Alice Baird
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alice Baird has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
Björn Schuller
University of Augsburg
2 shared publications- Björn Schuller
Technische Universität München, Munich, Germany
2 shared publications Bjoern Schuller
GLAM -Group on Language, Audio & Music Imperial College London UK
1 shared publication- Bo Dong
Shenzhen University General Hospital, Shenzhen China
1 shared publication - Fengquan Dong
Department of Cardiology, Shenzhen University General Hospital, Shenzhen 518055, China
1 shared publication - Florian Metze
Carnegie Mellon University, Pittsburgh, PA, USA
1 shared publication
Latest Publications
- 14 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (2) , 1334-1350
The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements
Truly real-life data presents a strong, but exciting challenge for sentiment and emotion research. The high variety of possible ‘in-the-wild’ properties makes large datasets such as these indispensable with respect to building robust machine learning models. A sufficient quantity of data covering a deep variety in the challenges of each modality to force the exploratory analysis of the interplay of all modalities has not yet been made available in this context. In this contribution, we present MuSe-CaR, a first of its kind multimodal dataset. The data is publicly available as it recently served as the testing bed for the 1st Multimodal Sentiment Analysis Challenge, and focused on the tasks of emotion, emotion-target engagement, and trustworthiness recognition by means of comprehensively integrating the audio-visual and language modalities. Furthermore, we give a thorough overview of the dataset in terms of collection and annotation, including annotation tiers not used in this year's MuSe 2020. In addition, for one of the sub-challenges -- predicting the level of trustworthiness -- no participant outperformed the baseline model, and so we propose a simple, but highly efficient Multi-Head-Attention network that exceeds using multimodal fusion the baseline by around 0.2 CCC (almost 50 % improvement).
- 14 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 14 (2) , 1334-1350
The Multimodal Sentiment Analysis in Car Reviews (MuSe-CaR) Dataset: Collection, Insights and Improvements
Truly real-life data presents a strong, but exciting challenge for sentiment and emotion research. The high variety of possible ‘in-the-wild’ properties makes large datasets such as these indispensable with respect to building robust machine learning models. A sufficient quantity of data covering a deep variety in the challenges of each modality to force the exploratory analysis of the interplay of all modalities has not yet been made available in this context. In this contribution, we present MuSe-CaR, a first of its kind multimodal dataset. The data is publicly available as it recently served as the testing bed for the 1st Multimodal Sentiment Analysis Challenge, and focused on the tasks of emotion, emotion-target engagement, and trustworthiness recognition by means of comprehensively integrating the audio-visual and language modalities. Furthermore, we give a thorough overview of the dataset in terms of collection and annotation, including annotation tiers not used in this year's MuSe 2020. In addition, for one of the sub-challenges -- predicting the level of trustworthiness -- no participant outperformed the baseline model, and so we propose a simple, but highly efficient Multi-Head-Attention network that exceeds using multimodal fusion the baseline by around 0.2 CCC (almost 50 % improvement).
- 10 July 2020
- Published by Springer Nature
- p. 229-242
Interaction with the Soundscape: Exploring Emotional Audio Generation for Improved Individual Wellbeing
- 10 July 2020
- Published by Springer Nature
- p. 229-242
Interaction with the Soundscape: Exploring Emotional Audio Generation for Improved Individual Wellbeing
- 22 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 24 (7) , 2082-2092
Machine Listening for Heart Status Monitoring: Introducing and Benchmarking HSS—The Heart Sounds Shenzhen Corpus
Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
- 22 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 24 (7) , 2082-2092
Machine Listening for Heart Status Monitoring: Introducing and Benchmarking HSS—The Heart Sounds Shenzhen Corpus
Auscultation of the heart is a widely studied technique, which requires precise hearing from practitioners as a means of distinguishing subtle differences in heart-beat rhythm. This technique is popular due to its non-invasive nature, and can be an early diagnosis aid for a range of cardiac conditions. Machine listening approaches can support this process, monitoring continuously and allowing for a representation of both mild and chronic heart conditions. Despite this potential, relevant databases and benchmark studies are scarce. In this paper, we introduce our publicly accessible database, the Heart Sounds Shenzhen Corpus (HSS), which was first released during the recent INTERSPEECH 2018 ComParE Heart Sound sub-challenge. Additionally, we provide a survey of machine learning work in the area of heart sound recognition, as well as a benchmark for HSS utilising standard acoustic features and machine learning models. At best our support vector machine with Log Mel features achieves 49.7% unweighted average recall on a three category task (normal, mild, moderate/severe).
