Grounding language in the physical world requires AI systems to interpret references that emerge dynamically during conversation. While current vision-language models (VLMs) excel at static image tasks, they struggle to resolve ambiguous expressions in spontaneous, multi-turn dialogue. We address this gap by introducing MM-Conv—speak, point, look—a benchmark for referential communication in dynamic 3D environments, built from 6.7 hours of egocentric VR interaction with synchronized speech, motion, gaze, and 3D scene geometry. The benchmark includes over 4,200 manually verified referring expressions spanning full, partitive, and pronominal types, enabling systematic evaluation of multimodal reference resolution.

We present a shoal of voices in Storspigg–TBI, a legally cleared, professionally recorded Swedish speech corpus derived from talking-book production at the Swedish Agency for Accessible Media (MTM). The corpus contains 1 000 information messages read by 99 narrators under controlled studio conditions. The material has undergone full legal assessment and a three-sweep adoption process ensuring provenance, FAIR/FACT compliance, and reproducibility in collaboration with the national research infrastructure Språkbanken Tal. The paper describes the legal framework, data-selection and curation pipeline, as well as initial automatic transcription using Swedish Whisper and wav2vec 2.0 models. The resulting corpus provides a high-quality reference resource for speech science and technology, supporting research on inter-speaker variation, prosody, and evaluation under consistent acoustic and linguistic conditions.

As part of the PSST challenge, we explore how data augmentations, data sources, and model size affect phoneme transcription accuracy on speech produced by individuals with aphasia. We evaluate model performance in terms of feature error rate (FER) and phoneme error rate (PER). We find that data augmentations techniques, such as pitch shift, improve model performance. Additionally, increasing the size of the model decreases FER and PER. Our experiments also show that adding manually-transcribed speech from non-aphasic speakers (TIMIT) improves performance when Room Impulse Response is used to augment the data. The best performing model combines aphasic and non-aphasic data and has a 21.0% PER and a 9.2% FER, a relative improvement of 9.8% compared to the baseline model on the primary outcome measurement. We show that data augmentation, larger model size, and additional non-aphasic data sources can be helpful in improving automatic phoneme recognition models for people with aphasia.

In order to develop its full potential, global communication needs linguistic support systems such as Machine Translation (MT). In the past decade, free online MT tools have become available to the general public, and the quality of their output is increasing. However, the use of such tools may entail various legal implications, especially as far as processing of personal data is concerned. This is even more evident if we take into account that their business model is largely based on providing translation in exchange for data, which can subsequently be used to improve the translation model, but also for commercial purposes. The purpose of this paper is to examine how free online MT tools fit in the European data protection framework, harmonised by the EU Data Protection Directive. The perspectives of both the user and the MT service provider are taken into account.

This article describes the development of a bidirectional shallow-transfer based machine translation system for Spanish and Aragonese, based on the Apertium platform, reusing the resources provided by other translators built for the platform. The system, and the morphological analyser built for it, are both the first resources of their kind for Aragonese. The morphological analyser has coverage of over 80\%, and is being reused to create a spelling checker for Aragonese. The translator is bidirectional: the Word Error Rate for Spanish to Aragonese is 16.83%, while Aragonese to Spanish is 11.61%.