Character-Level Incremental Speech Recognition with Recurrent Neural Networks
arXiv:1601.06581 · doi:10.1109/ICASSP.2016.7472696
Abstract
In real-time speech recognition applications, the latency is an important issue. We have developed a character-level incremental speech recognition (ISR) system that responds quickly even during the speech, where the hypotheses are gradually improved while the speaking proceeds. The algorithm employs a speech-to-character unidirectional recurrent neural network (RNN), which is end-to-end trained with connectionist temporal classification (CTC), and an RNN-based character-level language model (LM). The output values of the CTC-trained RNN are character-level probabilities, which are processed by beam search decoding. The RNN LM augments the decoding by providing long-term dependency information. We propose tree-based online beam search with additional depth-pruning, which enables the system to process infinitely long input speech with low latency. This system not only responds quickly on speech but also can dictate out-of-vocabulary (OOV) words according to pronunciation. The proposed model achieves the word error rate (WER) of 8.90% on the Wall Street Journal (WSJ) Nov'92 20K evaluation set when trained on the WSJ SI-284 training set.
To appear in ICASSP 2016
References in corpus (3)
Cited by in corpus (9)
- Who Needs Words? Lexicon-Free Speech Recognition
- Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition
- A limited-size ensemble of homogeneous CNN/LSTMs for high-performance word classification
- Simultaneous Speech-to-Speech Translation System with Neural Incremental ASR, MT, and TTS
- Generative Knowledge Transfer for Neural Language Models
- Character-Level Language Modeling with Hierarchical Recurrent Neural Networks
- FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks
- Leveraging Cross-Utterance Context For ASR Decoding
- Sequence-to-Sequence Learning via Attention Transfer for Incremental Speech Recognition