Pronunciation by analogy (PbA) is an emerging, data-driven technique with potential application in text-to-speech (TTS) systems, as well as being an influential psychological model of reading aloud. The underlying idea is that a pronunciation for an unknown word (i.e., one not in the dictionary, or lexicon, of the human or machine “reader”) is assembled by matching substrings of the input to substrings of known, lexical words, hypothesizing a partial pronunciation for each matched substring from the lexical knowledge of the “reader,” and concatenating the partial pronunciations. This paper assesses the capability of PbA to derive pronunciations for unknown words of English.
As a psychological model, PbA is “under-specified,” that is, the implementor of a simulation of the process faces detailed choices which can only be resolved by trial and error. One goal for this paper is to explore the impact of certain basic implementational choices on the performance of PbA systems. The variables studied are the specific lexical database used as the basis of the analogy process, the way of ranking/scoring candidate pronunciations, and the effect of manual versus automatic alignment of letters and phonemes.
When tested with short (monosyllabic) pseudowords previously used in experimental psychology studies, the lowest error rate achieved is 14.3% (for a test set of size 70). We conclude that current PbA systems are at best poor models of pseudoword pronunciation by humans.
To assess their suitability for use in a TTS application, in which multisyllabic words will be encountered, the implementations have also been tested with lexical words temporarily removed from the dictionary. The best performance obtained was 93.5% phonemes correct (corresponding to 67.9% words correct) for a 16,280-word dictionary. This is vastly superior to the 25.7% words correct obtained using a set of popular letter-to-sound rules, indicating considerable scope for analogy methods to be exploited in future TTS systems.
AINSWORTH, W. A. (1973). A system for converting English text into speech. IEEE Transactions on Audio and Electroacoustics, AU-21, 288–290.
2.
ANDREWS, S. (1989). Frequency and neighborhood effects on lexical access: Activation or search? Journal of Experimental Psychology: Learning, Memory and Cognition, 15, 802–814.
3.
BARON, J. (1977). Mechanisms for pronouncing printed words: Use and acquisition. In D. LaBerge & S. Samuels (Eds.), Basic processes in reading: Perception and comprehension (pp. 175–216). Hillsdale, NJ: Lawrence Erlbaum.
4.
BOSCH, A. van den, & DAELEMANS, W. (1993). Data-oriented methods for grapheme-to-phoneme conversion. Proceedings of 6th Conference of the European Chapter of the Association for Computational Linguistics, Utrecht, Netherlands, pp. 45–53.
5.
BROOKS, L. (1977). Non-analytic correspondences and pattern in word pronunciation. In J. Renquin (Ed.), Attention and performance VII (pp. 163–177). Hillsdale, NJ: Lawrence Erlbaum.
6.
BROWN, P., & BESNER, D. (1987). The assembly of phonology in oral reading: A new model. In M. Coltheart (Ed.), Attention and performance XII: The psychology of reading (pp. 471–489). London: Lawrence Erlbaum.
7.
BYRD, R.J., & CHODOROW, M. S. (1985). Using an on-line dictionary to find rhyming words and pronunciations for unknown words. Proceedings of the 23rd Meeting of Association for Computational Linguistics, Chicago, IL, pp. 277–283.
8.
COKER, C.H., CHURCH, K. W., & LIBERMAN, M. Y. (1990). Morphology and rhyming: Two powerful alternatives to letter-to-sound rules for speech synthesis. Proceedings of European Speech Association (ESCA) Workshop on Speech Synthesis, Autrans, France, pp. 83–86.
9.
COLTHEART, M. (1978). Lexical access in simple reading tasks. In G. Underwood (Ed.), Strategies of information processing (pp. 151–216). London: Academic.
10.
COLTHEART, M. (1984). Writing systems and reading disorders. In L. Henderson (Ed.), Orthographies and reading: Perspectives from cognitive psychology, neuropsychology and linguistics (pp. 67–79). London: Lawrence Erlbaum.
11.
COLTHEART, M., CURTIS, B, ATKINS, P., & HALLER, M. (1993). Models of reading aloud: Dual-route and parallel-distributed-processing approaches. Psychological Review, 100, 589–608.
12.
DAMPER, R. I. (1995). Self-learning and connectionist approaches to text-phoneme conversion. In J. Levy, D. Bairaktaris, J. Bullinaria, & P. Cairns (Eds.), Connectionist models of memory and language (pp. 117–144). London: UCL Press.
