"P.W. Ellis, Daniel" - Selaus tekijän mukaan TUNICRIS-julkaisut
Viitteet 1-7 / 7
-
Assessment of Self-Attention on Learned Features For Sound Event Localization and Detection
(DCASE, 15.11.2021)
conferenceObject -
Audio-visual scene classification: analysis of DCASE 2021 Challenge submissions
(DCASE, 15.11.2021)
conferenceObjectThis paper presents the details of the Audio-Visual Scene Classification task in the DCASE 2021 Challenge (Task 1 Subtask B). The task is concerned with classification using audio and video modalities, using a dataset of ... -
Continual Learning for Automated Audio Captioning Using the Learning without Forgetting Approach
(DCASE, 15.11.2021)
conferenceObject -
Diversity and bias in audio captioning datasets
(DCASE, 15.11.2021)
conferenceObjectDescribing soundscapes in sentences allows better understanding of the acoustic scene than a single label indicating the acoustic scene class or a set of audio tags indicating the sound events active in the audio clip. In ... -
Evaluating Off-the-Shelf Machine Listening and Natural Language Models for Automated Audio Captioning
(DCASE, 15.11.2021)
conferenceObject -
Fairness and Underspecification in Acoustic Scene Classification: The Case for Disaggregated Evaluations
(DCASE, 15.11.2021)
conferenceObject -
Low-complexity acoustic scene classification for multi-device audio: analysis of DCASE 2021 Challenge systems
(DCASE, 15.11.2021)
conferenceObjectThis paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task targeted development of low-complexity solutions with good generalization properties. The provided baseline ...
