We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train the attention and decoder networks. In this paper we address this shortcoming by pretraining our network parameters using only text-based data and transcribed speech from other languages. We analyze the relative contributions of both sources of data. Across 3 test languages, our text-based approach resulted in a 20% average relative improvement over a text-based augmentation technique without pretraining. Using transcribed speech from nearby languages gives a further 20-30% relative reduction in character error rate.
|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 - 2019|
|イベント||20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria|
継続期間: 2019 9月 15 → 2019 9月 19
ASJC Scopus subject areas