@inproceedings{BayerlTammewarRiedhammeretal.2021, author = {Bayerl, Sebastian P. and Tammewar, Aniruddha and Riedhammer, Korbinian and Riccardi, Giuseppe}, title = {Detecting Emotion Carriers by Combining Acoustic and Lexical Representations}, doi = {10.48550/arXiv.2112.06603}, pages = {8}, year = {2021}, abstract = {Personal narratives (PN) - spoken or written - are recollections of facts, people, events, and thoughts from one's own experience. Emotion recognition and sentiment analysis tasks are usually defined at the utterance or document level. However, in this work, we focus on Emotion Carriers (EC) defined as the segments (speech or text) that best explain the emotional state of the narrator ("loss of father", "made me choose"). Once extracted, such EC can provide a richer representation of the user state to improve natural language understanding and dialogue modeling. In previous work, it has been shown that EC can be identified using lexical features. However, spoken narratives should provide a richer description of the context and the users' emotional state. In this paper, we leverage word-based acoustic and textual embeddings as well as early and late fusion techniques for the detection of ECs in spoken narratives. For the acoustic word-level representations, we use Residual Neural Networks (ResNet) pretrained on separate speech emotion corpora and fine-tuned to detect EC. Experiments with different fusion and system combination strategies show that late fusion leads to significant improvements for this task.}, language = {en} } @inproceedings{TammewarBraunRoccabrunaetal.2022, author = {Tammewar, Aniruddha and Braun, Franziska and Roccabruna, Gabriel and Bayerl, Sebastian P. and Riedhammer, Korbinian and Riccardi, Giuseppe}, title = {Annotation of Valence for Spoken Personal Narratives}, pages = {10}, year = {2022}, abstract = {Personal Narrative (PN) is the recollection of individuals' life experiences, events, and thoughts along with the associated emotions in the form of a story. Compared to other genres such as social media texts or microblogs, where people write about ex-perienced events or products, the spoken PNs are complex to analyze and understand. They are usually long and unstructured, involving multiple and related events, characters as well as thoughts and emotions associated with events, objects, and persons. In spoken PNs, emotions are conveyed by changing the speech signal characteristics as well as the lexical content of the narrative. In this work, we annotate a corpus of spoken personal narratives, with the emotion valence using discrete values. The PNs are segmented into speech segments, and the annotators annotate them in the discourse context, with values on a 5 point bipolar scale ranging from -2 to +2 (0 for neutral). In this way, we capture the unfolding of the PNs events and changes in the emotional state of the narrator. We perform an in-depth analysis of the inter-annotator agreement, the relation between the label distribution w.r.t. the stimulus (positive/negative) used for the elicitation of the narrative, and compare the segment-level annotations to a baseline continuous annotation. We find that the neutral score plays an important role in the agreement. We observe that it is easy to differentiate the positive from the negative valence while the confusion with the neutral label is high.}, language = {en} }