arXiv subjects

Ilhan Aslan

Publications and source records attributed to Ilhan Aslan.

18 recordsLinked to original sources

arXiv2025

Detecting COPD Through Speech Analysis: A Dataset of Danish Speech and Machine Learning Approach

Chronic Obstructive Pulmonary Disease (COPD) is a serious and debilitating disease affecting millions around the world. Its early detection using non-invasive means could enable preventive interventions that improve quality of life and patient outcomes, with speech recently shown to be a valuable biomarker. Yet, its validity across different linguistic groups remains to be seen. To that end, audio data were collected from 96 Danish participants conducting three speech tasks (reading, coughing, sustained vowels). Half of the participants were diagnosed with different levels of COPD and the other half formed a healthy control group. Subsequently, we investigated different baseline models using openSMILE features and learnt x-vector embeddings. We obtained a best accuracy of 67% using openSMILE features and logistic regression. Our findings support the potential of speech-based analysis as a non-invasive, remote, and scalable screening tool as part of future COPD healthcare solutions.

cs.SD↗

arXiv2025

"How to Explore Biases in Speech Emotion AI with Users?" A Speech-Emotion-Acting Study Exploring Age and Language Biases

This study explores how age and language shape the deliberate vocal expression of emotion, addressing underexplored user groups, Teenagers (N = 12) and Adults 55+ (N = 12), within speech emotion recognition (SER). While most SER systems are trained on spontaneous, monolingual English data, our research evaluates how such models interpret intentionally performed emotional speech across age groups and languages (Danish and English). To support this, we developed a novel experimental paradigm combining a custom user interface with a backend for real-time SER prediction and data logging. Participants were prompted to hit visual targets in valence-arousal space by deliberately expressing four emotion targets. While limitations include some reliance on self-managed voice recordings and inconsistent task execution, the results suggest contrary to expectations, no significant differences between language or age groups, and a degree of cross-linguistic and age robustness in model interpretation. Though some limitations in high-arousal emotion recognition were evident. Our qualitative findings highlight the need to move beyond system-centered accuracy metrics and embrace more inclusive, human-centered SER models. By framing emotional expression as a goal-directed act and logging the real-time gap between human intent and machine interpretation, we expose the risks of affective misalignment.

cs.HC↗

arXiv2025

"If we misunderstand the client, we misspend 100 hours": Exploring conversational AI and response types for information elicitation

Client-designer alignment is crucial to the success of design projects, yet little research has explored how digital technologies might influence this alignment. To address this gap, this paper presents a three-phase study investigating how digital systems can support requirements elicitation in professional design practice. Specifically, it examines how integrating a conversational agent and choice-based response formats into a digital elicitation tool affects early-stage client-designer collaboration. The first phase of the study inquired into the current practices of 10 design companies through semi-structured interviews, informing the system's design. The second phase evaluated the system using a 2x2 factorial design with 50 mock clients, quantifying the effects of conversational AI and response type on user experience and perceived preparedness. In phase three, the system was presented to seven of the original 10 companies to gather reflections on its value, limitations, and potential integration into practice. Findings show that both conversational AI and choice-based responses lead to lower dependability scores on the User Experience Questionnaire, yet result in client input with greater clarity. We contribute design implications for integrating conversational AI and choice-based responses into elicitation tools to support mutual understanding in early-stage client-designer collaboration.

cs.HC↗

arXiv2025

Speech Command + Speech Emotion: Exploring Emotional Speech Commands as a Compound and Playful Modality

In an era of human-computer interaction with increasingly agentic AI systems capable of connecting with users conversationally, speech is an important modality for commanding agents. By recognizing and using speech emotions (i.e., how a command is spoken), we can provide agents with the ability to emotionally accentuate their responses and socially enrich users' perceptions and experiences. To explore the concept and impact of speech emotion commands on user perceptions, we realized a prototype and conducted a user study (N = 14) where speech commands are used to steer two vehicles in a minimalist and retro game style implementation. While both agents execute user commands, only one of the agents uses speech emotion information to adapt its execution behavior. We report on differences in how users perceived each agent, including significant differences in stimulation and dependability, outline implications for designing interactions with agents using emotional speech commands, and provide insights on how users consciously emote, which we describe as "voice acting".

cs.HC↗

arXiv2025

Towards Sustainable Creativity Support: An Exploratory Study on Prompt Based Image Generation