13.
DAMPER, R.I., & EASTMOND, J.F.G. (1996). Pronouncing text by analogy. Proceedings of 16th International Conference on Computational Linguistics (COLING-96), Vol.2, Copenhagen, Denmark, pp. 268–273.
14.
DEDINA, M.J., & NUSBAUM, H. C. (1986). PRONOUNCE: A program for pronunciation by analogy. Speech Research Laboratory Progress Report No. 12, Indiana University, Bloomington, IN.
15.
DEDINA, M.J., & NUSBAUM, H. C. (1991). PRONOUNCE: A program for pronunciation by analogy. Computer Speech and Language, 5, 55–64.
16.
ELOVITZ, H.S., JOHNSON, R., MCHUGH, A., & SHORE, J. A. (1976). Letter-to-sound rules for automatic translation of English text to phonetics. IEEE Transactions on Acoustics, Speech and Signal Processing, ASSP-24, 446–459.
17.
FEDERICI, S., PIRRELLI, V., & YVON, F. (1995). Advances in analogy-based learning: False friends and exceptional items in pronunciation by paradigm-driven analogy. Proceedings of International Joint Conference on Artificial Intelligence (IJCAI '95); Workshop on New Approaches to Learning for Natural Language Processing, Montreal, Canada, pp. 158–163.
18.
GLUSHKO, R. J. (1979). The organization and activation of orthographic knowledge in reading aloud. Journal of Experimental Psychology: Human Perception and Performance, 5, 674–691.
19.
GLUSHKO, R. J. (1981). Principles for pronouncing print: The psychology of phonography. In A.M. Lesgold & C.A. Perfetti (Eds.), Interactive processes in reading (pp. 61–84). Hillsdale, NJ: Lawrence Erlbaum.
20.
GOLDING, A. R. (1991). Pronouncing names by a combination of case-based and rule-based reasoning. Unpublished doctoral dissertation, Stanford University, California.
21.
GOLDING, A.R., & ROSENBLOOM, P. S. (1991). Improving rule-based systems through case-based reasoning. Proceedings of American Association for Artificial Intelligence Conference, AAAI-91, Anaheim, CA, pp.21–27.
22.
HUMPHREYS, G.W., & EVETT, L. J. (1985). Are there independent lexical and nonlexical routes in word processing? An evaluation of the dual-route theory of reading. Behavioral and Brain Sciences, 8, 689–740.
23.
HUNNICUTT, S. (1976). Phonological rules for a text-to-speech system. American Journal of Computational Linguistics, Microfiche, 57, 1–72.
24.
HUNNICUTT, S. (1980). Grapheme-to-phoneme rules: A review. Speech Transmission Laboratory Quarterly Progress and Status Report, Royal Institute of Technology (KTH), Stockholm, STL- QPSR 2–3/1980, 38–60.
25.
HUNNICUTT, S., MENG, H., SENEFF, S., & ZUE, V. (1993). Reversible letter-to-sound sound-to-letter generation based on parsing word morphology. Proceedings of 3rd European Conference on Speech Communication and Technology (Eurospeech '93), Vol.2, Berlin, Germany, pp. 763–766.
26.
KAY, J., & MARCEL, A. J. (1981). One process, not two, in reading aloud: Lexical analogies do the work of nonlexical rules. Quarterly Journal of Experimental Psychology, 33A, 397–414.
27.
KLATT, D. H. (1987). Review of text-to-speech conversion for English. Journal of the Acoustical Society of America, 82, 737–793.
28.
LAWRENCE, S.G. C., & KAYE, G. (1986). Alignment of phonemes with their corresponding orthography. Computer Speech and Language, 1, 153–165.
29.
LEHNERT, W. G. (1987) Case-based problem solving with a large knowledge base of learned cases. Proceedings of 6th National Conference of American Association for Artificial Intelligence (AAAI- 87), Seattle, WA, pp. 301–306.
30.
LEVENSHTEIN, V I. (1966). Binary codes capable of correcting deletions, insertions, and reversals. Cybernetics and Control Theory, 10, 707–710.
31.
LUCASSEN, J.M., & MERCER, R. L. (1984). An information theoretic approach to the automatic determination of phonemic baseforms. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP84), San Diego, CA, pp.42.5.1–42.5.4.
