Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings
This work addresses the challenge of improving spoken term detection for applications like speech recognition, but it is incremental as it builds upon existing multi-view approaches.
The paper tackled the problem of learning acoustic word embeddings for query-by-example spoken term detection by proposing a network architecture that combines Siamese multi-view encoders with a shared decoder to enhance the relationship between acoustic and text embeddings, achieving an 11.1% relative improvement in average precision on the WSJ dataset.
Acoustic word embeddings --- fixed-dimensional vector representations of arbitrary-length words --- have attracted increasing interest in query-by-example spoken term detection. Recently, on the fact that the orthography of text labels partly reflects the phonetic similarity between the words' pronunciation, a multi-view approach has been introduced that jointly learns acoustic and text embeddings. It showed that it is possible to learn discriminative embeddings by designing the objective which takes text labels as well as word segments. In this paper, we propose a network architecture that expands the multi-view approach by combining the Siamese multi-view encoders with a shared decoder network to maximize the effect of the relationship between acoustic and text embeddings in embedding space. Discriminatively trained with multi-view triplet loss and decoding loss, our proposed approach achieves better performance on acoustic word discrimination task with the WSJ dataset, resulting in 11.1% relative improvement in average precision. We also present experimental results on cross-view word discrimination and word level speech recognition tasks.