Multitask Learning With Low-Level Auxiliary Tasks For Encoder-Decoder Based Speech Recognition
18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION(2017)
摘要
End-to-end training of deep learning-based models allows for implicit learning of intermediate representations based on the final task loss. However, the end-to-end approach ignores the useful domain knowledge encoded in explicit intermediate-level supervision. We hypothesize that using intermediate representations as auxiliary supervision at lower levels of deep networks may be a good way of combining the advantages of end-to-end training and more traditional pipeline approaches. We present experiments on conversational speech recognition where we use lower-level tasks, such as phoneme recognition, in a multitask training approach with an encoder-decoder model for direct character transcription. We compare multiple types of lower-level tasks and analyze the effects of the auxiliary tasks. Our results on the Switchboard corpus show that this approach improves recognition accuracy over a standard encoder-decoder model on the Eva12000 test set.
更多查看译文
关键词
speech recognition, multitask learning, encoder-decoder, CTC, LSTM
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络