Pronunciation by analogy (PbA) is a data-driven method for relating letters to sound, with potential application to next-generation text-to-speech systems. This paper extends previous work on PbA in several directions. First, we have included `full' pattern matching between input letter string and dictionary entries, as well as including lexical stress in letter-to-phoneme conversion. Second, we have extended the method to phonemeto -letter conversion. Third, and most important, we have experimented with multiple, different strategies for scoring the candidate pronunciations. Individual scores for each strategy are obtained on the basis of rank and either multiplied or summed to produce a final, overall score. Five strategies have been studied and results obtained from all 31 possible combinations. The two combination methods perform comparably, with the product rule only very marginally superior to the sum rule. Nonparametric statistical analysis reveals that performance improves as more strategies are included in the combination: this trend is very highly significant ( p 0 0005). Accordingly for letter-to-phoneme conversion, best results are obtained when all five strategies are combined: word accuracy is raised to 65.5% relative to 61.7% for our best previous result and 63.0% for the best-performing single strategy. These improvements are very highly significant ( p 0 and p 0 00011 respectively). Similar results were found for phoneme-to-letter and letter-to-stress conversion, although the former was an easier problem for PbA than letter-to-phoneme conversion and the latter was harder. The main sources of error for the multi-strategy approach are very similar to those for the best single strategy, and mostly involve vowel letters and phonemes. 1

The automatic derivation of word pronunciations from input text is a central task for any text-to-speech system. For general English text at least, this is often thought to be a solved problem, with manually-derived linguistic rules assumed capable of handling `novel' words missing from the system dictionary. Data-driven methods, based on machine learning of the regularities implicit in a large pronouncing dictionary, have received considerable attention recently but are generally thought to perform less well. However, these tentative beliefs are at best uncertain without powerful methods for comparing text-to-phoneme subsystems. This paper contributes to the development of such methods by comparing the performance of four representative approaches to automatic phonemisation on the same test dictionary. As well as rule-based approaches, three data-driven techniques are evaluated: pronunciation by analogy (PbA), NETspeak and IB1-IG (a modified k-nearest neighbour method). Issues involved in comparative evaluation are detailed and elucidated. The data-driven techniques outperform rules in accuracy of letter-to-phoneme translation by a very significant margin but require aligned text-phoneme training data and are slower. Best translation results are obtained with PbA at approximately 72% words correct on a reasonably large pronouncing dictionary, compared to something like 26% words correct for the rules, indicating that automatic pronunciation of text is not a solved problem.

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, hypothesising 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 `underspecified', i.e. 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 stud...

A common requirement in speech technology is to align two different symbolic representations of the same linguistic `message'. For instance, we often need to align letters of words listed in a dictionary with the corresponding phonemes specifying their pronunciation. As dictionaries become ever bigger, manual alig nment becomes less and less tenable yet automatic alignment is a hard problem for a language like English. In this paper, we describe use of a form of the expectation-maximization (EM) algorithm to achieve automatic alignment of English text and phonemes. The quality of alignment is assessed by the performance of a pronunciation by analogy system using the aligned dictionary data. We find excellent performance---the best so far reported in the literature of letter-phoneme conversion---independent of the start point for alignment, indicating that the EM search space is strongly convex.

Pronunciation by analogy (PbA) is a data-driven technique for the automatic phonemisation of text which is receiving renewed attention from workers in text-to-speech synthesis. It uses the dictionary which provides the primary source of pronunciations via direct look-up as a secondary source of information about the pronunciation of unknown words. In this paper, we provide theoretical and empirical motivations for the use of PbA, review approaches to automatic pronunciation generation by analogy, and report on the implementation of a PbA module for the Festival text-to-speech synthesiser. We have used a much larger dictionary (British English Example Pronunciation or BEEP, approximately 200,000 words) than hitherto. New results of 86.7 % words correct are obtained for this dictionary on our best-performing PbA implementation. The Festival PbA module is still under development, however, and currently does less well. 1.

We propose a memory-based (similarity-based) approach to learning the mapping of words into phonetic representations for use in speech synthesis systems. The main advantage of memory-based data mining techniques is their high accuracy, the main disadvantage is processing speed. We introduce a hybrid between memory-based and decision-tree-based learning (TRIBL) which optimises the trade-off between efficiency and accuracy. TRIBL was used in TREETALK, a methodology for fast engineering of word-to-phonetics conversion systems. We also show that for English,a single TRIBL classifier trained on predicting phonetic transcription and word stress at the same time performs better than a `modular' approach in which different classifiers corresponding to linguistically relevant representations such as morphological and syllable structure are separately trained and integrated.

This paper extends previous work on pronunciation by analogy (PbA) in several directions. PbA is a data-driven method for converting letters to sound, with potential application to next-generation text-to-speech systems. We experiment with a range of methods for matching letter patterns in input words to those in the system dictionary when building a pronunciation lattice. We give preliminary consideration to deriving lexical stress for input words. Common errors are analysed: these mostly involve vowel letters and phonemes. An output is not necessarily guaranteed in PbA -- the so-called silence problem. We report on a simple but effective strategy for silence avoidance. Finally, we introduce the idea of using different strategies in combination to improve performance. 1. INTRODUCTION Modern text-to-speech (TTS) systems use look-up in a large dictionary as the primary strategy to determine the pronunciation of input words. However, it is not possible to list exhaustively all the word...

This paper describes a modification to, and a fast implementation of, the Viterbi algorithm for use in stochastic letter-to-phoneme conversion. A straightforward (but unrealistic) implementation of the Viterbi algorithm has a linear time complexity with respect to the length of the letter string, but quadratic complexity if we additionally consider the number of letter-tophoneme correspondences to be a variable determining the problem size. Since the number of correspondences can be large, processing time is long. If the correspondences are precompiled to a deterministic finite-state automaton to simplify the process of matching to determine state survivors, execution time is reduced by a large multiplicative factor. Speedup is inferred indirectly since the straightforward implementation of Viterbi decoding is too slow for practical comparison, and ranges between about 200 and 4000 depending upon the number of letters processed and the particular correspondences employed in the transdu...