- Open Access
Acoustic Sounds for Wellbeing: A Novel Dataset and Baseline Results
The field of sound healing includes ancient practices coming from a broad range of cultures. Across such practices there is a variety of acoustic instrumentation utilised. Practitioners suggest that sound has the ability to target both mental and even physical health issues, e.g., chronic-stress, or joint-pain. Instruments including the Tibetan singing bowl and vocal chanting, are still widely used today. With the noise-floor of modern urban soundscapes continually increasing and known to impact wellbeing, methods to improve this are needed. With that in mind, this study presents the Acoustic Sounds for Wellbeing (ASW) dataset. The ASW dataset is a dataset gathered from YouTube including 88\,+ hrs of audio from 5-classes of acoustic instrumentation (Gongs, Drumming, Singing Bowls, and Chanting). We additionally present initial baseline classification results on the dataset, finding that conventional Mel-Frequency Cepstra coefficient features achieve at best an unweighted average recalled of 57.4 % for a 5-class support vector machine classification paradigm.
Open AccessAcoustic Sounds for Wellbeing: A Novel Dataset and Baseline Results
The field of sound healing includes ancient practices coming from a broad range of cultures. Across such practices there is a variety of acoustic instrumentation utilised. Practitioners suggest that sound has the ability to target both mental and even physical health issues, e.g., chronic-stress, or joint-pain. Instruments including the Tibetan singing bowl and vocal chanting, are still widely used today. With the noise-floor of modern urban soundscapes continually increasing and known to impact wellbeing, methods to improve this are needed. With that in mind, this study presents the Acoustic Sounds for Wellbeing (ASW) dataset. The ASW dataset is a dataset gathered from YouTube including 88\,+ hrs of audio from 5-classes of acoustic instrumentation (Gongs, Drumming, Singing Bowls, and Chanting). We additionally present initial baseline classification results on the dataset, finding that conventional Mel-Frequency Cepstra coefficient features achieve at best an unweighted average recalled of 57.4 % for a 5-class support vector machine classification paradigm.
- Open Access
Responsible and Representative Multimodal Data Acquisition and Analysis: On Auditability, Benchmarking, Confidence, Data-Reliance & Explainability
The ethical decisions behind the acquisition and analysis of audio, video or physiological human data, harnessed for (deep) machine learning algorithms, is an increasing concern for the Artificial Intelligence (AI) community. In this regard, herein we highlight the growing need for responsible, and representative data collection and analysis, through a discussion of modality diversification. Factors such as Auditability, Benchmarking, Confidence, Data-reliance, and Explainability (ABCDE), have been touched upon within the machine learning community, and here we lay out these ABCDE sub-categories in relation to the acquisition and analysis of multimodal data, to weave through the high priority ethical concerns currently under discussion for AI. To this end, we propose how these five subcategories can be included in early planning of such acquisition paradigms.
Open AccessResponsible and Representative Multimodal Data Acquisition and Analysis: On Auditability, Benchmarking, Confidence, Data-Reliance & Explainability
The ethical decisions behind the acquisition and analysis of audio, video or physiological human data, harnessed for (deep) machine learning algorithms, is an increasing concern for the Artificial Intelligence (AI) community. In this regard, herein we highlight the growing need for responsible, and representative data collection and analysis, through a discussion of modality diversification. Factors such as Auditability, Benchmarking, Confidence, Data-reliance, and Explainability (ABCDE), have been touched upon within the machine learning community, and here we lay out these ABCDE sub-categories in relation to the acquisition and analysis of multimodal data, to weave through the high priority ethical concerns currently under discussion for AI. To this end, we propose how these five subcategories can be included in early planning of such acquisition paradigms.