medi_2009_journal_article.bib
@comment{{This file has been generated by bib2bib 1.79}}
@comment{{Command line: bib2bib -ob yeartype\medi_2009_journal_article.bib -c "type = 'journal article'" year\medi_2009.bib}}
@comment{{This file has been generated by bib2bib 1.79}}
@comment{{Command line: bib2bib -ob year\medi_2009.bib -c "year = '2009'" medi.bib}}
@article{Beutelmann:2009P,
type = {journal article},
author = {Beutelmann, Rainer and Brand, Thomas and Kollmeier, Birger},
title = {{P}rediction of binaural speech intelligibility with frequency-dependent interaural phase differences},
journal = {Journal of the Acoustical Society of America},
volume = {126},
number = {3},
pages = {1359-1368},
abstract = {The aim of this study was to test the hypothesis of independent processing strategies in adjacent binaural frequency bands underlying current models for binaural speech intelligibility in complex configurations and to investigate the effective binaural auditory bandwidth in broad-band signals. Speech reception thresholds (SRTs) were measured for binaural conditions with frequency-dependent interaural phase differences (IPDs) of speech and noise. SRT predictions with the binaural speech intelligibility model by Beutelmann and Brand (2006, J. Acoust. Soc. Am. 120, 331-342) were compared with the observed data. The IPDs of speech and noise had a sinusoidal shape on a logarithmic frequency scale. The bandwidth between zeros of the IPD function was varied from 1/8 to 4 octaves. Speech and noise had either the same IPD function (reference condition) or opposite signs of the IPD, function (binaural condition). Each condition had two subconditions with alternating and non-alternating signs, respectively, of the IPD function. The binaural unmasking with respect to the reference condition decreased from 6 dB to zero with decreasing IPD bandwidth for the alternating condition while it stayed significantly larger than zero for the non-alternating condition. The observed results were well predicted by the model with an analysis filter bandwidth of 2.3 equivalent rectangular bandwidths (ERBs). (C) 2009 Acoustical Society of America. [DOI: 10.1121/1.3177266]},
year = {2009}
}
@article{Bräcker:2009SVS,
type = {journal article},
author = {Bräcker, Timo and Hohmann, Volker and Kollmeier, Birger and Schulte, Michael},
title = {{S}imulation und {V}ergleich von {S}prachkodierungsstrategien in {C}ochlea-{I}mplantaten},
journal = {Zeitschrift für Audiologie/Audiological Acoustics},
volume = {48},
number = {4},
pages = {158-169},
year = {2009}
}
@article{Dau:2009A,
type = {journal article},
author = {Dau, Torsten and Ewert, Stephan D. and Oxenham, Andrew J.},
title = {{A}uditory stream formation affects comodulation masking release retroactively},
journal = {Journal of the Acoustical Society of America},
volume = {125},
number = {4},
pages = {2182-2188},
note = {Part 1},
abstract = {Many sounds in the environment have temporal envelope fluctuations that are correlated in different frequency regions. Comodulation masking release (CMR) illustrates how such coherent fluctuations can improve signal detection. This study assesses how perceptual grouping mechanisms affect CMR. Detection thresholds for a 1-kHz sinusoidal signal were measured in the presence of a narrowband (20-Hz-wide) on-frequency masker with or without four comodulated or independent flanking bands that were spaced apart by either 1/6 (narrow spacing) or 1 octave (wide spacing). As expected, CMR was observed for the narrow and wide comodulated flankers. However, in the wide (but not narrow) condition, this CMR was eliminated by adding a series of gated flanking bands after the signal. Control experiments showed that this effect was not due to long-term adaptation or general distraction. The results. are interpreted in terms of the sequence of "postcursor" flanking bands forming a perceptual stream with the original flanking bands, resulting in perceptual segregation of the flanking bands from the masker. The results are consistent with the idea that modulation analysis occurs within, not across, auditory objects, and that across-frequency CMR only occurs if the on-frequency and flanking bands fall within the same auditory object or stream. (c) 2009 Acoustical Society of America. [DOI: 10.1121/1.3082121]},
year = {2009}
}
@article{Dietz:2009L,
type = {journal article},
author = {Dietz, Mathias and Ewert, Stephan D. and Hohmann, Volker},
title = {{L}ateralization of stimuli with independent fine-structure and envelope-based temporal disparities},
journal = {Journal of the Acoustical Society of America},
volume = {125},
number = {3},
pages = {1622-1635},
