Search results for "Speech recognition"

Joint Alignment and Modeling of Correlated Behavior Streams

2013

The Variable Time-Shift Hidden Markov Model (VTS- HMM) is proposed for learning and modeling pairs of cor- related streams. Unlike previous coupled models for time series, the VTS-HMM accounts for varying time shifts be- tween correlated events in pairs of streams having different properties. The VTS-HMM is learned on a set of pairs of unaligned streams and, thus, learning entails simultaneous estimation of the varying time shifts and of the parameters of the model. The formulation is demonstrated in the analysis of videos of dyadic social interactions between children and adults in the Multimodal Dyadic Behavior Dataset (MMDB). In dyadic social interactions, an agent starts an interaction …

Interaction features for prediction of perceptual segmentation:Effects of musicianship and experimental task

2016

As music unfolds in time, structure is recognised and understood by listeners, regardless of their level of musical expertise. A number of studies have found spectral and tonal changes to quite successfully model boundaries between structural sections. However, the effects of musical expertise and experimental task on computational modelling of structure are not yet well understood. These issues need to be addressed to better understand how listeners perceive the structure of music and to improve automatic segmentation algorithms. In this study, computational prediction of segmentation by listeners was investigated for six musical stimuli via a real-time task and an annotation (non real-tim…

Evaluating the Effect of Stimuli Color and Frequency on SSVEP

2020

Brain&ndash

Do categorical representations modulate early automatic visual processing? A visual mismatch-negativity study.

2021

Perceptual categorization is an important cognitive function. In the auditory domain, categorization already occurs within the first 200 ms of information processing, as indexed by the mismatch negativity. Here, we assessed the characteristics of the visual mismatch negativity (vMMN) elicited during the categorization of previously unknown visual stimuli. To examine this, we used five-dot patterns with characteristics that allow for the formation of categories through rotation and reflection but not through other physical properties. To assess whether or not between-category and within-category vMMN differ in amplitude, the data was analyzed with the Bayesian approach. We observed that both…

Movement Perception in the Colliculus Superior

1977

Summary Neurophysiological measurements on cats' colliculus superior show results which are dependent on the movement of visual stimuli and movement of the background as well as on the movement of stimulus and background n!lative to each other. The movement dependent problems involved in pattern recognition by space time filters as regards resolution of details, distortion and eye movement are outlined in principle.

Visual mismatch negativity (vMMN): a prediction error signal in the visual modality

2015

Frontiers in Human Neuroscience, 8

2015

Previewing distracters enhances the efficiency of visual search. Watson and Humphreys (1997) proposed that the preview benefit rests on visual marking, a mechanism which actively encodes distracter locations at preview and inhibits them afterwards at search. As Watson and Humphreys did, we used a letter-color search task to study constraints of visual marking in conjunction search and near-efficient single-feature search with single-colored and homogeneous distracter letters. Search performance was measured for fixed target and distracter features (block design) and for randomly changed features across trials (random design). In single-feature search there was a full preview benefit for bot…

The effects of interletter spacing in visual-word recognition.

2010

Despite the importance of determining the effects of interletter spacing on visual-word recognition, this issue has often been neglected in the literature. The goal of the present study is to shed some light on this topic. The rationale is that a thin increase in interletter spacing, as in casino, may reduce lateral interference among internal letters without destroying a word's integrity and/or allow a more precise encoding of a word's letter positions. Here we examined whether identification times for word stimuli in a lexical decision task were faster when the target word had a slightly wider than default interletter spacing value relative to the default settings (e.g., casino vs. casino…

Neighborhood Effects in Visual Word Recognition and Reading

2015

Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions

2010

The choice of hidden non-linearity in a feed-forward multi-layer perceptron (MLP) architecture is crucial to obtain good generalization capability and better performance. Nonetheless, little attention has been paid to this aspect in the ASR field. In this work, we present some initial, yet promising, studies toward improving ASR performance by adopting hidden activation functions that can be automatically learned from the data and change shape during training. This adaptive capability is achieved through the use of orthonormal Hermite polynomials. The “adaptive” MLP is used in two neural architectures that generate phone posterior estimates, namely, a standalone configuration and a hierarch…