| 1. |
- Bernardy, Jean-Philippe, 1978, et al.
(författare)
-
Modelling prosodic structure using Artificial Neural Networks
- 2017
-
Ingår i: ExLing 2017. Proceedings of 8 th Tutorial and Research Workshop on Experimental Linguistics, 19-22 June 2017, Heraklion, Crete, Greece / edited by Antonis Botinis. - Athens : University of Athens. - 2529-1092. - 9789604661626
-
Konferensbidrag (refereegranskat)abstract
- The ability to accurately perceive whether a speaker is asking a question or is making a statement is crucial for any successful interaction. However, learning and classifying tonal patterns has been a challenging task for automatic speech recognition and for models of tonal representation, as tonal contours are characterized by significant variation. This paper provides a classification model of Cypriot Greek questions and statements. We evaluate two state-of-the-art network architectures: a Long Short-Term Memory (LSTM) network and a convolutional network (ConvNet). The ConvNet outperforms the LSTM in the classification task and exhibited an excellent performance with 95% classification accuracy.
|
|
| 2. |
- Eckerström, Marie, 1981, et al.
(författare)
-
Neurodegeneration and the Gothenburg MCI study – a background to the linguistic and extralinguistic parameters for early detection of cognitive impairment-project.
- 2019
-
Ingår i: Proceedings of the 10th International Conference of Experimental Linguistics, 25-27 September 2019, Lisbon, Portugal / edited by Antonis Botinis. - : ExLing Society. - 2529-1092. - 9786188458505
-
Konferensbidrag (refereegranskat)abstract
- Mild cognitive impairment (MCI) is the stage between the expected cognitive decline of a normal aging population and the more serious decline of dementia. Typically, the performance of a cognitive test is considered impaired if it is =>1.5 standard deviations below normal controls. The ongoing Gothenburg mild cognitive impairment (MCI) study is an attempt to conduct longitudinal in-depth phenotyping of patients with different forms and degrees of cognitive impairment using various assessment tools. This paper presents the background of the linguistic and extralinguistic parameters for early detection of cognitive impairment-project, a research which is partly based on data acquired at the Gothenburg MCI-study.
|
|
| 3. |
- Johansson, Sofie, 1969, et al.
(författare)
-
Lexical diversity and mild cognitive impairment
- 2019
-
Ingår i: Proceedings of the 10th International Conference of Experimental Linguistics, 25-27 September 2019, Lisbon, Portugal / edited by Antonis Botinis. - Athens, Greece : ExLing Society. - 2529-1092. - 9786188458505
-
Konferensbidrag (refereegranskat)abstract
- This paper explores the role that various lexical-based measures play for differentiating between individuals with mild forms of cognitive impairment (MCI) and healthy controls (HC). Recent research underscores the importance of language and linguistic analysis as essential components that can contribute to a variety of sensitive cognitive measures for the identification of milder forms of cognitive impairment. Subtle language changes serve as a sign that an individual’s cognitive functions have been impacted, potentially leading to early diagnosis. Our research aims to identify linguistic biomarkers that could distinguish between individuals with MCI and HC and also be useful in predicting MCI.
|
|
| 4. |
- Kokkinakis, Dimitrios, 1965, et al.
(författare)
-
Analysis of mRNA-vaccine posts on Swedish Twitter data
- 2023
-
Ingår i: 14th International Conference of Experimental Linguistics, Athens, Greece. - 2529-1092.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- The aim of this study was to use Swedish social media data to capture public perspectives and sentiments regarding the abovementioned study on possible effect of the novel mRNA vaccines that became massively available to the public during late 2021. The intention is to understand the key issues (topics/themes) that have captured public attention in Sweden, as well as the barriers and facilitators to successful or not mRNA vaccines.
|
|
| 5. |
- Kokkinakis, Dimitrios, 1965, et al.
(författare)
-
Negative vaccine voices in Swedish social media
- 2022
-
Ingår i: Proceedings of the 13th International Conference of Experimental Linguistics. - 2529-1092.
