CLJun 8, 2017

Advances in Joint CTC-Attention based End-to-End Speech Recognition with a Deep CNN Encoder and RNN-LM

arXiv:1706.02737v1310 citations
Originality Incremental advance
AI Analysis

This work improves speech recognition accuracy for spontaneous speech in Japanese and Chinese, though it appears incremental as it builds on existing joint CTC-attention approaches.

The authors tackled automatic speech recognition by developing an end-to-end model combining CTC and attention mechanisms with a deep CNN encoder and RNN language model, achieving a 5-10% error reduction on spontaneous Japanese and Chinese speech compared to prior systems and outperforming traditional hybrid ASR systems.

We present a state-of-the-art end-to-end Automatic Speech Recognition (ASR) model. We learn to listen and write characters with a joint Connectionist Temporal Classification (CTC) and attention-based encoder-decoder network. The encoder is a deep Convolutional Neural Network (CNN) based on the VGG network. The CTC network sits on top of the encoder and is jointly trained with the attention-based decoder. During the beam search process, we combine the CTC predictions, the attention-based decoder predictions and a separately trained LSTM language model. We achieve a 5-10\% error reduction compared to prior systems on spontaneous Japanese and Chinese speech, and our end-to-end model beats out traditional hybrid ASR systems.

Code Implementations6 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes