This paper describes a continuous speech recognition system using two-level predictive LR parsing. ATR has already implemented a predictive LR parsing algorithm in an HMM-based speech recognition system for Japanese. However, up to now, this system has used only intra-phrase grammatical constraints. In Japanese, a sentence is composed of several phrases, thus two kinds of grammars, namely an intra-phrase grammar and an inter-phrase grammar, are sufficient for recognizing sentences. Two-level predictive LR parsing makes it possible to use not only intra-phrase grammatical constraints but also inter-phrase grammatical constraints during speech recognition. The system is applied to Japanese sentence recognition, and attains a word accuracy of 95.9% and a sentence accuracy of 84.7%.