Phonological Parsing for Bi-directional Letter-to-Sound/Sound-to-Letter Generation

Phonological Parsing for Bi-directional Letter-to-Sound/Sound-to-Letter Generation 1 Helen M. Meng, Stephanie Seneff and Victor W. Zue Spoken Language Systems Group, Laboratory for Computer Science Massachusetts Institute of Technology, Cambridge, Massachusetts 02139 ABSTRACT In this paper, we describe a reversible letter-to-sound/sound- to-letter generation system based on an approach which com- bines a rule-based formalism with data-driven techniques. We adopt a probabilistic parsing strategy to provide a hierarchical lexical analysis of a word, including information such as mor- phology, stress, syllabification, phonemics and graphemics. Long-distance constraints are propagated by enforcing local constraints throughout the hierarchy. Our training and test- ing corpora are derived from the high-frequency portion of the Brown Corpus (10,000 words), augmented with markers indicating stress and word morphology. We evaluated our performance based on an unseen test set. The percentage of nonparsable words for letter-to-sound and sound-to-letter generation were 6% and 5% respectively. Of the remaining words our system achieved a word accuracy of 71.8~0 and a phoneme accuracy of 92.5% for letter-to-sound generation, and a word accuracy of 55.8% and letter accuracy of 89.4% for sound-to-letter generation. We also compared our hierar- chical approach with an alternative, single-layer approach to demonstrate how the hierarchy provides a parsimonious de- scription for English orthographic-phonological regularities, while simultaneously attaining competitive generation accu- racy. INTRODUCTION This paper describes a trainable probabilistic system for reversible letter-to-sound/sound-to-letter generation. Sound-to-letter generation is a crucial aspect in the prob- lem of automatic detection/incorporation of new words, which is in turn critical for the development of large vo- cabulary speech understanding systems. Moreover, letter- to-sound generation will continue to be important for speech output, especially in applications such as read- ing machines. To successfully achieve our goal, several important issues must be addressed. First, what should be the inventory of linguistic or lexical units for describ- ing English orthographic-phonological regularities? Sec- ond, how should these units be incorporated into the representation of English orthography and phonology? Third, what algorithms can be used to synthesize and an- alyze the spelling and pronunciation of an English word 1This research was supported by ARPA under Contract N00014- 89-J-1332, monitored through the Office of Naval Research, and a grant from Apple Computer Inc. in terms of these lexical units? These three issues will be addressed in detail in the following when we describe our approach and report on our system's performance for both letter-to-sound [1] and sound-to-letter genera- tion [2]. The novel features of our approach include the reversibility of the combined parsing and generative pro- cesses, the ability to provide multiple output hypotheses, the capability of handling uncertainty in the input, as well as our treatment of non-parsab!e words. PREVIOUS WORK Letter-to-Sound Generation One of the first approaches adopted for letter-to-sound generation is typified by MITalk [8]. It follows the theo- ries of generative grammar and the transformational cy- cle as proposed by Chomsky and Halle [3]. A large set of ordered cyclical rules are applied in turn to the word in question until a final pronunciation emerges. While the …

Content truncated to 500 words