Creativity is a valuable human skill that has long been augmented through both analog and digital tools. Recent progress in generative AI, such as image generation, provides a disruptive technological solution to supporting human creativity further and helping humans generate solutions faster. While AI image generators can help to rapidly visualize ideas based on user prompts, the use of such AI systems has also been critiqued due to their considerable energy usage. In this paper, we report on a user study (N = 24) to understand whether energy consumption can be reduced without impeding on the tool's perceived creativity support. Our results highlight that, for example, a main effect of (image generation) condition on energy consumption, and index of creativity support per prompt but not per task, which seem mainly attributed to image quantity per prompt. We provide details of our analysis on the relation between energy usage, creativity support, and prompting behavior, including attitudes towards designing with AI and its environmental impact.

cs.HC↗

arXiv2025

Static Vs. Agentic Game Master AI for Facilitating Solo Role-Playing Experiences

This paper presents a game master AI for single-player role-playing games. The AI is designed to deliver interactive text-based narratives and experiences typically associated with multiplayer tabletop games like Dungeons & Dragons. We report on the design process and the series of experiments to improve the functionality and experience design, resulting in two functional versions of the system. While v1 of our system uses simplified prompt engineering, v2 leverages a multi-agent architecture and the ReAct framework to include reasoning and action. A comparative evaluation demonstrates that v2 as an agentic system maintains play while significantly improving modularity and game experience, including immersion and curiosity. Our findings contribute to the evolution of AI-driven interactive fiction, highlighting new avenues for enhancing solo role-playing experiences.

cs.HC↗

arXiv2025

Speejis: Enhancing User Experience of Mobile Voice Messaging with Automatic Visual Speech Emotion Cues

Mobile messaging apps offer an increasing range of emotional expressions, such as emojis to help users manually augment their texting experiences. Accessibility of such augmentations is limited in voice messaging. With the term "speejis" we refer to accessible emojis and other visual speech emotion cues that are created automatically from speech input alone. The paper presents an implementation of speejis and reports on a user study (N=12) comparing the UX of voice messaging with and without speejis. Results show significant differences in measures such as attractiveness and stimulation and a clear preference of all participants for messaging with speejis. We highlight the benefits of using paralinguistic speech processing and continuous emotion models to enable finer grained augmentations of emotion changes and transitions within a single message in addition to augmentations of the overall tone of the message.

cs.HC↗

arXiv2024

Feel my Speech: Automatic Speech Emotion Conversion for Tangible, Haptic, or Proxemic Interaction Design

Innovations in interaction design are increasingly driven by progress in machine learning fields. Automatic speech emotion recognition (SER) is such an example field on the rise, creating well performing models, which typically take as input a speech audio sample and provide as output digital labels or values describing the human emotion(s) embedded in the speech audio sample. Such labels and values are only abstract representations of the felt or expressed emotions, making it challenging to analyse them as experiences and work with them as design material for physical interactions, including tangible, haptic, or proxemic interactions. This paper argues that both the analysis of emotions and their use in interaction designs would benefit from alternative physical representations, which can be directly felt and socially communicated as bodily sensations or spatial behaviours. To this end, a method is described and a starter kit for speech emotion conversion is provided. Furthermore, opportunities of speech emotion conversion for new interaction designs are introduced, such as for interacting with animals or robots.

cs.HC↗

arXiv2024

Audio Enhancement for Computer Audition -- An Iterative Training Paradigm Using Sample Importance

Neural network models for audio tasks, such as automatic speech recognition (ASR) and acoustic scene classification (ASC), are susceptible to noise contamination for real-life applications. To improve audio quality, an enhancement module, which can be developed independently, is explicitly used at the front-end of the target audio applications. In this paper, we present an end-to-end learning solution to jointly optimise the models for audio enhancement (AE) and the subsequent applications. To guide the optimisation of the AE module towards a target application, and especially to overcome difficult samples, we make use of the sample-wise performance measure as an indication of sample importance. In experiments, we consider four representative applications to evaluate our training paradigm, i.e., ASR, speech command recognition (SCR), speech emotion recognition (SER), and ASC. These applications are associated with speech and non-speech tasks concerning semantic and non-semantic features, transient and global information, and the experimental results indicate that our proposed approach can considerably boost the noise robustness of the models, especially at low signal-to-noise ratios (SNRs), for a wide range of computer audition tasks in everyday-life noisy environments.

cs.SD↗

arXiv2024

Modeling Emotional Trajectories in Written Stories Utilizing Transformers and Weakly-Supervised Learning

