Multi-sensor neural-network processing of noisy speech.

A Hussain

doi:10.1142/s0129065799000496

Home/Archive/PubMed

PubMed · 10630479

Multi-sensor neural-network processing of noisy speech.

A Hussain

View original source ↗Export metadata ↓

Abstract

In this paper, a novel Artificial Neural-Network (ANN) based multi-sensor multi-band adaptive signal-processing scheme is described for enhancing acoustic-speech corrupted by real noise and reverberation. Numerically robust adaptation-algorithms are employed for the ANN based sub-band filters; and, new simulation experiments are reported using real-reverberant automobile data which demonstrate that the proposed speech-enhancement system is capable of outperforming conventional linear filtering-based wide-band and multi-band noise-cancellation schemes.

Explore related subjects

Acoustic Stimulation Algorithms Auditory Cortex Automobiles Computer Simulation Humans Neural Networks, Computer Noise Nonlinear Dynamics Signal Processing, Computer-Assisted Speech Perception Journal Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

A Hussain. 1999. Multi-sensor neural-network processing of noisy speech.. https://doi.org/10.1142/s0129065799000496

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2008

Sensory filtering phenomenology in PTSD.

Disrupted sensory filtering, or problems with suppressing irrelevant environmental sensory stimuli, has been reported in individuals with posttraumatic stress disorder (PTSD). However, the relationship of sensory filtering deficits to specific PTSD symptoms versus an association with general trauma exposure is unclear. These relationships were examined by administering self-report measures of trauma exposure, PTSD, and sensory gating phenomenology to undergraduate participants with PTSD (n=32), with trauma history but without PTSD (n=144), and with minimal trauma history (n=153). Subjects with PTSD reported greater filtering disruption than individuals in the trauma only and low trauma groups, who did not differ. Individuals endorsing reexperiencing and numbing symptoms, and females endorsing hypervigilance, reported disrupted sensory filtering phenomenology. These results suggest that impaired filtering differentiates between individuals with PTSD symptoms and asymptomatic individuals exposed to multiple traumas and low-trauma controls.

Acoustic Stimulation↗

PubMed2007

Hypoglycemia reduces the blood-oxygenation level dependent signal in primary auditory and visual cortex: a functional magnetic resonance imaging study.

Studies of the effects of hypoglycemia on the brain using neurocognitive testing have suggested that mainly complex functions subserved by secondary and tertiary cortex are affected by mild to moderate hypoglycemia and that intensively treated patients with Type I diabetes mellitus (T1DM) may have altered sensitivity to the central nervous system effects of hypoglycemia. Functional magnetic resonance imaging provides a sensitive, regionally-specific probe of possible neurophysiologic changes related to hypoglycemia in the brain. Eleven intensively-treated T1DM patients and 11 matched non-diabetic controls took part in a 2-day protocol in which functional magnetic resonance imaging (MRI) was used to measure changes in the patterns of brain activation produced by simple auditory and visual stimuli in different conditions. On one day, participants were euglycemic the entire time. On the other day, an initial 50-min euglycemic period was followed by a 50-min hypoglycemic period. Results indicated that hypoglycemia reduced the amplitude of the blood-oxygenation level dependent response in primary auditory and visual cortex to simple auditory and visual stimuli. The latency and duration of the transient hemodynamic response function were not affected. Responses to hypoglycemia were similar in diabetic and non-diabetic participants. These results suggest that mild to moderate hypoglycemia may alter the balance of blood flow and oxygen extraction when glucose levels are lowered. Intensively-treated T1DM, with its attendant frequent hypoglycemic episodes, did not seem to alter hypoglycemic responses in primary visual and auditory cortex.

Acoustic Stimulation↗

PubMed2007

Song discrimination learning in zebra finches induces highly divergent responses to novel songs.

Perceptual biases can shape the evolution of signal form. Understanding the origin and direction of such biases is therefore crucial for understanding signal evolution. Many animals learn about species-specific signals. Discrimination learning using simple stimuli varying in one dimension (e.g. amplitude, wavelength) can result in perceptual biases with preferences for specific novel stimuli, depending on the stimulus dimensions. We examine how this translates to discrimination learning involving complex communication signals; birdsongs. Zebra finches (Taeniopygia guttata) were trained to discriminate between two artificial songs, using a Go/No-Go procedure. The training songs in experiment 1 differed in the number of repeats of a particular element. The songs in experiment 2 differed in the position of an odd element in a series of repeated elements. We examined generalization patterns by presenting novel songs with more or fewer repeated elements (experiment 1), or with the odd element earlier or later in the repeated element sequence (experiment 2). Control birds were trained with only one song. The generalization curves obtained from (i) control birds, (ii) experimental birds in experiment 1, and (iii) experimental birds in experiment 2 showed large and systematic differences from each other. Birds in experiment 1, but not 2, responded more strongly to specific novel songs than to training songs, showing 'peak shift'. The outcome indicates that learning about communication signals may give rise to perceptual biases that may drive signal evolution.

Acoustic Stimulation↗