The Cocktail Party Problem

Abstract

This review presents an overview of a challenging problem in auditory perception, the cocktail party phenomenon, the delineation of which goes back to a classic paper by Cherry in 1953. In this review, we address the following issues: (1) human auditory scene analysis, which is a general process carried out by the auditory system of a human listener; (2) insight into auditory perception, which is derived from Marr's vision theory; (3) computational auditory scene analysis, which focuses on specific approaches aimed at solving the machine cocktail party problem; (4) active audition, the proposal for which is motivated by analogy with active vision, and (5) discussion of brain theory and independent component analysis, on the one hand, and correlative neural firing, on the other.

On Analysis and Evaluation of Cocktail Party Effect on Applied Educational Practice Theory Using Neural Networks Modeling.

“…Historically, this CCP observed at cocktail party phenomenon, the delineation of which goes back to a classic paper by Cherry in 1953 [37] [38]. In this section , it is worthy to address the following issues associated to CCP : (1) human auditory scene analysis, which is a general process carried out by the auditory system of a human listener; (2) insight into auditory perception, which is derived from Marr's vision theory; (3) computational auditory scene analysis, which focuses on specific approaches aimed at solving the machine cocktail party problem; (4) active audition, the proposal for which is motivated by analogy with active vision, and (5) discussion of brain theory and independent component analysis, on the one hand, and correlative neural firing, on the other [39].Interestingly, the ability to maintain a conversation with one person while at a noisy cocktail party has often been used to illustrate a general characteristic of auditory selective attention, namely that perceivers' attention is usually directed to a particular set of sounds and not to others [40] [41]. Part of the cocktail party problem involves parsing co-occurring speech sounds and simultaneously integrating these various speech tokens into meaningful units ("auditory scene analysis").That auditory scene analysis framework to be neurobiologically feasible, it would have to accommodate the ability to switch the focus of attention from one speech signal of interest to another and do so with relative ease [39].…”

An exploration of eliminating cross-talk in surface electromyography using independent component analysis

“…The "cocktail party problem" is the common analogy used when describing the use of ICA [9]. Take for example a group people speaking simultaneously at one side of the room and two people listening in two separate locations at the opposite side of the room.…”

Latent semantics as cognitive components

“…Or similarly using a sparse constrained NMF non-negative matrix factorization, allow for retrieving a part-based representation of facial features from a linear mixture of statistically independent contexts [11]. However, such a retrieval of independent components may only partly resemble how we cognitively overcome challenges like the `cocktail party problem' of carrying on a conversation threatened to be overshadowed by other voices [12], as our brains are able to pick out a stream of particular interest based on embodied cognitive processes boosting the signal to noise ratio. In essence by top-down applying selective attention to switch between cross-correlated segregated features, which when subsequently grouped form a perceived outline similar to what makes a figure stand out from the background in an image [13].…”