Multi-view Recurrent Neural Acoustic Word Embeddings

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.

Appearing in ICLR 2017

Cited by in corpus (8)

• Effectiveness of self-supervised pre-training for speech recognition
• End-to-End ASR-free Keyword Search from Speech
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings
• Multilingual Jointly Trained Acoustic and Written Word Embeddings
• Acoustic Neighbor Embeddings
• Learning Joint Acoustic-Phonetic Word Embeddings
• Whole-Word Segmental Speech Recognition with Acoustic Word Embeddings
• Multimodal and Multi-view Models for Emotion Recognition