ELAN - aspects of interoperability and functionality

Sloetjes, Han; Somasundaram, Aarthy; Wittenburg, Peter

doi:10.21437/interspeech.2011-819

Cited by 42 publications

(45 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Samples were recorded using an H1n Zoom Handy Recorder for interviews in person and using Zoom for virtual assessments. Audio files of each discourse sample were imported and transcribed in the EUDICO Language Annotator (ELAN; Sloetjes & Wittenburg, 2008). Recordings were fully transcribed orthographically and included all verbal behaviours such as fillers.…”

Section: Methodsmentioning

confidence: 99%

The longitudinal trajectory of discourse from the hyperacute to the chronic phase in mild to moderate poststroke aphasia recovery: A case series study

Brisebois

Brambati

Rochon

et al. 2023

Intl J Lang & Comm Disor

View full text Add to dashboard Cite

Background Discourse analysis has recently received much attention in the aphasia literature. Even if post‐stroke language recovery occurs throughout the longitudinal continuum of recovery, very few studies have documented discourse changes from the hyperacute to the chronic phases of recovery. Aims To document a multilevel analysis of discourse changes from the hyperacute phase to the chronic phase of post‐stroke recovery using a series of single cases study designs. Methods & Procedures Four people with mild to moderate post‐stroke aphasia underwent four assessments (hyperacute: 0–24 h; acute: 24–72 h; subacute: 7–14 days; and chronic: 6–12 months post‐onset). Three discourse tasks were performed at each time point: a picture description, a personal narrative and a story retelling. Multilevel changes in terms of macro‐ and microstructural aspects were analysed. The results of each discourse task were combined for each time point. Individual effect sizes were computed to evaluate the relative strength of changes in an early and a late recovery time frame. Outcomes & Results Macrostructural results revealed improvements throughout the recovery continuum in terms of coherence and thematic efficiency. Also, the microstructural results demonstrated linguistic output improvement for three out of four participants. Namely, lexical diversity and the number of correct information units/min showed a greater gain in the early compared with the late recovery phase. Conclusions & Implications This study highlights the importance of investigating all discourse processing levels as the longitudinal changes in discourse operate differently at each phase of recovery. Overall results support future longitudinal discourse investigation in people with post‐stroke aphasia. What This Paper Adds What is already known on the subjectMulti‐level discourse analysis allows for in‐depth analysis of underlying discourse processes. To date, very little is known on the longitudinal discourse changes from aphasia onset through to the chronic stage of recovery. This study documents multi‐level discourse features in four people with mild to moderate aphasia in the hyperacute, acute, subacute and chronic stage of post‐stroke aphasia recovery. What this paper adds to existing knowledgeThe study found that most discourse variables demonstrated improvement throughout time. Macrostructural variables of coherence and thematic units improved throughout the continuum whereas microstructural variables demonstrated greater gains in the early compared to the late period of recovery. What are the potential or actual clinical implications of this work?This study suggests that multilevel discourse analysis will allow a better understanding of post‐stroke aphasia recovery, although more research is needed to determine the clinical utility of these findings. Future research may wish to investigate longitudinal discourse recovery in a larger sample of people with aphasia with heterogenous aphasia profiles and severities.

show abstract

Section: Methodsmentioning

confidence: 99%

The longitudinal trajectory of discourse from the hyperacute to the chronic phase in mild to moderate poststroke aphasia recovery: A case series study

Brisebois

Brambati

Rochon

et al. 2023

Intl J Lang & Comm Disor

View full text Add to dashboard Cite

show abstract

“…The corpus consisted of pairs of acquaintances holding a casual conversation for 1 h while being recorded. Questions and responses, social actions of questions (e.g., information requests, which ask for new information of factual or specific nature), question types (polar or content, as well as types of polar questions), and facial signals (like eyebrow frowns and raises) of the speakers in the corpus were manually transcribed by Dutch speakers using ELAN (5.5; Sloetjes & Wittenburg, 2008; for more details on the corpus conventions, see Nota et al., 2021, 2022; Trujillo & Holler, 2021). The transcription of questions and responses largely followed the coding scheme of Stivers and Enfield (2010), with additional rules to account for the complexity of the corpus data.…”

Section: Methodsmentioning

confidence: 99%

“…After that, all visual signals started before or at the onset of the verbal utterance (determined by the timing in the corpus), and had a gradual fade in and fade out that was largely based on the original fade lengths of those signals. Facial signal fades were coded in ELAN (5.5; Sloetjes & Wittenburg, 2008) from the first evidence of movement until the movement peak, or from the movement peak until the last evidence of movement. Fades under two frames were changed to 80 ms, to make the gradual build-up of the visual signals look more natural.…”

Section: Designmentioning

confidence: 99%

Conversational Eyebrow Frowns Facilitate Question Identification: An Online Study Using Virtual Avatars

Nota,

Trujillo,

Holler

2023

Cognitive Science

View full text Add to dashboard Cite

Conversation is a time‐pressured environment. Recognizing a social action (the ‘‘speech act,’’ such as a question requesting information) early is crucial in conversation to quickly understand the intended message and plan a timely response. Fast turns between interlocutors are especially relevant for responses to questions since a long gap may be meaningful by itself. Human language is multimodal, involving speech as well as visual signals from the body, including the face. But little is known about how conversational facial signals contribute to the communication of social actions. Some of the most prominent facial signals in conversation are eyebrow movements. Previous studies found links between eyebrow movements and questions, suggesting that these facial signals could contribute to the rapid recognition of questions. Therefore, we aimed to investigate whether early eyebrow movements (eyebrow frown or raise vs. no eyebrow movement) facilitate question identification. Participants were instructed to view videos of avatars where the presence of eyebrow movements accompanying questions was manipulated. Their task was to indicate whether the utterance was a question or a statement as accurately and quickly as possible. Data were collected using the online testing platform Gorilla. Results showed higher accuracies and faster response times for questions with eyebrow frowns, suggesting a facilitative role of eyebrow frowns for question identification. This means that facial signals can critically contribute to the communication of social actions in conversation by signaling social action‐specific visual information and providing visual cues to speakers’ intentions.

show abstract

“…Manual video annotation, such as using the ELAN tool [55], has long been in existence, but recent years have also seen automatic methods that could be used for scalable evaluation based on video. EgoScanning [28] processes first-person (egocentric) videos to detect important passages and adapts playback speed accordingly.…”

Section: Data-driven Evaluation In Hci and Visualizationmentioning

confidence: 99%

uxSense: Supporting User Experience Analysis with Visualization and Computer Vision

Batch

Fan

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Analyzing user behavior from usability evaluation can be a challenging and time-consuming task, especially as the number of participants and the scale and complexity of the evaluation grows. We propose UXSENSE, a visual analytics system using machine learning methods to extract user behavior from audio and video recordings as parallel time-stamped data streams. Our implementation draws on pattern recognition, computer vision, natural language processing, and machine learning to extract user sentiment, actions, posture, spoken words, and other features from such recordings. These streams are visualized as parallel timelines in a web-based front-end, enabling the researcher to search, filter, and annotate data across time and space. We present the results of a user study involving professional UX researchers evaluating user data using uxSense. In fact, we used uxSense itself to evaluate their sessions.

show abstract

ELAN - aspects of interoperability and functionality

Cited by 42 publications

References 2 publications

The longitudinal trajectory of discourse from the hyperacute to the chronic phase in mild to moderate poststroke aphasia recovery: A case series study

The longitudinal trajectory of discourse from the hyperacute to the chronic phase in mild to moderate poststroke aphasia recovery: A case series study

Conversational Eyebrow Frowns Facilitate Question Identification: An Online Study Using Virtual Avatars

uxSense: Supporting User Experience Analysis with Visualization and Computer Vision

Contact Info

Product

Resources

About