Telling stories is an integral part of human communication which can evoke emotions and influence the affective states of the audience. Automatically modeling emotional trajectories in stories has thus attracted considerable scholarly interest. However, as most existing works have been limited to unsupervised dictionary-based approaches, there is no benchmark for this task. We address this gap by introducing continuous valence and arousal labels for an existing dataset of children's stories originally annotated with discrete emotion categories. We collect additional annotations for this data and map the categorical labels to the continuous valence and arousal space. For predicting the thus obtained emotionality signals, we fine-tune a DeBERTa model and improve upon this baseline via a weakly supervised learning approach. The best configuration achieves a Concordance Correlation Coefficient (CCC) of $.8221$ for valence and $.7125$ for arousal on the test set, demonstrating the efficacy of our proposed approach. A detailed analysis shows the extent to which the results vary depending on factors such as the author, the individual story, or the section within the story. In addition, we uncover the weaknesses of our approach by investigating examples that prove to be difficult to predict.

cs.CL↗

arXiv2023

How to Compliment a Human -- Designing Affective and Well-being Promoting Conversational Things

With today's technologies it seems easier than ever to augment everyday things with the ability to perceive their environment and to talk to users. Considering conversational user interfaces, tremendous progress has already been made in designing and evaluating task oriented conversational interfaces, such as voice assistants for ordering food, booking a flight etc. However, it is still very challenging to design smart things that can have with their users an informal conversation and emotional exchange, which requires the smart thing to master the usage of social everyday utterances, using irony and sarcasm, delivering good compliments, etc. In this paper, we focus on the experience design of compliments and the Complimenting Mirror design. The paper reports in detail on three phases of a human-centered design process including a Wizard of Oz study in the lab with 24 participants to explore and identify the effect of different compliment types on user experiences and a consequent field study with 105 users in an architecture museum with a fully functional installation of the Complimenting Mirror. In our analyses we argue why and how a "smart" mirror should compliment users and provide a theorization applicable for affective interaction design with things in more general. We focus on subjective user feedback including user concerns and prepositions of receiving compliments from a thing and on observations of real user behavior in the field i.e. transitions of bodily affective expressions comparing affective user states before, during, and after compliment delivery. Our research shows that compliment design matters significantly and using the right type of compliments in our final design in the field test, we succeed in achieving reactive expressions of positive emotions, "sincere" smiles and laughter, even from the seemingly sternest users.

cs.HC↗

arXiv2022

Automatic Emotion Modelling in Written Stories

Telling stories is an integral part of human communication which can evoke emotions and influence the affective states of the audience. Automatically modelling emotional trajectories in stories has thus attracted considerable scholarly interest. However, as most existing works have been limited to unsupervised dictionary-based approaches, there is no labelled benchmark for this task. We address this gap by introducing continuous valence and arousal annotations for an existing dataset of children's stories annotated with discrete emotion categories. We collect additional annotations for this data and map the originally categorical labels to the valence and arousal space. Leveraging recent advances in Natural Language Processing, we propose a set of novel Transformer-based methods for predicting valence and arousal signals over the course of written stories. We explore several strategies for fine-tuning a pretrained ELECTRA model and study the benefits of considering a sentence's context when inferring its emotionality. Moreover, we experiment with additional LSTM and Transformer layers. The best configuration achieves a Concordance Correlation Coefficient (CCC) of .7338 for valence and .6302 for arousal on the test set, demonstrating the suitability of our proposed approach. Our code and additional annotations are made available at https://github.com/lc0197/emotion_modelling_stories.

cs.CL↗

arXiv2022

An Overview & Analysis of Sequence-to-Sequence Emotional Voice Conversion

Emotional voice conversion (EVC) focuses on converting a speech utterance from a source to a target emotion; it can thus be a key enabling technology for human-computer interaction applications and beyond. However, EVC remains an unsolved research problem with several challenges. In particular, as speech rate and rhythm are two key factors of emotional conversion, models have to generate output sequences of differing length. Sequence-to-sequence modelling is recently emerging as a competitive paradigm for models that can overcome those challenges. In an attempt to stimulate further research in this promising new direction, recent sequence-to-sequence EVC papers were systematically investigated and reviewed from six perspectives: their motivation, training strategies, model architectures, datasets, model inputs, and evaluation methods. This information is organised to provide the research community with an easily digestible overview of the current state-of-the-art. Finally, we discuss existing challenges of sequence-to-sequence EVC.

