Abstract | ||
---|---|---|
Traditional search through collections of audio recordings compares a text-based query to text metadata associated with each audio file and does not address the actual content of the audio. Text descriptions do not describe all aspects of the audio content in detail. Query by vocal imitation (QBV) is a kind of query by example that lets users imitate the content of the audio they seek, providing an alternative search method to traditional text search. Prior work proposed several neural networks, such as TL-IMINET, for QBV, however, previous systems have not been deployed in an actual search engine nor evaluated by real users. We have developed a state-of-the-art QBV system (Vroom!) and a baseline query-by-text search engine (TextSearch). We deployed both systems in an experimental framework to perform user experiments with Amazon Mechanical Turk (AMT) workers. Results showed that Vroom! received significantly higher search satisfaction ratings than TextSearch did for sound categories that were difficult for subjects to describe by text. Results also showed a better overall ease-of-use rating for Vroom! than TextSearch on the sound library used in our experiments. These findings suggest that QBV, as a complimentary search approach to existing text-based search, can improve both search results and user experience.
|
Year | DOI | Venue |
---|---|---|
2020 | 10.1145/3343413.3377963 | CHIIR '20: Conference on Human Information Interaction and Retrieval
Vancouver BC
Canada
March, 2020 |
Keywords | DocType | ISBN |
vocal imitation, sound search, subjective evaluation, Siamese style convolutional recurrent neural networks, text description | Conference | 978-1-4503-6892-6 |
Citations | PageRank | References |
1 | 0.37 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yichi Zhang | 1 | 3 | 1.10 |
Junbo Hu | 2 | 1 | 0.37 |
Yiting Zhang | 3 | 1 | 0.37 |
Bryan Pardo | 4 | 830 | 63.92 |
Zhiyao Duan | 5 | 305 | 26.86 |