Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition

TL;DR

This paper introduces a method to enhance neural speech recognition systems by adding a dynamic memory for new words, enabling instant recognition of unseen words without retraining.

Contribution

It presents a novel memory-augmented end-to-end speech recognition system that recognizes unseen words instantly by accessing a supplementary memory.

Findings

Recognizes over 85% of newly added words that were previously unrecognized.

Operates without additional training after deployment.

Improves open vocabulary recognition in neural ASR systems.

Abstract

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary systems. In practice, however, they often fail to recognize words not seen during training, e.g., named entities, numbers or technical terms. To alleviate this problem we supplement an end-to-end ASR system with a word/phrase memory and a mechanism to access this memory to recognize the words and phrases correctly. After the training of the ASR system, and when it has already been deployed, a relevant word can be added or subtracted instantly without the need for further training. In this paper we demonstrate that through this mechanism our system is able to recognize more than 85% of newly added words that it previously failed to recognize compared to a strong baseline.