abstract = {Psychoacoustic experiments were conducted to investigate the role and interaction of fine-structure and envelope-based interaural temporal disparities. A computational model for the lateralization of binaural stimuli, motivated by recent physiological findings, is suggested and evaluated against the psychoacoustic data. The model is based on the independent extraction of the interaural phase difference (IPD) from the stimulus fine-structure and envelope. Sinusoidally amplitude-modulated 1-kHz tones were used in the experiments. The lateralization from either carrier (fine-structure) or modulator (envelope) IPD was matched with an interaural level difference, revealing a nearly linear dependence for both IPD types up to 135 degrees, independent of the modulation frequency. However, if a carrier IPD was traded with an opposed modulator IPD to produce a centered sound image, a carrier IPD of 45 degrees required the largest opposed modulator IPD. The data could be modeled assuming a population of binaural neurons with a physiological distribution of the best IPDs clustered around 45 degrees-50 degrees. The model was also used to predict the perceived lateralization of previously published data. Subject-dependent differences in the perceptual salience of fine-structure and envelope cues, also reported previously, could be modeled by individual weighting coefficients for the two cues.},
year = {2009}
}
@article{Epp:2009C,
type = {journal article},
author = {Epp, Bastian and Verhey, Jesko L.},
title = {{C}ombination of masking releases for different center frequencies and masker amplitude statistics},
journal = {Journal of the Acoustical Society of America},
volume = {126},
number = {5},
pages = {2479-2489},
abstract = {Several masking experiments have shown that the auditory system is able to use coherent envelope fluctuations of the masker across frequency within one ear as well as differences in interaural disparity between signal and masker to enhance signal detection. The two effects associated with these abilities are comodulation masking release (CMR) and binaural masking level difference (BMLD). The aim of the present study was to investigate the combination of CMR and BMLD. Thresholds for detecting a sinusoidal signal were measured in a flanking-band paradigm at three different signal frequencies. The masker was presented diotically, and various interaural phase differences (IPDs) of the signal were used. The masker components were either multiplied or Gaussian narrowband noises. In addition, a transposed stimulus was used to increase the BMLD at a high signal frequency. For all frequencies and masker conditions, thresholds decreased as the signal IPD increased and were lower when the masker components were comodulated. The data show an addition of the monaural and binaural masking releases in decibels when masker conditions with and without comodulation and the same spectrum were compared. (C) 2009 Acoustical Society of America. [DOI: 10.1121/1.3205404]},
year = {2009}
}
@article{Epp:2009S,
type = {journal article},
author = {Epp, Bastian and Verhey, Jesko L.},
title = {{S}uperposition of masking releases},
journal = {Journal of Computational Neuroscience},
volume = {26},
number = {3},
pages = {393-407},
abstract = {We are constantly exposed to a mixture of sounds of which only few are important to consider. In order to improve detectability and to segregate important sounds from less important sounds, the auditory system uses different aspects of natural sound sources. Among these are (a) its specific location and (b) synchronous envelope fluctuations in different frequency regions. Such a comodulation of different frequency bands facilitates the detection of tones in noise, a phenomenon known as comodulation masking release (CMR). Physiological as well as psychoacoustical studies usually investigate only one of these strategies to segregate sounds. Here we present psychoacoustical data on CMR for various virtual locations of the signal by varying its interaural phase difference (IPD). The results indicate that the masking release in conditions with binaural (interaural phase differences) and across-frequency (synchronous envelope fluctuations, i.e. comodulation) cues present is equal to the sum of the masking releases for each of the cues separately. Data and model predictions with a simplified model of the auditory system indicate an independent and serial processing of binaural cues and monaural across-frequency cues, maximizing the benefits from the envelope comparison across frequency and the comparison of fine structure across ears.},
year = {2009}
}
@article{Grimm:2009TPH,
