- Hui Lin
- Jui-Ting Huang
- Francoise Beaufays
- Brian Strope
- Yun-hsuan Sung
Abstract
We evaluate different architectures to recognize multilingual speech for real-time mobile applications. In particular, we show that combining the results of several recognizers greatly outperforms other solutions such as training a single large multilingual system or using an explicit language identification system to select the appropriate recognizer. Experiments are conducted on a trilingual English-French-Mandarin mobile speech task. The data set includes Google searches, Maps queries, as well as more general inputs such as email and short message dictation. Without pre-specifying the input language, the combined system achieves comparable accu- racy to that of the monolingual systems when the input language is known. The combined system is also roughly 5% absolute better than an explicit language identification approach, and 10% better than a single large multilingual system.
Research Areas
Learn more about how we do research
We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work