Computational Auditory Scene Analysis: Principles, Algorithms, and Applications

By D. Wang, Guy J. Brown. IEEE Trans. Neural Networks, 2008

1,174 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ee41d30c6c1cf0b553f5a6233ba0104bd2bba19a

How researchers see this paper

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

In Signal Processing

Citations in the corpus

Separate Anything You Describe (2023, positive): “sound separation aims to separate real-world sound recordings into individual source tracks, also known as the “cocktail party problem” [2].”
A Regression Approach to Speech Enhancement Based on Deep Neural Networks (2015, background): “However, due to the binary nature of the IBM, as defined in computational auditory scene analysis (CASA) [29], it offers limited improvements to speech quality even though binary masking has been shown to improve speech intelligibility.”
On the optimality of ideal binary time-frequency masks (2008, positive): “Inspired by ASA, computational auditory scene analysis (CASA) attempts to build monaural and binaural systems that possess the same functionality [2].”
Divide and Conquer: A Deep CASA Approach to Talker-Independent Monaural Speaker Separation (2019, background): “A traditional approach to monaural speech separation is computational auditory scene analysis (CASA) [37], which is inspired by human auditory scene analysis (ASA) mechanisms [3].”
Binaural Classification for Reverberant Speech Segregation Using Deep Neural Networks (2014, background): “Index Terms— Binary classi ﬁ cation, computational auditory scene analysis (CASA), deep neural networks (DNNs), room reverberation, speech segregation.”
End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction (2018, methodology): “…training [1, 2, 6, 7] have dramatically improved the performance of single-channel speaker-independent multi-speaker speech separation, demonstrating overwhelming advantages over previous methods including graphical modeling approaches [8], spectral clustering approaches [9], and CASA methods [10].”
Ideal ratio mask estimation using deep neural networks for robust speech recognition (2013, positive): “Inspired by the remarkable robustness of human listeners, CASA aims to develop speech separation algorithms motivated by the principles of auditory scene analysis [10].”
Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions (2011, background): “In computational auditory scene analysis (CASA) applications, a binary mask is often applied to the noisy speech spectrum to recover the target signal [20] –[23].”
Cracking the cocktail party problem by multi-beam deep attractor network (2017, background): “s entirely relies on the spectral properties of speech, such as pitch continuity, harmonic structures, common onsets etc., and this can be achieved by using statistical models [10], rule-based models [3, 11], or decompositionbased models [12, 13, 14, 15]. In multi-channel systems, the separation pro”
Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification (2017, methodology): “The training label is represented by the IRM, which is computed as in [32] from the T-F representation based on a gammatone filter bank with 64 filters linearly spaced on a Mel frequency scale and with a bandwidth equal to one equivalent rectangular bandwidth [33].”
An Open Dataset for Research on Audio Field Recording Archives: freefield1010 (2013, positive): “Such research may come under the umbrella of “computational auditory scene analysis” (CASA) [Wang and Brown, 2006].”
Joint noise adaptive training for robust automatic speech recognition (2014, methodology): “In such methods, a T-F mask is estimated from the input signal which is then used to enhance the noisy spectrogram (or any other T-F representation that is used) [6].”
Deep Belief Networks Based Voice Activity Detection (2013, background): “Hence, in the future work, we should pay particular attention to the acoustic features that are developed from physical and physiological areas for the diversity between the features [61], [62].”
Supervised Speech Separation Based on Deep Learning: An Overview (2017, positive): “CASA defines the solution to the cocktail party problem as a system that achieves human separation performance in all listening conditions ([140], p.28).”