Application of the Liberman-Prince Stress Rules to Computer Synthesized Speech

APPLICATION OF THE LIBERMAN-PRINCE STRESS RULES TO COMPUTER SYNTHESIZED SPEECH David L. McPeters* and Alan L. Tharp Computer Science Department North Carolina State University Raleigh, North Carolina 27650 USA ABSTRACT Computer synthesized speech is and will con- tinue to be an important feature of many artifi- cially intelligent systems. Although current computer synthesized speech is intelligible, it cannot yet pass a Turing test. One avenue for improving the intelligibility of computer synthe- sized speech and for making it more human-like is to incorporate stress patterns on words. But to achieve this improvement, a set of stress predic- tion rules amenable to computer implementation is needed. This paper evaluates one such theory for pre- dlcting stress, that of Liberman and Prince. It first gives an overview of the theory and then discusses modifications which were necessary for computer implementation. It then describes an experiment which was performed to determine the model's strengths and shortcomings. The paper con- cludes with the results of that study. I INTRODUCTION Since speech is such an important component of human activities, it is essential that it be included in computer systems simulating human behavior or performing human tasks. Advantages of interacting with a computer system capable of speech include tha= a) special equipment (e.g. a terminal) is unnecessary for receiving output from the device. b) the output may be communicated to several people simultaneously. c) it m~y be used to gain someone's atten- tion. d) it is useful in communicating information in an emergency. *Current address: Bell Laboratories, Indianapolis, Indiana 46219. 192 The primary methods for generating computer synthesized speech are i) to use a lexicon of word pronunciations and then assemble a message from these stored words or 2) to use a letter-to-sound translator. A shortcoming common to both methods, and of interest to linguists and more recently computer scientists, is the inclusion of English prosody in computer synthesized speech e.g. Klatt [6], Lehlste [8], Wltten et al [ll] and Hill [5]. Of the three primary components of English prosody, this paper considers only stress (the other two are intonation and pause). It applies the theory for stress prediction proposed by lin- guists Mark Liberman and Alan Prince [9] to com- puter synthesized speech. Their theory was chosen primarily as a result of it having received wide- spread attention since its introduction (see Paradls [lO], Yip [12], FuJimura [3 and 4] and Basboll [2]). II THE LIBERMAN-PRINCE MODEL In addition to the attention it received, the Liberman-Prince model [9] (hereafter referred to as rhe LP model) is attractive for computer appli- cation for two other reasons. First, the majority of its rules can be applied without knowledge of the lexical category (part-of-speech) of the word being processed since the rules are based only on the sequences and attributes of letters in a word. This feature is especially important in an unre- stricted text-to-speech translation system. Secondly, since the metrical trees that define the prominence relations are a common data structure, a computer model may be …

Content truncated to 500 words