TL;DR
This paper introduces an end-to-end neural model optimized for open vocabulary keyword search in spoken content, effectively handling imbalanced data and improving retrieval accuracy over existing methods.
Contribution
The proposed model directly predicts keyword occurrences in speech frames and enhances existing LVCSR-based keyword search systems through rescoring.
Findings
Outperforms similar models on balanced keyword search tasks.
Handles imbalanced keyword search scenarios effectively.
Significantly improves LVCSR-based keyword search results.
Abstract
Recently, neural approaches to spoken content retrieval have become popular. However, they tend to be restricted in their vocabulary or in their ability to deal with imbalanced test settings. These restrictions limit their applicability in keyword search, where the set of queries is not known beforehand, and where the system should return not just whether an utterance contains a query but the exact location of any such occurrences. In this work, we propose a model directly optimized for keyword search. The model takes a query and an utterance as input and returns a sequence of probabilities for each frame of the utterance of the query having occurred in that frame. Experiments show that the proposed model not only outperforms similar end-to-end models on a task where the ratio of positive and negative trials is artificially balanced, but it is also able to deal with the far more…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
