CNN-based Spoken Term Detection and Localization without Dynamic Programming
This work addresses a problem in speech processing for applications like audio search, but it appears incremental as it builds on existing embedding spaces and focuses on specific tasks.
The paper tackles spoken term detection and localization by predicting word embeddings from speech signals and comparing them to target terms, eliminating the need for dynamic programming at inference. It achieves evaluation on read speech corpora, though no concrete performance numbers are provided in the abstract.
In this paper, we propose a spoken term detection algorithm for simultaneous prediction and localization of in-vocabulary and out-of-vocabulary terms within an audio segment. The proposed algorithm infers whether a term was uttered within a given speech signal or not by predicting the word embeddings of various parts of the speech signal and comparing them to the word embedding of the desired term. The algorithm utilizes an existing embedding space for this task and does not need to train a task-specific embedding space. At inference the algorithm simultaneously predicts all possible locations of the target term and does not need dynamic programming for optimal search. We evaluate our system on several spoken term detection tasks on read speech corpora.