A temporal warped 2D psychoacoustic modeling for robust speech recognition system

Binaural release from masking in forward-masked intensity discrimination: Evidence for effects of selective attention

“…The auditory mechanism underlying temporal masking is still less well understood than simultaneous masking (e.g., Plack, 1996;Zeng, 1998;Plack et al, 2002;Oberfeld, 2008Oberfeld, , 2009Laback et al, 2011). In applied contexts like audio coding or communication engineering there is still a potential for integrating effects of temporal masking into the models (e.g., Dai and Soon, 2011;Gunawan et al, 2010;Rhebergen et al, 2010).…”

Effect of MFCC Based Features for Speech Signal Alignments

“…For better alignment or matching, normalization of the subband temporal modulation envelopes may be used [17]. The main factors responsible for the stagnation in the fields of speech recognition are environmental noise, channel distortion, and speaker variability [10], [11], [12]. Let us consider simple speech recognition as a pattern matching problem.…”

2D Psychoacoustic modeling of equivalent masking for automatic speech recognition

“…1. Compared with the filters introduced in our previous work [16][17][18], the parameters of the filters (see Table C1) introduced in this paper are positive or zero. Therefore, they are referred to as 'P-filter' and other algorithms will be called 'N-filter' (short for negative filter parameters).…”

“…For example, a person with a healthy auditory system has little difficulty in communicating with other people in a crowded shopping mall, which would be a very challenging task for modern ASR [12][13][14][15]. Therefore, our approach is to analyze and model the human auditory system in order to improve the performance of ASR [14,16,17]. Psychoacoustics is the study of the physical human auditory system, and many of its theories can be applied to artificial systems [6].…”

“…Our previous work goes into depth on how speech signals are processed by the human auditory system and converted to neural spikes, which are then processed by the brain [16][17][18]. The masking effect describes the phenomenon that a clearly audible sound (maskee) becomes weak or inaudible in the presence of another sound (masker).…”