Two-stage continuous speech recognition using feature-based models: a preliminary study

In recent research, we have demonstrated that linguistic features can be used to improve speech recognition for an isolated vocabulary recognition task. This paper addresses two important new research problems in our attempts to build a two-stage speech recognition system using linguistic features. First, through a controlled study we show that our knowledge-driven feature sets perform competitively when compared with similar classes discovered by data-driven approaches. Secondly, we show that the cohort idea can be effectively generalized to continuous speech. Improved recognition results are achieved using this two-stage framework on multiple speech recognition experiments, on conversational telephone quality speech.