32.
McCULLOCH, N., BEDWORTH, M., & BRIDLE, J. S. (1987). NETspeak---a re-implementation of NETtalk. Computer Speech and Language, 2, 289–301.
33.
MOHRI, M. (forthcoming). Finite-state transducers in language and speech processing. To appear in Computational Linguistics.
34.
OGDEN, C. K. (1937). Basic English.London: Kegan Paul.
35.
PATTERSON, K.E., & MORTON, J. (1985). From orthography to phonology: A new attempt at an old interpretation. In K. Patterson, J. Marshall, & M. Coltheart (Eds.), Surface dyslexia: Neuropsychological and cognitive studies of phonological reading (pp. 355–359). London: Lawrence Erlbaum.
36.
POLLATSEK, A., & RAYNER, K. (1993). Reading. In M.I. Posner (Ed.), Foundations of cognitive science (2nd ed.) (pp. 401–436). Cambridge, MA: Bradford/MIT.
37.
POLS, L.C.W. (1989). Assessment of text-to-speech synthesis systems. In A. J. Fourcin, G. Harland, W. Barry, & V Hazan (Eds.), Speech input and output assessment: Multilingual methods and standards (pp. 53–81). Chichester, U.K.: Ellis Horwood.
38.
SEIDENBERG, M.S., & McCLELLAND, J. L. (1989). A distributed, developmental model of word recognition and naming. Psychological Review97, 447–452.
39.
SEJNOWSKI. T. J., & ROSENBERG, C. R. (1987). Parallel networks that learn to pronounce English text. Complex Systems, 1, 145–152.
40.
STANFILL, C. W. (1987). Memory-based reasoning applied to English pronunciation. Proceedings of 6th National Conference of the American Association for Artificial Intelligence (AAAI87), Seattle, WA, pp. 577–581.
41.
STANFILL, C. W. (1988). Learning to read: A memory-based model. Proceedings of Case-Based Reasoning Workshop, Clearwater Beach, FL, pp.406–413.
42.
SULLIVAN, K. P. H. (1988). The Latex IPA fonts and their usage. Vision, Speech and Signal Processing Research Group Technical Note 88/TN1, Department of Electronics and Computer Science, University of Southampton, U.K.
43.
SULLIVAN, K. P. H. (1992). Synthesis-by-analogy: A psychologically-motivated approach to text-to-speech conversion. Unpublished doctoral dissertation, University of Southampton, U.K.
44.
SULLIVAN, K. P. H., & DAMPER, R. I. (1989). The relevance of psychological models of oral reading to computer text-to-speech conversion. Vision, Speech, and Signal Processing Research Group Technical Report VSSP 89/TR1, Department of Electronics and Computer Science, University of Southampton, U.K.
45.
SULLIVAN, K. P. H., & DAMPER, R. I. (1990). A psychologically-governed approach to novel-word pronunciation within a text-to-speech system. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '90), Vol. 1, Albuquerque, NM, pp. 341–344.
46.
SULLIVAN, K.P. H., & DAMPER, R. I. (1991). Speech synthesis by analogy: Recent advances and results. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP '91), Vol.II, Toronto, Canada, pp. 761–764.
47.
SULLIVAN, K.P. H., & DAMPER, R. I. (1992a). Synthesis-by-analogy: A bi-lingual investigation using German and English. Proceedings of International Conference on Spoken Language Processing (ICSLP '92), Vol.1, Banff, Canada, pp. 113–116.
48.
SULLIVAN, K.P. H., & DAMPER, R. I. (1992b). Novel-word pronunciation within a text-to-speech system. In G. Bailly & C. Benoît (Eds.), Talking machines: Theories, models and applications (pp. 183–195). Amsterdam: Elsevier (North-Holland).
49.
SULLIVAN, K.P. H., & DAMPER, R. I. (1993). Novel-word pronunciation: A cross-language study. Speech Communication, 13, 441–452.
50.
THORNDIKE, E.L., & LORGE, I. (1944). The teachers' word book of 30,000 words.NY: Teachers College, Columbia University.
51.
YVON, F. (1996). Grapheme-to-phoneme conversion using multiple unbounded overlapping chunks. Proceedings of Conference on New Methods in Natural Language Processing (NeMLaP '96), Ankara, Turkey, pp.218–228.
