Andrea Gulli
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Andrea Gulli has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Enrico Muzzi
3 shared publicationsEva Orzan
3 shared publications- Federico Fontana
HCI Lab, Department of Mathematics, Computer Science and Physics, University of Udine, Udine, Italy
3 shared publications Alessandro Aruffo
Otorhinolaryngology and Audiology, Institute for Maternal and Child Health IRCCS "Burlo Garofolo", Trieste, Italy
2 shared publicationsFederico Fontana
2 shared publicationsMichele Geronazzo
2 shared publications
Latest Publications
- Open Access
- 1 May 2026
- Published by Elsevier in International Journal of Child-Computer Interaction
- Vol. 48
Pitch training for children with cochlear implants: Negotiating clinical validity through mobile game-based design
- 1 May 2026
- Published by Elsevier in International Journal of Child-Computer Interaction
- Vol. 48
Open AccessPitch training for children with cochlear implants: Negotiating clinical validity through mobile game-based design
- Open Access
- 31 December 2025
- Published by Copernicus Center Foundation in Philosophical Problems in Science (Zagadnienia Filozoficzne w Nauce)
- No. 79
From Digital Twins to Entangled Twins
This article introduces the concept of Entangled Twins (ETs) as an interdisciplinary framework emerging from a sustained dialogue between Human–Computer Interaction (HCI) research and phenomenological philosophy. Building on the Digital Twin (DT) paradigm while critically reworking its representational logic, ETs are conceived as relational configurations in which human users and AI-driven systems become dynamically entangled, with significant implications for agency, responsibility, and human-centered design. The theoretical framework draws on phenomenological analyses of intersubjectivity and embodiment (Husserl, Merleau-Ponty, and Sartre) together with design-oriented concerns in HCI.Within this perspective, human–machine interaction is conceptualized in terms of aWe-subject: a plural and co-constituted configuration of agency. Through this interdisciplinary approach, a prototypical audio-augmented experience is examined as a phenomenologically informed case, elucidating the conditions under which human–machine entanglement can emerge. On this basis, the paper argues that ETs raise distinctive questions concerning responsibility and agency, articulating an ethics of entanglement capable of informing the human-centered aspirations of Industry 5.0.
- 31 December 2025
- Published by Copernicus Center Foundation in Philosophical Problems in Science (Zagadnienia Filozoficzne w Nauce)
- No. 79
Open AccessFrom Digital Twins to Entangled Twins
This article introduces the concept of Entangled Twins (ETs) as an interdisciplinary framework emerging from a sustained dialogue between Human–Computer Interaction (HCI) research and phenomenological philosophy. Building on the Digital Twin (DT) paradigm while critically reworking its representational logic, ETs are conceived as relational configurations in which human users and AI-driven systems become dynamically entangled, with significant implications for agency, responsibility, and human-centered design. The theoretical framework draws on phenomenological analyses of intersubjectivity and embodiment (Husserl, Merleau-Ponty, and Sartre) together with design-oriented concerns in HCI.Within this perspective, human–machine interaction is conceptualized in terms of aWe-subject: a plural and co-constituted configuration of agency. Through this interdisciplinary approach, a prototypical audio-augmented experience is examined as a phenomenologically informed case, elucidating the conditions under which human–machine entanglement can emerge. On this basis, the paper argues that ETs raise distinctive questions concerning responsibility and agency, articulating an ethics of entanglement capable of informing the human-centered aspirations of Industry 5.0.
