{"total":16,"rows":[{"id":"2102.13468","title":"The INTERSPEECH 2021 Computational Paralinguistics Challenge: COVID-19 Cough, COVID-19 Speech, Escalation & Primates","created":"2021-02-24","cited_by_count":32,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"area":null},{"id":"2110.14769","title":"Detecting Dementia from Speech and Transcripts using Transformers","created":"2021-10-27","cited_by_count":13,"area":null},{"id":"2104.11629","title":"DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data","created":"2021-04-23","cited_by_count":12,"area":null},{"id":"2304.14882","title":"The ACM Multimedia 2023 Computational Paralinguistics Challenge: Emotion Share & Requests","created":"2023-04-28","cited_by_count":8,"area":null},{"id":"2110.08895","title":"DECAR: Deep Clustering for learning general-purpose Audio Representations","created":"2021-10-17","cited_by_count":7,"area":null},{"id":"2104.10121","title":"On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era","created":"2021-04-20","cited_by_count":5,"area":null},{"id":"2305.16406","title":"Context-aware attention layers coupled with optimal transport domain adaptation and multimodal fusion methods for recognizing dementia from spontaneous speech","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2205.06799","title":"The ACM Multimedia 2022 Computational Paralinguistics Challenge: Vocalisations, Stuttering, Activity, & Mosquitoes","created":"2022-05-13","cited_by_count":4,"area":null},{"id":"2202.08981","title":"A Summary of the ComParE COVID-19 Challenges","created":"2022-02-17","cited_by_count":2,"area":null},{"id":"2110.05732","title":"Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables","created":"2021-10-12","cited_by_count":1,"area":null},{"id":"2203.13628","title":"DeLoRes: Decorrelating Latent Spaces for Low-Resource Audio Representation Learning","created":"2022-03-25","cited_by_count":1,"area":null},{"id":"2208.12086","title":"A Study on Broadcast Networks for Music Genre Classification","created":"2022-08-25","cited_by_count":1,"area":null},{"id":"2412.11943","title":"autrainer: A Modular and Extensible Deep Learning Toolkit for Computer Audition Tasks","created":"2024-12-16","cited_by_count":1,"area":null},{"id":"2107.13977","title":"Underwater Acoustic Networks for Security Risk Assessment in Public Drinking Water Reservoirs","created":"2021-07-29","cited_by_count":0,"area":null},{"id":"2206.13365","title":"Interpretable Acoustic Representation Learning on Breathing and Speech Signals for COVID-19 Detection","created":"2022-06-27","cited_by_count":0,"area":null}],"next_cursor":null}