Soft Mask Methods for Single-Channel Speaker Separation

By Aarthi M. Reddy, Bhiksha Raj. 2007

137 citations recorded by the source corpus.

Subfields: Computational Mechanics, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Signal Processing

Citations in the corpus

SEANet: A Multi-modal Speech Enhancement Network (2020, neutral): “Traditional signal processing methods adopt spectral noise subtraction [1, 2], spectral masking [3, 4], statistical methods based on Wiener ﬁltering [5] and Bayesian estimators [6, 7].”
On the optimality of ideal binary time-frequency masks (2008, background): “Partly due to this claim, many recent computational systems have used the IBM as a measure of ceiling performance for sound source separation (Li et al., 2006; Kim et al., 2006; Harding et al., 2006; Radfar et al., 2007; Deshmukh et al., 2007; Reddy and Raj, 2007).”
On Training Targets for Supervised Speech Separation (2014, methodology): “For example, techniques in [14], [26] build probabilistic interaction models between different sources based on learned priors, and show signi ﬁ cant performance gain in low SNR conditions.”
Deep neural networks for single channel source separation (2013, methodology): “The training data can be modeled using probabilistic models such as Gaussian mixture model (GMM) [1, 2, 3], hidden Markov model (HMM) or factorial HMM [4, 5, 6].”
The Conversation: Deep Audio-Visual Speech Enhancement (2018, unknown): “by using voice characteristics of a known speaker [3, 4, 5, 6, 7].”
A Tandem Algorithm for Pitch Estimation and Voiced Speech Segregation (2010, methodology): “We have suggested that the IBM is a reasonable goal for CASA [16], [37], and it has since been used as a measure of ceiling performance for speech separation [26], [31], [32].”