Some remarks on Klatt’s ‘‘Review of text‐to‐speech conversion for English’’ [J. Acoust. Soc. Am. 82, 737–793 (1987)]

Dennis Klatt’s article ‘‘Review of text‐to‐speech conversion for English’’ [J. Acoust. Soc. Am. 82, 737–793 (1987)] provides an excellent review of many developments in the area of English text‐to‐speech conversion, an area in which Klatt has been an undisputed leader. However, as Klatt himself points out (p. 738), he is ‘‘an active participant in the field who has many biases that ... no doubt color the review.’’ Understandably then, Klatt emphasizes his own contributions in certain areas, focusing, for example, more heavily on phoneme‐to‐speech conversion than text‐to‐phoneme conversion, and on his own rules rather than those of others. This letter expands on the article by considering selected results of the work by myself and my associates in text‐to‐speech synthesis over the last 14 years. These results are presented primarily to broaden the reader’s perspective, but also to clarify some misrepresentations in Klatt’s article.