-
Konferensbidrag (refereegranskat)abstract
- Vaccinations are one of the most significant interventions to public health, but vaccine hesitancy creates concerns for a portion of the population in many countries, including Sweden. Since discussions on vaccine hesitancy are often taken on social networking sites, data from Swedish social media are used to study and quantify the sentiment among the discussants on the vaccination-or-not topic during phases of the COVID-19 pandemic. Out of all the posts analyzed a majority showed a stronger negative sentiment, prevailing throughout the whole of the examined period, with some spikes or jumps due to the occurrence of certain vaccine-related events distinguishable in the results. Sentiment analysis can be a valuable tool to track public opinions regarding the use, efficacy, safety, and importance of vaccination.
|
|
| 6. |
- Lundholm Fors, Kristina, 1977, et al.
(författare)
-
Reading and mild cognitive impairment
- 2019
-
Ingår i: Proceedings of the 10th International Conference of Experimental Linguistics, 25-27 September 2019, Lisbon, Portugal / edited by Antonis Botinis. - : ExLing Society. - 2529-1092. - 9786188458505
-
Konferensbidrag (refereegranskat)abstract
- In the present study, we investigated the discriminatory power of eye-tracking features in distinguishing between individuals with mild cognitive impairment (MCI) and healthy controls (HC). The eye movements of the study participants were recorded at two different time points, 18 months apart. Using a machine learning approach with leave-one-out cross-validation, we were able to discriminate between the groups with 73.6 AUC. However, somewhat surprisingly the classification was less successful using data from the second recording session, which might be attributed to the non-static nature of cognitive status. Still, the outcome suggests that eye-tracking measures can be exploited as useful markers of MCI.
|
|
| 7. |
- Themistocleous, Charalambos, 1980, et al.
(författare)
-
Automated speech analysis improves MCI diagnosis
- 2020
-
Ingår i: Proceedings of the 11th Experimental Linguistics Conference (ExLing). - 2529-1092.
-
Konferensbidrag (refereegranskat)abstract
- Mild Cognitive Impairment (MCI) is a condition characterized by cognitive decline greater than expected for an individual's age and education level. In this study, we are investigating whether acoustic properties of speech production can improve the classification of individuals with MCI from healthy controls augmenting the Mini Mental State Examination, a traditional screening tool, with automatically extracted acoustic information. We found that just one acoustic feature, can improve the AUC score (measuring a trade-off between sensitivity and specificity) from 0.77 to 0.89 in a boosting classification task. These preliminary results suggest that computerized language analysis can improve the accuracy of traditional screening tools
|
|
| 8. |
- Themistocleous, Charalambos, 1980, et al.
(författare)
-
Effects of Mild Cognitive Impairment on vowel duration
- 2018
-
Ingår i: Proceedings of the 9th Tutorial & Research Workshop on Experimental Linguistics, 28 - 30 August 2018, Paris, France / edited by Antonis Botinis. - 2529-1092. - 9789604661626
-
Konferensbidrag (refereegranskat)abstract
- Mild cognitive impairment (MCI) is a neurological condition, which is characterized by a noticeable decline of cognitive abilities, including communicative and linguistic skills. In this study, we have measured the duration of vowels produced in a reading task by 55 speakers— 30 healthy controls and 25 MCI—. The main results showed that MCI speakers differed significantly from HC in vowel duration as MCI speakers produced overall longer vowels. Also, we found that gender effects on vowel duration were different in MCI and HC. One significant aspect of this finding is that they highlight the contribution of vowel acoustic features as markers of MCI.
|
|
| 9. |
- Themistocleous, Charalambos, 1980, et al.
(författare)
-
Speech and Mild Cognitive Impairment detection
- 2019
-
Ingår i: Proceedings of the 10th International Conference of Experimental Linguistics, 25-27 September 2019, Lisbon, Portugal / edited by Antonis Botinis. - : ExLing Society. - 2529-1092. - 9786188458505
-
Konferensbidrag (refereegranskat)abstract
- It is of great importance to detect objective markers that can enable the early and fast identification of individuals with Mild Cognitive Impairment (MCI) from healthy individuals to inform, patient care, family and treatment planning. Connected speech productions can offer such markers. This study analyses recordings from picture description tasks by Swedish individuals with MCI and healthy control individuals (HC) and shows that voice quality, periodicity, and speech rate distinguish individuals with MCI from HC.
|
|
