Formalizing cooking procedures remains a challenging task due to their inherent complexity and ambiguity. We introduce an extensible domain-specific language for representing recipes as directed action graphs, capturing processes, transfers, environments, concurrency, and compositional structure. Our approach enables precise, modular modeling of complex culinary workflows. Initial manual evaluation on a full English breakfast recipe demonstrates the DSL's expressiveness and suitability for future automated recipe analysis and execution. This work represents initial steps towards an action-centric ontology for cooking, using temporal graphs to enable structured machine understanding, precise interpretation, and scalable automation of culinary processes - both in home kitchens and professional culinary settings.

In the realm of human-computer interaction, fostering a natural dialogue between humans and machines is paramount. A key, often overlooked, component of this dialogue is the use of interjections such as "mmm" and "hmm". Despite their frequent use to express agreement, hesitation, or requests for information, these interjections are typically dismissed as "non-words" by Automatic Speech Recognition (ASR) engines. Addressing this gap, we introduce a novel task dedicated to interjection classification, a pioneer in the field to our knowledge. This task is challenging due to the short duration of interjection signals and significant inter- and intra-speaker variability. In this work, we present and publish a dataset of interjection signals collected specifically for interjection classification. We employ this dataset to train and evaluate a baseline deep learning model. To enhance performance, we augment the training dataset using techniques such as tempo and pitch transformation, which significantly improve classification accuracy, making models more robust. The interjection dataset, a Python library for the augmentation pipeline, baseline model, and evaluation scripts, are available to the research community.

Detecting and segmenting dysfluencies is crucial for effective speech therapy and real-time feedback. However, most methods only classify dysfluencies at the utterance level. We introduce StutterCut, a semi-supervised framework that formulates dysfluency segmentation as a graph partitioning problem, where speech embeddings from overlapping windows are represented as graph nodes. We refine the connections between nodes using a pseudo-oracle classifier trained on weak (utterance-level) labels, with its influence controlled by an uncertainty measure from Monte Carlo dropout. Additionally, we extend the weakly labelled FluencyBank dataset by incorporating frame-level dysfluency boundaries for four dysfluency types. This provides a more realistic benchmark compared to synthetic datasets. Experiments on real and synthetic datasets show that StutterCut outperforms existing methods, achieving higher F1 scores and more precise stuttering onset detection.

Non-Verbal Vocalisations (NVVs) are short `non-word' utterances without proper linguistic (semantic) meaning but conveying connotations -- be this emotions/affects or other paralinguistic information. We start this contribution with a historic sketch: how they were addressed in psychology and linguistics in the last two centuries, how they were neglected later on, and how they came to the fore with the advent of emotion research. We then give an overview of types of NVVs (formal aspects) and functions of NVVs, exemplified with the typical NVV \textit{ah}. Interesting as they are, NVVs come, however, with a bunch of challenges that should be accounted for: Privacy and general ethical considerations prevent them of being recorded in real-life (private) scenarios to a sufficient extent. Isolated, prompted (acted) exemplars do not necessarily model NVVs in context; yet, this is the preferred strategy so far when modelling NVVs, especially in AI. To overcome these problems, we argue in favour of corpus-based approaches. This guarantees a more realistic modelling; however, we are still faced with privacy and sparse data problems.

Despite significant progress in neural spoken dialog systems, personality-aware conversation agents -- capable of adapting behavior based on personalities -- remain underexplored due to the absence of personality annotations in speech datasets. We propose a pipeline that preprocesses raw audio recordings to create a dialogue dataset annotated with timestamps, response types, and emotion/sentiment labels. We employ an automatic speech recognition (ASR) system to extract transcripts and timestamps, then generate conversation-level annotations. Leveraging these annotations, we design a system that employs large language models to predict conversational personality. Human evaluators were engaged to identify conversational characteristics and assign personality labels. Our analysis demonstrates that the proposed system achieves stronger alignment with human judgments compared to existing approaches.

Contemporary state-of-the-art video object segmentation (VOS) models compare incoming unannotated images to a history of image-mask relations via affinity or cross-attention to predict object masks. We refer to the internal memory state of the initial image-mask pair and past image-masks as a working memory buffer. While the current state of the art models perform very well on clean video data, their reliance on a working memory of previous frames leaves room for error. Affinity-based algorithms include the inductive bias that there is temporal continuity between consecutive frames. To account for inconsistent camera views of the desired object, working memory models need an algorithmic modification that regulates the memory updates and avoid writing irrelevant frames into working memory. A simple algorithmic change is proposed that can be applied to any existing working memory-based VOS model to improve performance on inconsistent views, such as sudden camera cuts, frame interjections, and extreme context changes. The resulting model performances show significant improvement on video data with these frame interjections over the same model without the algorithmic addition. Our contribution is a simple decision function that determines whether working memory should be updated based on the detection of sudden, extreme changes and the assumption that the object is no longer in frame. By implementing algorithmic changes, such as this, we can increase the real-world applicability of current VOS models.

