A fundamental problem in auditory and speech processing is the segregation of speech from concurrent sounds. This problem has been a focus of study in computational auditory scene analysis (CASA), and it has also been recently investigated from the perspective of blind source separation. Using a standard corpus of voiced speech mixed with interfering sounds, we report a comparison between CASA ...

For speech segregation, a blind separation model (BSS) is tested together with a CASA model which is based on the localisation cue and the evaluation of the time delay of arrival (TDOA). The test database is composed of 332 binary mixture sentences recorded in stereo with a static set-up. These are truncated at 1 second for the simulations. For applying the two models, we cut the frequency doma...

The Residue-Driven Architecture presented here is a model of auditory stream segregation from input sounds. A subsystem to extract auditory streams by using some sound attributes is called an agency and the design of each agency is based on the residue-driven architecture. This architecture consists of three kinds of agents: an event-detector, a tracergenerator, and tracers. The event-detector ...

This case describes the implementation and subsequent failure of an innovative system installed in the bars of Alvalade XXI, the recently built football stadium in Lisbon, Portugal. Casa XXI, the company running the bars, had entrusted the project to an IT supplier who had limited experience with large systems. During the inauguration, the system failed spectacularly creating a chaotic situatio...

Online tracking of speakers is an important task for applications in smart environments such as camera control, meeting annotation and speech separation. Challenges for an audio-only system are small-room reverberation, noise, the unknown number of speakers, and gaps occurring in natural speech. Combining models from neurobiology and cognitive psychology with many-channel signal processing and ...

For speech segregation, a recurrent blind separation model (BSS) is tested together with a CASA model, which is based on the localisation cue and the evaluation of the time delay of arrival (TDOA). The test database is composed of 332 binary mixture sentences recorded in stereo with a static set-up. These are truncated at 1 second for the simulations. For applying the two models, we cut the fre...

We propose and test a cocktail-party recognition technique based on segregation applied before recognition. This CASA front-end uses the TDOA (Time Delay Of Arrival) evaluated within subbands in order to determine the Relative Level (RL) of two competing speech sources. To perform the evaluation of the model, we have recorded a stereo database ST-NB95 from the mono Numbers95. This is composed o...

A challenging problem for research in computational auditory scene analysis is the integration of evidence derived from multiple grouping principles. We describe a computational model which addresses this issue through the use of a `blackboard' architecture. The model integrates evidence from multiple grouping principles at several levels of abstraction, and manages competition between principl...

An algorithm is proposed which calculates a computationally efficient approximation of a certain physiologically-motivated representation for sound, called the summary autocorrelation function. This representation has been found very useful in several tasks, such as sound separation, multiple period estimation, and computational auditory scene analysis. However, it has been computationally too ...

CASA is the technique used to segregate a target speech from a monaural mixture. This article proposes a technique to separate the sinusoidal noise from monaural mixtures. Many sounds are there that are important to humans are having pseudo-periodic structure over a particular period /stretch of time. Where this fixed period is typically range of 100Hz-5KHz which gives the corresponding pitch p...