on the Recognition of Speech, with

By E. C. Cmm. 2008

How researchers see this paper

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

1. Yi Luo
2. Dong Yu
3. Yoshua Bengio
4. Shinji Watanabe
5. Zhuo Chen
6. Kristen Grauman
7. Lior Wolf
8. Jinyu Li

Citations in the corpus

• On the Binding Problem in Artificial Neural Networks (2020, background): “For example, auditory objects may correspond to different sources of sound, such as speakers talking simultaneously in the same room (cocktail-party problem; Cherry, 1953).”
• Audio-Visual Scene Analysis with Self-Supervised Multisensory Features (2018, background): “separating the individual sound sources in an audio stream — also known as the cocktail party problem [28] — is a classic audio-understanding task [29].”
• Multitalker Speech Separation With Utterance-Level Permutation Invariant Training of Deep Recurrent Neural Networks (2017, methodology): “Since the cocktail party problem was initially formalized [3], a large number of potential solutions have been proposed [5], and the most popular techniques originate from the field of Computational Auditory Scene Analysis (CASA) [6]–[10].”
• Permutation invariant training of deep models for speaker-independent multi-talker speech separation (2016, background): “Oespite the significant progress made in dietating single-speaker speech in the recent years [1, 2, 3, 4] , the progress made in multitalker mixed speech separation and recognition, often referred to as the cocktail-party problem [5, 6] , has been less impressive.”
• Emotion and cognition: insights from studies of the human amygdala. (2006, background): “An early example of this is the classic " cocktail party effect " described by Cherry (1953), in which an emotionally significant item, such as the subject's name, was noticed even when it was presented among a stream of unattended stimuli during an attentionally demanding dichotic listening task.”
• Emergence of neural encoding of auditory objects while listening to competing speakers (2012, background): “For example, in the classic “cocktail party problem,” where multiple speakers are talking at the same time (9), human listeners can selectively attend to a chosen target speaker, even if the competing speakers are acoustically more salient (e.”
• 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].”
• I, me, mine: Automatic attentional capture by self-related stimuli (2012, background): “The idea that self-related stimuli are prioritized by the cognitive system is reminiscent of the so-called “cocktail party effect” (Cherry, 1953).”
• Understanding intuition: The case for two forms of intuition (2012, background): “What is in focus requires focal attention and that kind of attention can be paid only to one thing at a time (Anderson, 2000; Broadbent, 1958; Cherry, 1953; Deutsch and Deutsch, 1963; Sullivan, 1976; Treisman, 1964).”
• Does working memory training generalize (2010, background): “Finally, the dichotic listening task (Cherry, 1953; Moray, 1959) requires participants to verbally shadow words that are spoken into one ear while ignoring what is said in the other.”
• Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals (2020, background): “This type of problem is called the cocktail party problem [7, 3].”
• Speech recognition in adverse conditions: A review (2012, background): “Greater interference is observed with semantically noticeable distractors (cf. cocktail party effect, Cherry 1953), with babble noise made of intelligible talkers (e.g., Simpson & Cooke, 2005), and with native rather than non-native interfering speech (e.g., Van Engen & Bradlow, 2007; although see…”
• The restless mind. (2006, background): “First, during dichotic listening, attention is rapidly and efficiently drawn to both self-relevant stimuli (Bargh, 1982; Klinger, 1978) and goal-relevant information (Gollwitzer & Bargh, 1996), in a manner similar to the cocktail party effect (Cherry, 1953).”
• Dividing attention in the classroom reduces exam performance (2018, background): “For example, when more than one person is speaking, while listening to one person speak a listener hears nothing of what the other speaker is saying (Cherry, 1953; Wood & Cowan, 1995).”
• DEEP ATTRACTOR NETWORK FOR SINGLE-MICROPHONE SPEAKER SEPARATION (2016, background): “Two main difficulties hinder the efficacy of deep learning algorithms to tackle the famous “cocktail party problem”[7].”
• What Happened to My Dog in That Network: Unraveling Top-down Generators in Convolutional Neural Networks (2015, background): “The demonstrated role of top-down information in human perception (Stroop, 1935; Cherry, 1953; Hill & Johnston, 2007; Ames Jr, 1951) provides a suggestive indication of the role that top-down information could play in deep learning.”
• Effects of Attention on Neuroelectric Correlates of Auditory Stream Segregation (2006, background): “For example, a listener at a cocktail party must process speech from one person while other speakers are talking (Cherry, 1953).”
• Mechanisms Underlying Selective Neuronal Tracking of Attended Speech at a ‘Cocktail Party’ (2013, background): “of Attended Speech at a ‘‘Cocktail Party’’ Elana M. Zion Golumbic,1,4 Nai Ding,5,6 Stephan Bickel,7,8 Peter Lakatos,4 Catherine A. Schevon,2 Guy M. McKhann,3 Robert R. Goodman,3 Ronald Emerson,2 Ashesh D. Mehta,7,8 Jonathan Z. Simon,5,6 David Poeppel,9 and Charles E. Schroeder1,4,* 1Department of…”