Sound has long been used to enhance eating experiences, and increasingly, we know sound can shape how we perceive taste. Yet intentionally composing sounds to modulate taste remains underexplored in cross-sensory HCI design. While prior research has mapped individual auditory parameter (e.g., pitch, timbre, rhythm) to basic taste perceptions, less is known about how holistic sound compositions combining multiple parameters can be systematically designed and evaluated. We present a human-in-the-loop workflow that brings together professional sound designers and generative AI to create 160 sounds with taste intentions informed by established auditory-taste parameters. In a study with 149 participants on sound-taste correspondences, we identify sounds that strongly correspond to basic taste words. Our contributions are threefold: (1) a workflow for designing taste-matching sounds; (2) a curated repository of reusable sound stimuli for cross-sensory research; and (3) a designerly framework for creating compositional taste-matching sounds alongside insights into sound-taste word correspondences and association strategies, offering implications for cross-sensory HCI.

Sounds play a crucial role in shaping dining experiences. Recently, designers have increasingly integrated them into interfaces that connect diners with food. Yet, little is known about how sounds can function as culinary materials to enrich chefs’ creativity, particularly in creating meaningful auditory interactions that resonate with their culinary creations. Hence, we present GastroConcerto, an auditory dining system that combines a magnetic contact microphone equipped under the plate with a companion mobile application. This system delves into the interactive space between diners and their food to introduce a novel interactive mechanism of dining–sound pairing, enabling chefs to design specific auditory interactions that respond to diners’ individual interactions with the food on dining containers. Through a within-subjects study and field deployment, we examined how GastroConcerto enriches chefs’ creative practices in crafting "sonic dish" experiences. Ultimately, our goal is to shift the ownership of auditory interaction design from interface designers to chefs, thereby supporting their culinary creativity.

The rise of personal speech data collection has enabled malicious actors to manipulate content using AI-powered tools via speech tampering techniques, such as copy-move forgery, deleting, homologous splicing, and heterologous splicing operations. These made-up things lead to fake voices, cheating, and spreading lies. While deep neural networks (DNNs) show promise for blind speech tampering detection, current methods lack cross-type generalisation due to software-specific limitations and rarely consider the classification of tampering types. To address this issue, this work presents an integrated detection framework (IDF) based on DNNs with three key components: 1) an encoder-decoder detection network generating a preliminary localisation mask (PLM) from Mel spectrogram features (MSFs); 2) an adaptive speech tampering localisation algorithm for refining the PLM; and 3) a dedicated classification network for tampering-type identification. Our IDF is trained using only the basic MSFs, ground-truth masks (GTMs), integer-class labels, binary cross-entropy loss, and sparse categorical cross-entropy loss. Supporting this work, we have produced a comprehensive dataset comprising 55,500 pairs of MSFs and GTMs for authentic and tampered speech samples derived from Chinese and English corpora through systematic tampering simulations. Experimental results demonstrate the consistent performance of our IDF framework across multiple languages and manipulation types. The model achieves average F-scores of 95.32% on Chinese, 96.02% on English, 88.81% on Spanish, and 95.75% on spoofed samples for detection tasks, while maintaining a localisation error below 0.1 seconds.

While interest in blending sound with culinary experiences has grown in Human-Food Interaction (HFI), the significance of food's material properties in shaping sound-related interactions has largely been overlooked. This paper explores the opportunity to enrich the HFI experience by treating food not merely as passive nourishment but as an integral material in computational architecture with input/output capabilities. We introduce “Sonic Delights,” where food is a comestible auditory-gustatory interface to enable users to interact with and consume digital sound. This concept redefines food as a conduit for interactive auditory engagement, shedding light on the untapped multisensory possibilities of merging taste with digital sound. An associated study allowed us to articulate design insights for forthcoming HFI endeavors that seek to weave food into multisensory design, aiming to further the integration of digital interactivity with the culinary arts.