Wide context acoustic modeling in read vs. spontaneous speech

Context-dependent acoustic models have been applied in speech recognition research for many years, and have been shown to increase the recognition accuracy signi cantly. The most common approach is to use triphones. Recently, several speech recognition groups have started investigating the use of larger phonetic context windows when building acoustic models. In this paper we discuss some of the computational problems arising from wide context modeling (polyphonic modeling) and present methods to cope with these problems. A two stage decision tree based polyphonic clustering approach is described which implements a more exible parameter tying scheme. The new clustering approach gave us signi cant improvement across all tasks WSJ, SWB, and Spontaneous Scheduling Task and across all languages involved (German, Spanish, English). We report recognition results based on the JANUS speech recognition toolkit [2, 8] on two tasks comparing acoustic context phenomena in English read versus spontaneous speech. We used our WSJ 60K recognizer and the JANUS SWB 10K polyphonic recognizer.