cs.SD↗

arXiv2021

On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the SER systems. Further, more clarification is required for analysing the impact of ASR's word error rate (WER) on linguistic emotion recognition per se and in the context of fusion with acoustic information exploitation in the age of deep ASR systems. In order to tackle the above issues, we create transcripts from the original speech by applying three modern ASR systems, including an end-to-end model trained with recurrent neural network-transducer loss, a model with connectionist temporal classification loss, and a wav2vec framework for self-supervised learning. Afterwards, we use pre-trained textual models to extract text representations from the ASR outputs and the gold standard. For extraction and learning of acoustic speech features, we utilise openSMILE, openXBoW, DeepSpectrum, and auDeep. Finally, we conduct decision-level fusion on both information streams -- acoustics and linguistics. Using the best development configuration, we achieve state-of-the-art unweighted average recall values of $73.6\,\%$ and $73.8\,\%$ on the speaker-independent development and test partitions of IEMOCAP, respectively.

cs.SD↗

arXiv2021

Towards Tool-Support for Interactive-Machine Learning Applications in the Android Ecosystem

Consumer applications are becoming increasingly smarter and most of them have to run on device ecosystems. Potential benefits are for example enabling cross-device interaction and seamless user experiences. Essential for today's smart solutions with high performance are machine learning models. However, these models are often developed separately by AI engineers for one specific device and do not consider the challenges and potentials associated with a device ecosystem in which their models have to run. We believe that there is a need for tool-support for AI engineers to address the challenges of implementing, testing, and deploying machine learning models for a next generation of smart interactive consumer applications. This paper presents preliminary results of a series of inquiries, including interviews with AI engineers and experiments for an interactive machine learning use case with a Smartwatch and Smartphone. We identified the themes through interviews and hands-on experience working on our use case and proposed features, such as data collection from sensors and easy testing of the resources consumption of running pre-processing code on the target device, which will serve as tool-support for AI engineers.

cs.HC↗

arXiv2020

Towards Somaesthetics Inspired Games: Exploring the Influence of a Mirror Effect on Self-Presentation in a Public Setting

We report on an initial user study, which explores how players of an augmented mirror game, self-style or self-present themselves when they are allowed to see themselves in the mirror compared to when they do not see themselves. To this end, we customized an open source fruit slicing game into an interactive installation for an architecture museum and conducted with 36 visitors a field study. Based on an analysis of video recordings of participants we identified, for example significant differences in how often participants smile. Ultimately, presenting a self-image to gamers in a social setting resulted in behavior change, which we argue could be utilized carefully from a Somaesthetics perspective as an experience design feature in future games.

cs.HC↗

arXiv2020

Drawing with AI -- Exploring Collaborative Inking Experiences Based on Mid-air Pointing and Reinforcement Learning

Digitalization is changing the nature of tools and materials, which are used in artistic practices in professional and non-professional settings. For example, today it is common that even children express their ideas and explore their creativity by drawing on tablets as digital canvases. While there are many software-based tools, which resemble traditional tools, such as various forms of virtual brushes, erasers, etc. in contrast to traditional materials there is potential in augmenting software-based tools and digital canvases with artificial intelligence. Curious about how it would feel to interact with a digital canvas, which would be in contrast to a traditional canvas dynamic, responsive, and potentially able to continuously adapt to its user's input, we developed a drawing application and conducted a qualitative study with 14 users. In this paper, we describe details of our design process, which lead up to using a k-armed bandit as a simple form of reinforcement learning and a LeapMotion sensor to allow people from all walks of like, old and young to draw on pervasive displays, small and large, positioned near or far.

cs.HC↗

arXiv2020

Resonating Experiences of Self and Others enabled by a Tangible Somaesthetic Design

Digitalization is penetrating every aspect of everyday life including a human's heart beating, which can easily be sensed by wearable sensors and displayed for others to see, feel, and potentially "bodily resonate" with. Previous work in studying human interactions and interaction designs with physiological data, such as a heart's pulse rate, have argued that feeding it back to the users may, for example support users' mindfulness and self-awareness during various everyday activities and ultimately support their wellbeing. Inspired by Somaesthetics as a discipline, which focuses on an appreciation of the living body's role in all our experiences, we designed and explored mobile tangible heart beat displays, which enable rich forms of bodily experiencing oneself and others in social proximity. In this paper, we first report on the design process of tangible heart displays and then present results of a field study with 30 pairs of participants. Participants were asked to use the tangible heart displays during watching movies together and report their experience in three different heart display conditions (i.e., displaying their own heart beat, their partner's heart beat, and watching a movie without a heart display). We found, for example that participants reported significant effects in experiencing sensory immersion when they felt their own heart beats compared to the condition without any heart beat display, and that feeling their partner's heart beats resulted in significant effects on social experience. We refer to resonance theory to discuss the results, highlighting the potential of how ubiquitous technology could utilize physiological data to provide resonance in a modern society facing social acceleration.

cs.HC↗