Name
Abstract | ||
|---|---|---|
Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips' sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not been investigated. This paper contributes an Audio-Grounding dataset(1), which provides the correspondence between sound events and the captions provided in Audiocaps, along with the location (timestamps) of each present sound event. Based on such, we propose the text-to-audio grounding (TAG) task, which interactively considers the relationship between audio processing and language understanding. A baseline approach is provided, resulting in an event-F1 score of 28.3% and a Polyphonic Sound Detection Score (PSDS) score of 14.7%. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ICASSP39728.2021.9414834 | 2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021) |
Keywords | DocType | Citations |
text-to-audio grounding, sound event detection, dataset, deep learning | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xuenan Xu | 1 | 0 | 2.70 |
| Heinrich Dinkel | 2 | 23 | 5.79 |
| Mengyue Wu | 3 | 0 | 4.73 |
| Kai Yu | 4 | 1082 | 90.58 |