This paper reports the preliminary results of experiments on listening to several sounds at once. Two issues are addressed: segregating speech streams from a mixture of sounds, and interfacing speech stream segregation with automatic speech recognition (ASR). Speech stream segregation (SSS) is modeled as a process of extracting harmonic fragments, grouping these extracted harmonic fragments, an...

A recent finding of the inability of listeners to judge the order of three or four nonspeech sounds presented in a repetitive cycle is explained by the concept of stream segregation. Two experiments showed that at high presention rates of a short cycle of six tones (three high and three low), 5s invariably segregated the tone sequences into streams based on frequency and could perceive only tho...

A general assumption underlying auditory scene analysis is that the initial grouping of acoustic elements is independent of attention. The effects of attention on auditory stream segregation were investigated by recording event-related potentials (ERPs) while participants either attended to sound stimuli and indicated whether they heard one or two streams or watched a muted movie. The stimuli w...

A model of auditory scene analysis is proposed, which incorporates an attentional mechanism and is implemented using a network of neural oscillators. The core of the model is a two-layer neural oscillator network which performs stream segregation and selection on the basis of oscillatory correlation. A stream is represented by a sychronised oscillator population, whereas different streams are r...

A listener is thought to be able to organise musical notes into groups within musical streams/voices. A stream segment is a relatively short coherent sequence of tones that is separated horizontally from co-sounding streams and, vertically from neighbouring musical sequences. This paper presents a novel algorithm that discovers musical stream segments in symbolic musical data. The proposed algo...

The mismatch negativity (MMN), a component of event-related potentials (ERP), was used to investigate the effect of attention on auditory stream segregation. Subjects were presented with sequences of alternating high and low tones that occurred at a constant rate, which they ignored. When subjects ignored the stimuli, the three-tone standard and deviant sequences contained within the high- and ...

Sounds provide us with useful information about our environment which complements that provided by other senses, but also poses specific processing problems. How does the auditory system distentangle sounds from different sound sources? And what is it that allows intermittent sound events from the same source to be associated with each other? Here we review findings from a wide range of studies...

Understanding three simultaneous speeches is proposed as a challenge problem to foster arti cial intelligence, speech and sound understanding or recognition, and computational auditory scene analysis research. Automatic speech recognition under noisy environments is attacked by speech enhancement techniques such as noise reduction and speaker adaptation. However, the signal-to-noise ratio of sp...

Auditory stream segregation involves linking temporally separate acoustic events into one or more coherent sequences. For any non-trivial sequence of sounds, many alternative descriptions can be formed, only one or very few of which emerge in awareness at any time. Evidence from studies showing bi-/multistability in auditory streaming suggest that some, perhaps many of the alternative descripti...