Lithuanian Broadcast Speech Transcription Using Semi-supervised Acoustic Model Training

详细信息    查看全文

• 作者：Rasa Lileikytė^a ; ^{lileikyte@limsi.fr" class="auth_mail" title="E-mail the corresponding author} ; ^{rasalileikyte@gmail.com" class="auth_mail" title="E-mail the corresponding author} ; Arseniy Gorin^a ; Lori Lamel^a ; Jean-Luc Gauvain^a ; Thiago Fraga-Silva^b
• 关键词：Automatic speech recognition ; Low-resourced languages ; Semi-supervised training ; Neural networks ; Lithuanian language
• 刊名：Procedia Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：81
• 期：Complete
• 页码：107-113
• 全文大小：176 K

文摘

This paper reports on an experimental work to build a speech transcription system for Lithuanian broadcast data, relying on unsupervised and semi-supervised training methods as well as on other low-knowledge methods to compensate for missing resources. Unsupervised acoustic model training is investigated using 360 hours of untranscribed speech data. A graphemic pronunciation approach is used to simplify the pronunciation model generation and there-fore ease the language model adaptation for the system users. Discriminative training on top of semi-supervised training is also investigated, as well as various types of acoustic features and their combinations. Experimental results are provided for each of our development steps as well as contrastive results comparing various options. Using the best system configuration a word error rate of 18.3% is obtained on a set of development data from the Quaero program.