An active approach to speaker and task adaptation based on automatic analysis of vocabulary confusability

Speaker and task adaptation can be made more efficient if an automatic speech recognition system can actively elicit particularly useful adaptation data from a new speaker for a given speech recognition task. This paper presents such an active approach based on an automatic analysis of how difficult the given task vocabulary is. Comparative experiments are designed and conducted for a simple application scenario of searching an item from a long list via voice. The experimental results demonstrate that the proposed active adaptation strategy performs much better than traditional passive adaptation strategies.