Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition
This addresses the issue of out-of-vocabulary word recognition in deployed ASR systems, enabling instant updates for specific contexts, though it is incremental as it builds on existing memory-augmented approaches.
The paper tackles the problem of neural sequence-to-sequence speech recognition systems failing to recognize out-of-vocabulary words like named entities or technical terms, and demonstrates that supplementing the system with a memory mechanism allows instant addition of new words without retraining, achieving over 85% recognition of previously unrecognized words compared to a baseline.
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.