- Open Access
- 24 October 2025
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2025 (1) , 1-21
Enhancing drone audition with rotor-conditioned deep models
The problem of recovering speech from audio recordings captured by a microphone aboard an unmanned aerial vehicle during flight is investigated. Enhancing a recording in this condition is difficult due to non-stationary noise from the motors and the propellers, along with environmental disturbance and motion-induced air flows. Together, these sources dramatically decrease the signal-to-noise ratio (SNR). This paper investigates the integration of rotor speed time series as a structured conditioning signal into neural speech enhancement models. We implement and evaluate rotor-informed variants of three state-of-the-art architectures: Wave-U-Net (time domain), DCCRN, and DCUNet (both time-frequency domain). Experiments on a custom UAV acoustics dataset spanning SNR levels from − 30 to 0 dB show that rotor conditioning yields consistent and statistically significant improvements across SNR, SI-SDR, STOI, and PESQ metrics. These benefits generalize across model families, and a lightweight rotor-informed variant achieves best or near-best results despite using only 25% of the parameters. The findings establish rotor-informed conditioning as a robust and generalizable strategy for speech enhancement in low-SNR UAV environments.
- 24 October 2025
- Published by Springer Nature in EURASIP Journal on Audio, Speech, and Music Processing
- Vol. 2025 (1) , 1-21
Open AccessEnhancing drone audition with rotor-conditioned deep models
The problem of recovering speech from audio recordings captured by a microphone aboard an unmanned aerial vehicle during flight is investigated. Enhancing a recording in this condition is difficult due to non-stationary noise from the motors and the propellers, along with environmental disturbance and motion-induced air flows. Together, these sources dramatically decrease the signal-to-noise ratio (SNR). This paper investigates the integration of rotor speed time series as a structured conditioning signal into neural speech enhancement models. We implement and evaluate rotor-informed variants of three state-of-the-art architectures: Wave-U-Net (time domain), DCCRN, and DCUNet (both time-frequency domain). Experiments on a custom UAV acoustics dataset spanning SNR levels from − 30 to 0 dB show that rotor conditioning yields consistent and statistically significant improvements across SNR, SI-SDR, STOI, and PESQ metrics. These benefits generalize across model families, and a lightweight rotor-informed variant achieves best or near-best results despite using only 25% of the parameters. The findings establish rotor-informed conditioning as a robust and generalizable strategy for speech enhancement in low-SNR UAV environments.
- Open Access
- 25 September 2025
- Published by MDPI AG in Audiology Research
- Vol. 15 (5) , 123
Time Delay and Frequency Analysis of Remote Microphones
Background/Objectives: A.BA.CO. is a speech-to-text captioning system developed for school classrooms. The system uses remote microphones to capture the teacher’s speech without background noise. Under this setup, an issue of signal latency arises for students wearing hearing aids (HAs) or cochlear implants (CIs), whose latency is different from that of the remote microphones and may require the development of a temporal coupling solution. This study establishes the foundation for such a solution by determining the latency of two RMs (Remote Microphones) compatible with both HA and CI systems. The frequency response of the systems is analyzed independently and combined. Methods: The RMs combined with two Behind-The-Ear HAs, for which transparency was verified, were tested with two different compression ratios in a laboratory specializing in electroacoustic measurements using the comparison method to assess performance. Results: The time measurements revealed that the RMs differ by 10–12 ms (23–24 ms and 33–35 ms) and that the two HAs have time delays that differ by 1–2 ms (6–7 ms and 5–7 ms). The frequency responses showed that when HA and RM have similar gains, they exhibit comb-filter distortions. This effect could alter the acoustic output of devices in the ear canal and vary according to the mix ratio and mutual positions of HA and RM, potentially necessitating greater commitment from the wearer. Conclusions: The communication system will have to foresee different delays based on the model and brand of RM because similar transmission systems do not have the same time delays. RMs were originally designed for HA and are most effective if they represent the only or major acoustic stimulation that reaches the eardrum. These limits must be considered when estimating the effectiveness of A.BA.CO. with RM.
