UMD Theses and Dissertations

Permanent URI for this collectionhttp://hdl.handle.net/1903/3

New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a given thesis/dissertation in DRUM.

More information is available at Theses and Dissertations at University of Maryland Libraries.

Browse

Subject: search.filters.subject.cocktail party problem

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    CORTICAL REPRESENTATION OF SPEECH IN COMPLEX AUDITORY ENVIRONMENTS AND APPLICATIONS
    (2017) Puvvada, Venkata Naga Krishna Chaitanya; Simon, Jonathan Z; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Being able to attend and recognize speech or a particular sound in complex listening environments is a feat performed by humans effortlessly. The underlying neural mechanisms, however, remain unclear and cannot yet be emulated by artificial systems. Understanding the internal (cortical) representation of external acoustic world is a key step in deciphering the mechanisms of human auditory processing. Further, understanding neural representation of sound finds numerous applications in clinical research for psychiatric disorders with auditory processing deficits such as schizophrenia. In the first part of this dissertation, cortical activity from normal hearing human subjects is recorded, non-invasively, using magnetoencephalography in two different real-life listening scenarios. First, when natural speech is distorted by reverberation as well as stationary additive noise. Second, when the attended speech is degraded by the presence of multiple additional talkers in the background, simulating a cocktail party. Using natural speech affected by reverberation and noise, it was demonstrated that the auditory cortex maintains both distorted as well as distortion-free representations of speech. Additionally, we show that, while the neural representation of speech remained robust to additive noise in absence of reverberation, noise had detrimental effect in presence of reverberation, suggesting differential mechanisms of speech processing for additive and reverberation distortions. In the cocktail party paradigm, we demonstrated that primary like areas represent the external auditory world in terms of acoustics, whereas higher-order areas maintained an object based representation. Further, it was demonstrated that background speech streams were represented as an unsegregated auditory object. The results suggest that object based representation of auditory scene emerge in higher-order auditory cortices. In the second part of this dissertation, using electroencephalographic recordings from normal human subjects and patients suffering from schizophrenia, it was demonstrated, for the first time, that delta band steady state responses are more affected in schizophrenia patients compared with healthy individuals, contrary to the prevailing dominance of gamma band studies in literature. Further, the results from this study suggest that the inadequate ability to sustain neural responses in this low frequency range may play a vital role in auditory perceptual and cognitive deficit mechanisms in schizophrenia. Overall this dissertation furthers current understanding of cortical representation of speech in complex listening environments and how auditory representation of sounds is affected in psychiatric disorders involving aberrant auditory processing.
  • Thumbnail Image
    Item
    Neuromorphic model for sound source segregation
    (2015) Krishnan, Lakshmi; Shamma, Shihab; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    While humans can easily segregate and track a speaker's voice in a loud noisy environment, most modern speech recognition systems still perform poorly in loud background noise. The computational principles behind auditory source segregation in humans is not yet fully understood. In this dissertation, we develop a computational model for source segregation inspired by auditory processing in the brain. To support the key principles behind the computational model, we conduct a series of electro-encephalography experiments using both simple tone-based stimuli and more natural speech stimulus. Most source segregation algorithms utilize some form of prior information about the target speaker or use more than one simultaneous recording of the noisy speech mixtures. Other methods develop models on the noise characteristics. Source segregation of simultaneous speech mixtures with a single microphone recording and no knowledge of the target speaker is still a challenge. Using the principle of temporal coherence, we develop a novel computational model that exploits the difference in the temporal evolution of features that belong to different sources to perform unsupervised monaural source segregation. While using no prior information about the target speaker, this method can gracefully incorporate knowledge about the target speaker to further enhance the segregation.Through a series of EEG experiments we collect neurological evidence to support the principle behind the model. Aside from its unusual structure and computational innovations, the proposed model provides testable hypotheses of the physiological mechanisms of the remarkable perceptual ability of humans to segregate acoustic sources, and of its psychophysical manifestations in navigating complex sensory environments. Results from EEG experiments provide further insights into the assumptions behind the model and provide motivation for future single unit studies that can provide more direct evidence for the principle of temporal coherence.
  • Thumbnail Image
    Item
    SEGREGATION OF SPEECH SIGNALS IN NOISY ENVIRONMENTS
    (2011) Vishnubhotla, Srikanth; Espy-Wilson, Carol Y; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)
    Automatic segregation of overlapping speech signals from single-channel recordings is a challenging problem in speech processing. Similarly, the problem of extracting speech signals from noisy speech is a problem that has attracted a variety of research for several years but is still unsolved. Speech extraction from noisy speech mixtures where the background interference could be either speech or noise is especially difficult when the task is to preserve perceptually salient properties of the recovered acoustic signals for use in human communication. In this work, we propose a speech segregation algorithm that can simultaneously deal with both background noise as well as interfering speech. We propose a feature-based, bottom-up algorithm which makes no assumptions about the nature of the interference or does not rely on any prior trained source models for speech extraction. As such, the algorithm should be applicable for a wide variety of problems, and also be useful for human communication since an aim of the system is to recover the target speech signals in the acoustic domain. The proposed algorithm can be compartmentalized into (1) a multi-pitch detection stage which extracts the pitch of the participating speakers, (2) a segregation stage which teases apart the harmonics of the participating sources, (3) a reliability and add-back stage which scales the estimates based on their reliability and adds back appropriate amounts of aperiodic energy for the unvoiced regions of speech and (4) a speaker assignment stage which assigns the extracted speech signals to their appropriate respective sources. The pitch of two overlapping speakers is extracted using a novel feature, the 2-D Average Magnitude Difference Function, which is also capable of giving a single pitch estimate when the input contains only one speaker. The segregation algorithm is based on a least squares framework relying on the estimated pitch values to give estimates of each speaker's contributions to the mixture. The reliability block is based on a non-linear function of the energy of the estimates, this non-linear function having been learnt from a variety of speech and noise data but being very generic in nature and applicability to different databases. With both single- and multiple- pitch extraction and segregation capabilities, the proposed algorithm is amenable to both speech-in-speech and speech-in-noise conditions. The algorithm is evaluated on several objective and subjective tests using both speech and noise interference from different databases. The proposed speech segregation system demonstrates performance comparable to or better than the state-of-the-art on most of the objective tasks. Subjective tests on the speech signals reconstructed by the algorithm, on normal hearing as well as users of hearing aids, indicate a significant improvement in the perceptual quality of the speech signal after being processed by our proposed algorithm, and suggest that the proposed segregation algorithm can be used as a pre-processing block within the signal processing of communication devices. The utility of the algorithm for both perceptual and automatic tasks, based on a single-channel solution, makes it a unique speech extraction tool and a first of its kind in contemporary technology.