type = {journal article},
author = {Grimm, Giso and Guilmin, G. and Poppen, F. and Vlaming, M. and Hohmann, Volker},
title = {{T}he {P}ersonal {H}earing {S}ystem-{A} {S}oftware {H}earing {A}id for a {P}ersonal {C}ommunication {S}ystem},
journal = {Eurasip Journal on Advances in Signal Processing},
abstract = {A concept and architecture of a personal communication system (PCS) is introduced that integrates audio communication and hearing support for the elderly and hearing-impaired through a personal hearing system (PHS). The concept envisions a central processor connected to audio headsets via a wireless body area network (WBAN). To demonstrate the concept, a prototype PCS is presented that is implemented on a netbook computer with a dedicated audio interface in combination with a mobile phone. The prototype can be used for field-testing possible applications and to reveal possibilities and limitations of the concept of integrating hearing support in consumer audio communication devices. It is shown that the prototype PCS can integrate hearing aid functionality, telephony, public announcement systems, and home entertainment. An exemplary binaural speech enhancement scheme that represents a large class of possible PHS processing schemes is shown to be compatible with the general concept. However, an analysis of hardware and software architectures shows that the implementation of a PCS on future advanced cell phone-like devices is challenging. Because of limitations in processing power, recoding of prototype implementations into fixed point arithmetic will be required and WBAN performance is still a limiting factor in terms of data rate and delay. Copyright (C) 2009 Giso Grimm et al.},
year = {2009}
}
@article{Grimm:2009ISE,
type = {journal article},
author = {Grimm, Giso and Hohmann, Volker and Kollmeier, Birger},
title = {{I}ncrease and {S}ubjective {E}valuation of {F}eedback {S}tability in {H}earing {A}ids by a {B}inaural {C}oherence-{B}ased {N}oise {R}eduction {S}cheme},
journal = {IEEE Transactions on Audio Speech and Language Processing},
volume = {17},
number = {7},
pages = {1408-1419},
abstract = {The effect of a binaural coherence-based noise reduction scheme on the feedback stability margin and sound quality in hearing aids has been analyzed. For comparison, a conventional adaptive feedback canceler (AFC) and the combination of the adaptive filter with the binaural coherence filter have been tested. The observed quantities are feedback stability and target signal attenuation. An objective measure of feedback stability, i.e., the added stable gain (ASG) was obtained for a number of algorithmic settings and compared to a subjective measure of feedback stability, the added tolerable gain (ATG). In an attempt to eliminate the subjective bias in estimating the ATG, the "unbiased added gain" (UAG) is introduced as a new method. Both, objective and subjective measures give similar results for feedback stability. This allows for a valid comparison across different feedback reduction schemes both in isolation and in combination: whereas the ASG of the coherence filter without combination with AFC is negligible, the results indicate that a robust feedback suppression in hearing aids can be achieved if the benefit of de-correlation and the head-shadow effect in binaural hearing aids is used in an advantageous way. The ASG reaches 23 dB for the best combination at the expense of an average target signal attenuation of 15 dB at critical frequencies. The attribute of the coherence filter is that it adaptively limits the maximum gain before feedback becomes audible. The UAG analysis revealed that subjects used a stable quality criterion across the conditions tested and that the group of subjects covered a large range of individual quality criteria.},
year = {2009}
}
@article{Heise:2009I,
type = {journal article},
author = {Heise, Stephan J. and Mauermann, Manfred and Verhey, Jesko L.},
title = {{I}nvestigating possible mechanisms behind the effect of threshold fine structure on amplitude modulation perception},
journal = {Journal of the Acoustical Society of America},
volume = {126},
number = {5},
pages = {2490-2500},
abstract = {Detection thresholds for sinusoidal amplitude modulation at low levels are higher (worse) when the carrier of the signal falls in a region of high pure-tone sensitivity (a minimum of the fine structure of the threshold in quiet) than when it falls at a fine-structure maximum. This study explores possible mechanisms behind this phenomenon by measuring modulation detection thresholds as a function of modulation frequency (experiment 1) and of carrier level for tonal carriers (experiment 2) and for 32-Hz wide noise carriers (experiment 3). The carriers could either fall at a fine-structure minimum, a fine-structure maximum, or in a region without fine structure. Modulation frequencies varied between 8 Hz and one fine-structure cycle, and carrier levels varied between 7.5 and 37.5 dB sensation levels. A large part of the results can be explained by assuming a reduction in effective modulation depth by spontaneous otoacoustic emissions-or more generally cochlear resonances-that synchronize to the carrier at fine-structure minima. Beating between cochlear resonances and the stimulus ("monaural diplacusis") may hamper the detection task, but this cannot account for the whole effect. (C) 2009 Acoustical Society of America. [DOI: 10.1121/1.3224731]},
year = {2009}
}
@article{Heise:2009T,
type = {journal article},
author = {Heise, Stephan J. and Mauermann, Manfred and Verhey, Jesko L.},
title = {{T}hreshold fine structure affects amplitude modulation perception},
journal = {Journal of the Acoustical Society of America},
volume = {125},
number = {1},
pages = {EL33-EL38},
abstract = {Modulation detection thresholds of a sinusoidally amplitude-modulated tone were measured for two different positions of the low-level carrier relative to the fine structure of the threshold in quiet. Modulation detection thresholds were higher for a carrier at a fine-structure minimum than for a carrier at a fine-structure maximum, regardless of whether the carriers had the same sound pressure level or the same sensation level. This indicates that even for small variations of the carrier frequency, the sensitivity to amplitude modulation can vary substantially due to the frequency characteristics of the threshold in quiet.},
year = {2009}
}
@article{Jürgens:2009M,
type = {journal article},
author = {Jürgens, Tim and Brand, Thomas},
title = {{M}icroscopic prediction of speech recognition for listeners with normal hearing in noise using an auditory model},
journal = {Journal of the Acoustical Society of America},
volume = {126},
number = {5},
pages = {2635-2648},
abstract = {This study compares the phoneme recognition performance in speech-shaped noise of a microscopic model for speech recognition with the performance of normal-hearing listeners. "Microscopic" is defined in terms of this model twofold. First, the speech recognition rate is predicted on a phoneme-by-phoneme basis. Second, microscopic modeling means that the signal waveforms to be recognized are processed by mimicking elementary parts of human's auditory processing. The model is based on an approach by Holube and Kollmeier [J. Acoust. Soc. Am. 100, 1703-1716 (1996)] and consists of a psychoacoustically and physiologically motivated preprocessing and a simple dynamic-time-warp speech recognizer. The model is evaluated while presenting nonsense speech in a closed-set paradigm. Averaged phoneme recognition rates, specific phoneme recognition rates, and phoneme confusions are analyzed. The influence of different perceptual distance measures and of the model's a-priori knowledge is investigated. The results show that human performance can be predicted by this model using an optimal detector, i.e., identical speech waveforms for both training of the recognizer and testing. The best model performance is yielded by distance measures which focus mainly on small perceptual distances and neglect outliers. (C) 2009 Acoustical Society of America. [DOI: 10.1121/1.3224721]},
year = {2009}
}
@article{Kayser:2009DMI,
type = {journal article},
author = {Kayser, Hendrik and Ewert, Stephan D. and Anemüller, Jörn and Rohdenburg, Thomas and Hohmann, Volker and Kollmeier, Birger},
title = {{D}atabase of {M}ultichannel {I}n-{E}ar and {B}ehind-the-{E}ar {H}ead-{R}elated and {B}inaural {R}oom {I}mpulse {R}esponses},
journal = {Eurasip Journal on Advances in Signal Processing},
abstract = {An eight-channel database of head-related impulse responses (HRIRs) and binaural room impulse responses (BRIRs) is introduced. The impulse responses (IRs) were measured with three-channel behind-the-ear (BTEs) hearing aids and an in-ear microphone at both ears of a human head and torso simulator. The database aims at providing a tool for the evaluation of multichannel hearing aid algorithms in hearing aid research. In addition to the HRIRs derived from measurements in an anechoic chamber, sets of BRIRs for multiple, realistic head and sound-source positions in four natural environments reflecting daily-life communication situations with different reverberation times are provided. For comparison, analytically derived IRs for a rigid acoustic sphere were computed at the multichannel microphone positions of the BTEs and differences to real HRIRs were examined. The scenes' natural acoustic background was also recorded in each of the real-world environments for all eight channels. Overall, the present database allows for a realistic construction of simulated sound fields for hearing instrument research and, consequently, for a realistic evaluation of hearing instrument algorithms. Copyright (C) 2009 H. Kayser et al.},
