The cocktail party problem.

By Josh H. McDermott. Current Biology, 2009

690 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Developmental Biology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/69ad0088590f63fd921f9e7e7f6ed911375952a0

How researchers see this paper

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

In Cognitive Neuroscience

In Developmental Biology

In Signal Processing

Citations in the corpus

Separate Anything You Describe (2023, neutral): “Many previous works on sound separation mainly focus on separating one or a few sources, such as in speech enhancement [6], [7], speech separation [8], [9], and music source separation [5].”
Applications of Artificial Intelligence in Machine Learning: Review and Prospect (2015, neutral): “[19]”
Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks (2017, background): “H AVING a conversation in a complex acoustic environment, with multiple noise sources and competing background speakers, is a task humans are remarkably good at [1], [2].”
Self-supervised Audio-visual Co-segmentation (2019, methodology): “Semantic segmentation of images [2, 3] and sound source separation in audio [4, 5, 6, 7] are two important and popular tasks in the computer vision and computational audition communities.”
Deep Learning Techniques for Music Generation - A Survey (2017, background): “39 More generally speaking, audio source separation, sometimes coined as the cocktail party effect, is known to be a very difficult problem, see the original article in [17] and a more recent survey in [68].”
Audio Super Resolution using Neural Networks (2017, background): “Audio processing also raises basic research questions pertaining to time series and generative modeling (Haykin & Chen, 2005; Bilmes, 2004).”
The Sound of Pixels (2018, background): “Sound source separation, also known as the “cocktail party problem” [18,19], is a classic problem in engineering and perception.”
EgoCom: A Multi-Person Multi-Modal Egocentric Communications Dataset (2020, background): “With a single audio source, one must solve the challenging cocktail party problem [5] and with multiple audio input sources, one must solve an often misspecified matrix factorization [6].”
Looking to listen at the cocktail party (2018, neutral): “Isik et al. [2016] and Yu et al. [2017] subsequently introduced methods which successfully use a permutation invariant loss function to train a DNN.”
Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation (2020, background): “Speech separation, often referred to as the cocktail party problem [1, 2], is a fundamental task in signal processing with a wide range of real-world applications, such as separating clean speech from noisy speech signals to improve the accuracy of automatic speech recognition.”
The neural activity of auditory conscious perception (2025, unknown): “…streams and establish which cognitive processes occur at various levels of those streams (Bizley and Cohen, 2013; Bregman, 1990; Christison-Lagay et al., 2015; Griffiths, 2008; Kaas and Hackett, 1999; McDermott, 2010; Micheyl et al., 2007; Razak, 2011; Romanski et al., 1999; Singh, 1987).”