Preprint
Multi-view Recurrent Neural Acoustic Word Embeddings
arXiv (Cornell University)
03/10/2017
DOI: 10.48550/arxiv.1611.04496
Abstract
Recent work has begun exploring neural acoustic word embeddings---fixed-dimensional vector representations of arbitrary-length speech segments corresponding to words. Such embeddings are applicable to speech retrieval and recognition tasks, where reasoning about whole words may make it possible to avoid ambiguous sub-word representations. The main idea is to map acoustic sequences to fixed-dimensional vectors such that examples of the same word are mapped to similar vectors, while different-word examples are mapped to very different vectors. In this work we take a multi-view approach to learning acoustic word embeddings, in which we jointly learn to embed acoustic sequences and their corresponding character sequences. We use deep bidirectional LSTM embedding models and multi-view contrastive losses. We study the effect of different loss variants, including fixed-margin and cost-sensitive losses. Our acoustic word embeddings improve over previous approaches for the task of word discrimination. We also present results on other tasks that are enabled by the multi-view approach, including cross-view word discrimination and word similarity.
Details
- Title: Subtitle
- Multi-view Recurrent Neural Acoustic Word Embeddings
- Creators
- Wanjia HeWeiran WangKaren Livescu
- Resource Type
- Preprint
- Publication Details
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.1611.04496
- eISSN
- 2331-8422
- Language
- English
- Date posted
- 03/10/2017
- Academic Unit
- Computer Science
- Record Identifier
- 9984696566502771
Metrics
1 Record Views