year = {2009}
}
@article{Lüddemann:2009E,
type = {journal article},
author = {Lüddemann, Helge and Riedel, Helmut and Kollmeier, Birger},
title = {{E}lectrophysiological and psychophysical asymmetries in sensitivity to interaural correlation steps},
journal = {Hearing Research},
volume = {256},
number = {1-2},
pages = {39-57},
abstract = {The binaural auditory system's sensitivity to changes in the interaural cross correlation (IAC), as an indicator for the perceived spatial diffuseness of a sound, is of major importance for the ability to distinguish concurrent sound sources. In this article, we present electroencephalographical and corresponding psychophysical experiments with stepwise transitions of the IAC in continuously running noise. Both the transient and sustained brain response, display electrophysiological correlates of specific binaural processing in humans. The transient late auditory evoked potentials (LAEP) systematically depend on the size of the IAC transition, the reference correlation preceding the transition, the direction of the transition and on unspecific context information from the stimulus sequence. The psychophysical and electrophysiological data are characterized by two asymmetries. (1) Major asymmetry: for reference correlations of +1 and -1, psychoacoustical thresholds are comparatively lower, and the peak-to-peak-amplitudes of LAEP are larger than for a reference correlation of zero. (2) Minor asymmetry: for IAC transitions in the positive parameter range, perceptual thresholds are slightly better and peak-to-peak amplitudes are larger than in the negative range. In all experimental conditions, LAEP amplitudes are linearly related to the dB scaled power ratio of correlated (N-0) versus anticorrelated (N-pi) signal components. The voltage gain of LAEP per dB(N-0/N-pi) closely corresponds to a constant perceptual distance between two correlations. We therefore suggest that activity in the auditory cortex and perceptual IAC sensitivity are better represented by the dB-scaled N-0/N-pi power ratio than by the normalized IAC itself (C) 2009 Elsevier B.V. All rights reserved.},
year = {2009}
}
@article{Sukowski:2009UVF,
type = {journal article},
author = {Sukowski, Helga and Brand, Thomas and Wagener, Kirsten and Kollmeier, Birger},
title = {{U}ntersuchung zur {V}ergleichbarkeit des {F}reiburger {S}prachtests mit dem {G}öttinger {S}atztest und dem {E}insilber-{R}eimtest nach von {W}allenbaerg und {K}ollmer},
journal = {HNO},
volume = {57},
pages = {239-250},
year = {2009}
}
@article{Verhey:2009C,
type = {journal article},
author = {Verhey, Jesko L. and Ernst, Stephan M.A.},
title = {{C}omodulation masking release for regular and irregular modulators},
journal = {Hearing Research},
volume = {253},
number = {1-2},
pages = {97-106},
abstract = {The present study investigates whether the difference in comodulation masking release (CMR) for different modulator types is due to the different degrees of modulator regularity, as suggested in the literature, or results from different envelope distributions. Thresholds of a sinusoidal signal are measured in the presence of a noise masker which was either broadband or narrow band. A square-wave modulator with different degrees of regularity is used that preserves the envelope distribution. The measured CMR does not decrease as the regularity decreases. This finding argues against the hypothesis that the difference in CMR for different modulator types reported in the literature is due to differences in regularity. The data for the narrow-band conditions which either mimic the auditory frequency selectivity or preserve the modulation spectrum indicate that most of the CMR of the present study is due to within-channel cues. In agreement with this finding, within-channel models using either a peripheral nonlinearity or a modulation filterbank predict a CMR of a similar size. In contrast to the model predictions and the findings for the narrow-band conditions, the CMR for the broadband masker increases as the regularity decreases. This suggests that the CMR is not solely determined by the envelope distributions. (C) 2009 Elsevier B.V. All rights reserved.},
year = {2009}
}