeexplore.ieee.org
Recently, there has been growing use of deep neural networks in many modern speech-
based systems such as speaker recognition, speech enhancement, and emotion …
based systems such as speaker recognition, speech enhancement, and emotion …
Reducing f0 frame error of f0 tracking algorithms under noisy conditions with an unvoiced/voiced classification frontend
In this paper, we propose an F0 Frame Error (FFE) metric which combines Gross Pitch Error
(GPE) and Voicing Decision Error (VDE) to objectively evaluate the performance of …
(GPE) and Voicing Decision Error (VDE) to objectively evaluate the performance of …