- 25 September 2025
- Published by MDPI AG in Audiology Research
- Vol. 15 (5) , 123
Open AccessTime Delay and Frequency Analysis of Remote Microphones
Background/Objectives: A.BA.CO. is a speech-to-text captioning system developed for school classrooms. The system uses remote microphones to capture the teacher’s speech without background noise. Under this setup, an issue of signal latency arises for students wearing hearing aids (HAs) or cochlear implants (CIs), whose latency is different from that of the remote microphones and may require the development of a temporal coupling solution. This study establishes the foundation for such a solution by determining the latency of two RMs (Remote Microphones) compatible with both HA and CI systems. The frequency response of the systems is analyzed independently and combined. Methods: The RMs combined with two Behind-The-Ear HAs, for which transparency was verified, were tested with two different compression ratios in a laboratory specializing in electroacoustic measurements using the comparison method to assess performance. Results: The time measurements revealed that the RMs differ by 10–12 ms (23–24 ms and 33–35 ms) and that the two HAs have time delays that differ by 1–2 ms (6–7 ms and 5–7 ms). The frequency responses showed that when HA and RM have similar gains, they exhibit comb-filter distortions. This effect could alter the acoustic output of devices in the ear canal and vary according to the mix ratio and mutual positions of HA and RM, potentially necessitating greater commitment from the wearer. Conclusions: The communication system will have to foresee different delays based on the model and brand of RM because similar transmission systems do not have the same time delays. RMs were originally designed for HA and are most effective if they represent the only or major acoustic stimulation that reaches the eardrum. These limits must be considered when estimating the effectiveness of A.BA.CO. with RM.
- Open Access
- 5 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0312073
Previous binaural experience supports compensatory strategies in hearing-impaired children’s auditory horizontal localization
This study investigates auditory localization in children with a diagnosis of hearing impairment rehabilitated with bilateral cochlear implants or hearing aids. Localization accuracy in the anterior horizontal field and its distribution along the angular position of the source were analyzed. Participants performed a localization task in a virtual environment where they could move their heads freely and were asked to point to an invisible sound source. The source was rendered using a loudspeaker set arranged as a semi-circular array in the horizontal plane. The participants’ head positions were tracked while their hands pointed to the auditory target; the preferred listening position and the onset of active strategies involving head movement were extracted. A significant correlation was found between age and localization accuracy and age and head movement in children with bilateral hearing aids. Investigating conditions where no, one, or both hearing devices were turned off, it was found that asymmetrical hearing caused the largest errors. Under this specific condition, head movement was used erratically by children with bilateral cochlear implants who focused on postures maximizing sound intensity at the more sensitive ear. Conversely, those with a consolidated binaural hearing experience could use dynamic cues even if one hearing aid was turned off. This finding may have implications for the clinical evaluation and rehabilitation of individuals with hearing impairments.
- 5 December 2024
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 19 (12) , e0312073
Open AccessPrevious binaural experience supports compensatory strategies in hearing-impaired children’s auditory horizontal localization
This study investigates auditory localization in children with a diagnosis of hearing impairment rehabilitated with bilateral cochlear implants or hearing aids. Localization accuracy in the anterior horizontal field and its distribution along the angular position of the source were analyzed. Participants performed a localization task in a virtual environment where they could move their heads freely and were asked to point to an invisible sound source. The source was rendered using a loudspeaker set arranged as a semi-circular array in the horizontal plane. The participants’ head positions were tracked while their hands pointed to the auditory target; the preferred listening position and the onset of active strategies involving head movement were extracted. A significant correlation was found between age and localization accuracy and age and head movement in children with bilateral hearing aids. Investigating conditions where no, one, or both hearing devices were turned off, it was found that asymmetrical hearing caused the largest errors. Under this specific condition, head movement was used erratically by children with bilateral cochlear implants who focused on postures maximizing sound intensity at the more sensitive ear. Conversely, those with a consolidated binaural hearing experience could use dynamic cues even if one hearing aid was turned off. This finding may have implications for the clinical evaluation and rehabilitation of individuals with hearing impairments.