How does the presence of an AI assistant affect the collective attention of a team? We study 20 human teams of 3-4 individuals paired with one voice-only AI assistant during a challenging puzzle task. Teams are randomly assigned to an AI assistant with a human- or robotic-sounding voice that provides either helpful or misleading information about the task. Treating each individual AI interjection as a treatment intervention, we identify the causal effects of the AI on dynamic group processes involving language use. Our findings demonstrate that the AI significantly affects what teams discuss, how they discuss it, and the alignment of their mental models. Teams adopt AI-introduced language for both terms directly related to the task and for peripheral terms, even when they (a) recognize the unhelpful nature of the AI, (b) do not consider the AI a genuine team member, and (c) do not trust the AI. The process of language adaptation appears to be automatic, despite doubts about the AI's competence. The presence of an AI assistant significantly impacts team collective attention by modulating various aspects of shared cognition. This study contributes to human-AI teaming research by highlighting collective attention as a central mechanism through which AI systems in team settings influence team performance. Understanding this mechanism will help CSCW researchers design AI systems that enhance team collective intelligence by optimizing collective attention.

The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech. However, the efficacy of these models diminishes when applied to atypical speech, such as stuttering. This paper introduces AS-70, the first publicly available Mandarin stuttered speech dataset, which stands out as the largest dataset in its category. Encompassing conversational and voice command reading speech, AS-70 includes verbatim manual transcription, rendering it suitable for various speech-related tasks. Furthermore, baseline systems are established, and experimental results are presented for ASR and stuttering event detection (SED) tasks. By incorporating this dataset into the model fine-tuning, significant improvements in the state-of-the-art ASR models, e.g., Whisper and Hubert, are observed, enhancing their inclusivity in addressing stuttered speech.

Automatic speech recognition (ASR) systems, increasingly prevalent in education, healthcare, employment, and mobile technology, face significant challenges in inclusivity, particularly for the 80 million-strong global community of people who stutter. These systems often fail to accurately interpret speech patterns deviating from typical fluency, leading to critical usability issues and misinterpretations. This study evaluates six leading ASRs, analyzing their performance on both a real-world dataset of speech samples from individuals who stutter and a synthetic dataset derived from the widely-used LibriSpeech benchmark. The synthetic dataset, uniquely designed to incorporate various stuttering events, enables an in-depth analysis of each ASR's handling of disfluent speech. Our comprehensive assessment includes metrics such as word error rate (WER), character error rate (CER), and semantic accuracy of the transcripts. The results reveal a consistent and statistically significant accuracy bias across all ASRs against disfluent speech, manifesting in significant syntactical and semantic inaccuracies in transcriptions. These findings highlight a critical gap in current ASR technologies, underscoring the need for effective bias mitigation strategies. Addressing this bias is imperative not only to improve the technology's usability for people who stutter but also to ensure their equitable and inclusive participation in the rapidly evolving digital landscape.

In the wake of the surging tide of deep learning over the past decade, Automatic Speech Recognition (ASR) has garnered substantial attention, leading to the emergence of numerous publicly accessible ASR systems that are actively being integrated into our daily lives. Nonetheless, the impartial and replicable evaluation of these ASR systems encounters challenges due to various crucial subtleties. In this paper we introduce the SpeechColab Leaderboard, a general-purpose, open-source platform designed for ASR evaluation. With this platform: (i) We report a comprehensive benchmark, unveiling the current state-of-the-art panorama for ASR systems, covering both open-source models and industrial commercial services. (ii) We quantize how distinct nuances in the scoring pipeline influence the final benchmark outcomes. These include nuances related to capitalization, punctuation, interjection, contraction, synonym usage, compound words, etc. These issues have gained prominence in the context of the transition towards an End-to-End future. (iii) We propose a practical modification to the conventional Token-Error-Rate (TER) evaluation metric, with inspirations from Kolmogorov complexity and Normalized Information Distance (NID). This adaptation, called modified-TER (mTER), achieves proper normalization and symmetrical treatment of reference and hypothesis. By leveraging this platform as a large-scale testing ground, this study demonstrates the robustness and backward compatibility of mTER when compared to TER. The SpeechColab Leaderboard is accessible at https://github.com/SpeechColab/Leaderboard