Book Review: Auditory Scene Analysis: The Perceptual Organization of Sound

By Quentin Summerfield. 1992

How researchers see this paper

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

1. Dong Yu
2. Jinyu Li
3. Shinji Watanabe
4. Yoshua Bengio
5. Zhuo Chen
6. Deliang Wang
7. Li Deng
8. Kristen Grauman

Citations in the corpus

• On the Binding Problem in Artificial Neural Networks (2020, background): “, 1998; Palmer, 1992; Palmer and Rock, 1994), including for other sensory modalities, such as audio (Bregman, 1994) and tactile (Gallace and Spence, 2011).”
• 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].”
• Permutation invariant training of deep models for speaker-independent multi-talker speech separation (2016, background): “Despite the significant progress made in dictating 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.”
• Exploring Monaural Features for Classification-Based Speech Segregation (2013, background): “Computational auditory scene analysis (CASA), which is inspired by Bregman’s account of auditory scene analysis (ASA) [2], has shown considerable promise in the last decade.”
• An Overview of Speaker Identification: Accuracy and Robustness Issues (2011, background): “Initially formulated as a technique for recovering partially occluded objects in image recognition [69], the missing data approach has a conceptual relationship with the human auditory system and its ability to process corrupted speech signals [70], [71].”
• The Infant's Auditory World: Hearing, Speech, and the Beginnings of Language (2007, background): “The latter stage of processing is known as sound source segregation or auditory scene analysis (Bregman, 1990).”
• Chunking in Music by Coarticulation (2010, background): “Such phase-transitions result in the forming, or conversely, the splitting up, of chunks, as has previously been documented in Gestalt theory inspired auditory research (Bregman 1990).”
• New Era for Robust Speech Recognition (2017, methodology): “Multichannel MESSL [5] models every pair of microphones separately using the binaural model described in Sect.”
• The Dynamic Brain: From Spiking Neurons to Neural Masses and Cortical Fields (2008, methodology): “Note that the exact experimental numerical values at which the boundaries occur vary from subject to subject and depend on the experimental methods employed [ 128 ].”
• Multiple fundamental frequency estimation based on harmonicity and spectral smoothness (2003, background): “cally separate a sound in a mixture [1].”
• Learning Spectral Clustering, With Application To Speech Separation (2006, background): “Timbre can be loosely defined as the set of properties of a voiced speech signal once the pitch has been factored out (Bregman, 1990).”
• Deep clustering: Discriminative embeddings for segmentation and separation (2015, background): “Nevertheless human listeners easily perceive separate sources in an acoustic mixture, and this ability has inspired a variety of computational approaches to the so-called auditory scene analysis or cocktail party problem [1].”
• The Perception of Musical Timbre (2008, background): “In general, a given source will produce sounds that are relatively similar in pitch, loudness, timbre, and spatial position from one event to the next (cf. Bregman, 1990; McAdams and Bregman, 1979, for reviews).”
• Perception and Production of Syncopated Rhythms (2007, background): “According to Bregman and Campbell (1971) and Bregman (1990) , regularly recurring auditory”
• Speech recognition with amplitude and frequency modulations. (2005, unknown): “40, 1201–1215. 38. Chen, H. & Zeng, F. G. (2004) J. Acoust. Soc. Am. 116, 2269–2277. 39. Schroeder, M. R., Atal, B. S. & Hall, J. L. (1979) J. Acoust. Soc. Am. 66, 1647–1652. 40. Bregman, A. S. (1994) Auditory Scene Analysis: The Perceptual Organization of Sound (MIT Press, Cambridge, MA).”
• Crossmodal object-based attention: auditory objects affect visual processing. (2005, background): “Kubovy and Van Valkenburg (2001; also see Bregman, 1990) have maintained that for perceiving two auditory objects it is not necessary to have two auditory sources originating from separate spatial locations, as, in their view, frequency separation is a sufficient condition to produce distinct audito”
• Chime-home: A dataset for sound source recognition in a domestic environment (2015, background): “This paper relates to the relatively unexplored CASA task of sound source recognition (SSR) [5], which we define as the task of assigning a set of semantic labels to a given audio recording, based on the sound sources contributing to the acoustic scene (cf. [6]).”
• Speech Perception (2004, background): “The central lesson of work on auditory scene analysis is that ordinary sounds are individuated—they are distinguished from each other at a time, and they are tracked and segmented over time—in the face of highly complex, interwoven acoustic information (Bregman, 1990).”