One Microphone Source Separation

By Sam T. Roweis. 2000

507 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (2018, background): “Researchers have proposed many successful probabilistic approaches to this problem [30,31,32,33].”
Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals (2020, background): “In reality, the observed data contains various entangled components, making the one-to-many sequence transduction for mixture signals a common problem in machine learning [35, 16, 30].”
Cocktail Party Processing via Structured Prediction (2012, background): “Model-based methods (e.g., [3]) work well in constrained environments, and source models need to be trained in advance.”
On Ideal Binary Mask As the Computational Goal of Auditory Scene Analysis (2005, background): “single utterance tends to be sparsely distributed (Jourjine et al., 2000; Roweis, 2001 ).”
A Supervised Learning Approach to Monaural Segregation of Reverberant Speech (2009, background): “One example is the spectral learning approach which is based on parameterized aﬃn-ity matrices built from low-level features and solves the separation problem by formulating it as segmentation in a time-frequency (T-F) plane [4].”
VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency (2021, background): “While early work assumes access to multiple microphones to facilitate separation [53, 78, 18], some methods tackle the “blind” separation problem with monaural audio [65, 68, 69], including recent deep learning approaches [37, 73, 33, 40, 48].”
Multiband audio modeling for single-channel acoustic source separation (2004, methodology): “In [1], 8000 states HMMs were built for two different speakers.”
A General Flexible Framework for the Handling of Prior Information in Audio Source Separation (2012, background): “There are also many works on NMF and its extensions [33]–[38] and on GMMs/HMMs [39], [40] based on nongaussian models of the complex-valued STFT coefficients.”
Energy Disaggregation via Discriminative Sparse Coding (2010, methodology): “The algorithmic approach we present in this paper builds upo n sparse coding methods and recent work in single-channel source separation [24, 23, 22].”
PhaseNet: Discretized Phase Modeling with Deep Neural Networks for Audio Source Separation (2018, methodology): “The estimation is achieved by explicit modeling of target magnitude spectrograms [1–8] or by estimating time-frequency (TF) masks [9–14].”
Single-channel speech separation using sparse non-negative matrix factorization (2006, methodology): “It has been suggested by Roweis [1] to use a factorial HMM to separate mixed speech.”
Soft Mask Methods for Single-Channel Speaker Separation (2007, methodology): “In the process, we also avoid several of the assumptions and approximations common in statistical mask estimation methods, e.g., Roweis [21] and Reyes-Gomez et al. [16] approximate the distribution of the maximum of two log-normal random variables by a log normal.”
Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation (2012, background): “Due to their ability to capture complex aggregate signals via a compact structure, such models have found applications in areas as speech recognition (Virtanen, 2006), audio separation (Roweis, 2001), and pitch tacking (Bach and Jordan, 2005).”
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].”
Monaural Sound Source Separation by Nonnegative Matrix Factorization With Temporal Continuity and Sparseness Criteria (2007, background): “extract only the most prominent source [1], [2], or which utilize prior information of the source signals [3], [4].”
Exploring Monaural Features for Classification-Based Speech Segregation (2013, background): “Algorithms such as [19], [27], [28] can work well if the statistical properties of the observations correspond well to training conditions.”