- Open Access
- 22 December 2023
- Published by MDPI AG in Multimodal Technologies and Interaction
- Vol. 8 (1) , 1
The Role of Haptics in Training and Games for Hearing-Impaired Individuals: A Systematic Review
Sensory substitution and augmentation are pivotal concepts in multi-modal perception, particularly when confronting the challenges associated with impaired or missing sense rehabilitation. The present systematic review investigates the role of haptics for the hearing impaired in training or gamified activities. We applied a set of keywords to the Scopus® and PubMed® databases, obtaining a collection of 35 manuscripts spanning 23 years. Each article has been categorized following a documented procedure and thoroughly analyzed. Our findings reveal a rising number of studies in this field in the last five years, mostly testing the effectiveness of the developed rehabilitative method (77.14%). Despite a wide variety in almost every category we analyzed, such as haptic devices, body location, and data collection, we report a constant difficulty in recruitment, reflected in the low number of hearing-impaired participants (mean of 8.31). This review found that in all six papers reporting statistically significant positive results, the vibrotactile device in use generated vibrations starting from a sound, suggesting that some perceptual aspects connected to sound are transmittable through touch. This fact provides evidence that haptics and vibrotactile devices could be viable solutions for hearing-impaired rehabilitation and training.
- 22 December 2023
- Published by MDPI AG in Multimodal Technologies and Interaction
- Vol. 8 (1) , 1
Open AccessThe Role of Haptics in Training and Games for Hearing-Impaired Individuals: A Systematic Review
Sensory substitution and augmentation are pivotal concepts in multi-modal perception, particularly when confronting the challenges associated with impaired or missing sense rehabilitation. The present systematic review investigates the role of haptics for the hearing impaired in training or gamified activities. We applied a set of keywords to the Scopus® and PubMed® databases, obtaining a collection of 35 manuscripts spanning 23 years. Each article has been categorized following a documented procedure and thoroughly analyzed. Our findings reveal a rising number of studies in this field in the last five years, mostly testing the effectiveness of the developed rehabilitative method (77.14%). Despite a wide variety in almost every category we analyzed, such as haptic devices, body location, and data collection, we report a constant difficulty in recruitment, reflected in the low number of hearing-impaired participants (mean of 8.31). This review found that in all six papers reporting statistically significant positive results, the vibrotactile device in use generated vibrations starting from a sound, suggesting that some perceptual aspects connected to sound are transmittable through touch. This fact provides evidence that haptics and vibrotactile devices could be viable solutions for hearing-impaired rehabilitation and training.
- Open Access
- 6 December 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (12) , e0278705
Spontaneous head movements support accurate horizontal auditory localization in a virtual visual environment
This study investigates the relationship between auditory localization accuracy in the horizontal plane and the spontaneous translation and rotation of the head in response to an acoustic stimulus from an invisible sound source. Although a number of studies have suggested that localization ability improves with head movements, most of them measured the perceived source elevation and front-back disambiguation. We investigated the contribution of head movements to auditory localization in the anterior horizontal field in normal hearing subjects. A virtual reality scenario was used to conceal visual cues during the test through a head mounted display. In this condition, we found that an active search of the sound origin using head movements is not strictly necessary, yet sufficient for achieving greater sound source localization accuracy. This result may have important implications in the clinical assessment and training of adults and children affected by hearing and motor impairments.
- 6 December 2022
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 17 (12) , e0278705
Open AccessSpontaneous head movements support accurate horizontal auditory localization in a virtual visual environment
This study investigates the relationship between auditory localization accuracy in the horizontal plane and the spontaneous translation and rotation of the head in response to an acoustic stimulus from an invisible sound source. Although a number of studies have suggested that localization ability improves with head movements, most of them measured the perceived source elevation and front-back disambiguation. We investigated the contribution of head movements to auditory localization in the anterior horizontal field in normal hearing subjects. A virtual reality scenario was used to conceal visual cues during the test through a head mounted display. In this condition, we found that an active search of the sound origin using head movements is not strictly necessary, yet sufficient for achieving greater sound source localization accuracy. This result may have important implications in the clinical assessment and training of adults and children affected by hearing and motor impairments.