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.
|ジャーナル||Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH|
|出版ステータス||Published - 2017|
|イベント||18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden|
継続期間: 2017 8 20 → 2017 8 24
ASJC Scopus subject areas