SONICOM

@article{VICENTE2025109490,

title = {Exploring the relationship between task difficulty, head-related transfer function and spatial release from masking in a speech-on-speech experiment},

author = {Thibault Vicente and Daniel González-Toledo and María Cuevas-Rodríguez and Luis Molina-Tanco and Arcadio Reyes-Lecuona and Lorenzo Picinali},

url = {https://www.sciencedirect.com/science/article/pii/S0378595525003077},

doi = {https://doi.org/10.1016/j.heares.2025.109490},

issn = {0378-5955},

year  = {2025},

date = {2025-01-01},

urldate = {2025-01-01},

journal = {Hearing Research},

pages = {109490},

abstract = {It is known that individuals make use of spatial hearing cues to improve the audibility of a target signal and separate it from competing sounds. This phenomenon is known as spatial release from masking (SRM). Recent research has shown that this happens also when sources are located in the median plane, where interaural differences are limited. When assessing this within virtual conditions, it has been shown that employing individually measured head-related transfer functions (HRTFs) results in higher SRM abilities compared to using non-individual filters. In a previously published work, we found that Spanish speakers benefit from individual HRTFs when discriminating a target English speech from a single masker in the median plane. This study replicates the protocol of that previous work, varying the number of maskers and participants’ English proficiency levels to explore relationships among task difficulty and HRTF use. Results from a first experiment show that English speakers behave differently to Spanish ones; their SRM advantage is not significant. We suggest that this is due to their language proficiency, which allows them to rely on spectral glimpsing alone, that is, exploiting spectro-temporal gaps between voices rather than spectral cues introduced by spatial separation. A second experiment introduces a second speech masker, co-located with the first; by making the task more complex, participants seem to increase their reliance on spatial cues, resulting in significant effects of masker position and HRTF. This highlights a trade-off between the use of target glimpsing and spatial cues and the need for further exploration into how task difficulty influences SRM with different HRTFs.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ReyesLecuona2025,

title = {Binaural Rendering Toolbox (BRT). Una herramienta de auralización 3D en tiempo real para investigación en psicoacústica y realidad virtual},

author = {Arcadio Reyes‐Lecuona and Maria Cuevas-Rodriguez and Daniel Gonzalez-Toledo and Pablo Gutierrez-Parera},

year  = {2025},

date = {2025-01-01},

journal = {Sociedad Española de Acústica SEA - Revista de Acústica},

volume = {56},

number = {1-2},

pages = {3–12},

abstract = {Binaural Rendering Toolbox (BRT) es un conjunto de herramientas diseñadas para la simulación acústica espacial 3D en tiempo real, que incluyen, como núcleo principal, una librería C++ de código abierto. Su arquitectura flexible permite la creación de cadenas de procesamiento personalizadas mediante modelos acústicos independientes de fuente, entorno y oyente, así como filtros postbinaurales. BRT se adapta a diversas aplicaciones en acústica aplicada, como la auralización de salas reales, la simulación de acústica virtual para realidad extendida interactiva y la investigación en psicoacústica. Este artículo presenta los conceptos clave que sustentan la herramienta e ilustra su funcionamiento mediante una serie de casos de uso representativos.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ReyesLecuona2025a,

title = {Renderizado de Audio Espacial en Realidad Virtual con el Binaural Rendering Toolbox (BRT)},

author = {Arcadio Reyes‐Lecuona and Daniel Gonzalez-Toledo and Maria Cuevas-Rodriguez},

year  = {2025},

date = {2025-01-01},

journal = {Interaccion - Revista Digital de AIPO},

volume = {6},

number = {1},

pages = {51–61},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{10.1121/10.0024239,

title = {Spatial release from masking in the median plane with non-native speakers using individual and mannequin head related transfer functions},

author = {Daniel González-Toledo and María Cuevas-Rodríguez and Thibault Vicente and Lorenzo Picinali and Luis Molina-Tanco and Arcadio Reyes-Lecuona},

url = {https://doi.org/10.1121/10.0024239},

doi = {10.1121/10.0024239},

issn = {0001-4966},

year  = {2024},

date = {2024-01-01},

urldate = {2024-01-01},

journal = {The Journal of the Acoustical Society of America},

volume = {155},

number = {1},

pages = {284-293},

abstract = {Spatial release from masking (SRM) in speech-on-speech tasks has been widely studied in the horizontal plane, where interaural cues play a fundamental role. Several studies have also observed SRM for sources located in the median plane, where (monaural) spectral cues are more important. However, a relatively unexplored research question concerns the impact of head-related transfer function (HRTF) personalisation on SRM, for example, whether using individually-measured HRTFs results in better performance if compared with the use of mannequin HRTFs. This study compares SRM in the median plane in a speech-on-speech virtual task rendered using both individual and mannequin HRTFs. SRM is obtained using English sentences with non-native English speakers. Our participants show lower SRM performances compared to those found by others using native English participants. Furthermore, SRM is significantly larger when the source is spatialised using the individual HRTF, and this effect is more marked for those with lower English proficiency. Further analyses using a spectral distortion metric and the estimation of the better-ear effect, show that the observed SRM can only partially be explained by HRTF-specific factors and that the effect of the familiarity with individual spatial cues is likely to be the most significant element driving these results.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{9931551,

title = {The SONICOM Project: Artificial Intelligence-Driven Immersive Audio, From Personalization to Modeling [Applications Corner]},

author = {Lorenzo Picinali and Brian FG Katz and Michele Geronazzo and Piotr Majdak and Arcadio Reyes-Lecuona and Alessandro Vinciarelli},

url = {https://ieeexplore.ieee.org/document/9931551},

doi = {10.1109/MSP.2022.3182929},

year  = {2022},

date = {2022-01-01},

journal = {IEEE Signal Processing Magazine},

volume = {39},

number = {6},

pages = {85-88},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Imp/2021,

title = {Impact of non-individualised head related transfer functions on speech-in-noise performances within a synthesised virtual environment},

author = {María Cuevas-Rodríguez and Daniel González-Toledo and Arcadio Reyes-Lecuona and Lorenzo Picinali},

url = {https://asa.scitation.org/doi/10.1121/10.0004220},

doi = {10.1121/10.0004220},

issn = {0001-4966},

year  = {2021},

date = {2021-04-01},

urldate = {2021-04-01},

journal = {The Journal of the Acoustical Society of America},

volume = {149},

number = {4},

pages = {2573–2586},

abstract = {When performing binaural spatialisation, it is widely accepted that the choice of the head related transfer functions (HRTFs), and in particular the use of individually measured ones, can have an impact on localisation accuracy, externalization, and overall realism. Yet the impact of HRTF choices on speech-in-noise performances in cocktail party-like scenarios has not been investigated in depth. This paper introduces a study where 22 participants were presented with a frontal speech target and two lateral maskers, spatialised using a set of non-individual HRTFs. Speech reception threshold (SRT) was measured for each HRTF. Furthermore, using the SRT predicted by an existing speech perception model, the measured values were compensated in the attempt to remove overall HRTF-specific benefits. Results show significant overall differences among the SRTs measured using different HRTFs, consistently with the results predicted by the model. Individual differences between participants related to their SRT performances using different HRTFs could also be found, but their significance was reduced after the compensation. The implications of these findings are relevant to several research areas related to spatial hearing and speech perception, suggesting that when testing speech-in-noise performances within binaurally rendered virtual environments, the choice of the HRTF for each individual should be carefully considered.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{Reyes-Lecuona2021c,

title = {Binaural Audio and Rotation Gain in Virtual Environments},

author = {Arcadio Reyes-Lecuona and Ana Márquez-Moncada and Bottcher Hauke Luis and Daniel González-Toledo and María Cuevas-Rodriguez and Luis Molina-Tanco},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

journal = {Interaccion - Revista Digital de AIPO},

volume = {2},

issue = {2},

pages = {54-62},

keywords = {},

pubstate = {published},

tppubtype = {article}

}