pronunciation dictionary
Recently Published Documents


TOTAL DOCUMENTS

47
(FIVE YEARS 10)

H-INDEX

4
(FIVE YEARS 0)

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Zhang Shufang

In this paper, a system for automatic detection and correction of mispronunciation of native Chinese learners of English by speech recognition technology is designed with the help of radiomagnetic pronunciation recording devices and computer-aided software. This paper extends the standard pronunciation dictionary by predicting the phoneme confusion rules in the language learner’s pronunciation that may lead to mispronunciation and generates an extended pronunciation dictionary containing the standard pronunciation of each word and the possible mispronunciation variations, and automatic speech recognition uses the extended pronunciation dictionary to detect and diagnose the learner’s mispronunciation of phonemes and provides real-time feedback. It is generated by systematic crosslinguistic phonological comparative analysis of the differences in phoneme pronunciation with each other, and a data-driven approach is used to do automatic phoneme recognition of learner speech and analyze the mapping relationship between the resulting mispronunciation and the corresponding standard pronunciation to automatically generate additional phoneme confusion rules. In this paper, we investigate various aspects of several issues related to the automatic correction of English pronunciation errors based on radiomagnetic pronunciation recording devices; design the general block diagram of the system, etc.; and discuss some key techniques and issues, including endpoint detection, feature extraction, and the system’s study of pronunciation standard algorithms, analyzing their respective characteristics. Finally, we design and implement a model of an automatic English pronunciation error correction system based on a radiomagnetic pronunciation recording device. Based on the characteristics of English pronunciation, the correction algorithm implemented in this system uses the similarity and pronunciation duration ratings based on the log posterior probability, which combines the scores of both, and standardizes this system scoring through linear mapping. This system can achieve the purpose of automatic recognition of English mispronunciation correction and, at the same time, improve the user’s spoken English pronunciation to a certain extent.


Verbum ◽  
2020 ◽  
Vol 11 ◽  
pp. 6
Author(s):  
Lina Bikelienė ◽  
Laura Černelytė

The pilot study reports on the prevalence of four phonetic changes (yod coalescence, yod dropping, /ʒ/ versus /ʤ/ in loan words, and GOAT allophony) in General British. The study consists of two stages to address the question from different perspectives: native speakers’ preferences and documentation of the changes in current pronouncing dictionaries.Sixty words likely to undergo one of the changes are chosen for the analysis. The survey is based on the framework by Wells (1998). Though the descriptive study resultsreveal a high degree of the respondents’ preference for ‘modern’ pronunciation, it varies across categories. The comparative analysis of the manifestation of the changes in the Longman Pronunciation Dictionary (2008), the Cambridge English Pronouncing Dictionary (2011), and the Current British English Searchable Transcriptions (N/A) indicate their gradual way into the ‘standard’ language.


Author(s):  
Laine Strankale ◽  
Pēteris Paikens

This paper covers the devlopment of a custom OCR solution based on the Tesseract open source engine developed for digitization of a Latvian pronunciation dictionary where the pronunciation data is described using a large variety of diacritic markings not supported by standard OCR solutions. We describe our efforts in training a model for these symbols without the additional support of preexisting dictionaries and illustrate how word error rate (WER) and character error rate (CER) are affected by changes in the dataset content and size. We also provide an error analysis and postulate possible causes for common pitfalls. The resulting model achieved a CER of 2.07%, making it suitable for digitization of the whole dictionary in combination with heuristic post-processing and proofreading, resulting in a useful resource for further development of speech technology for Latvian.


2020 ◽  
Vol 24 (3) ◽  
pp. 527-543
Author(s):  
NICOLAS TRAPATEAU

A long /aː/ in pre-fricative and pre-nasal contexts in words such as fast, answer or after is one of the most distinctive phonological features of British RP and, to a certain extent, of Southern Hemisphere varieties of English (Trudgill 2010). The lengthening of /a/ has been particularly gaining ground from the eighteenth century onwards (Beal 1999; Jones 2006). The pronouncing dictionaries published between the eighteenth century and the present day allow us to trace its lexical diffusion (Labov 1994) across the whole lexicon. Drawing on the statistics of the ARCHER corpus, the lexical sets of the ECEP database, the full electronic edition of Walker's dictionary (1791), Wells’ Longman Pronunciation Dictionary (2008) and the Macquarie Dictionary (2015), this article examines the role played by the phonetic environment, word frequency, phonetic analogy and isolated lead words like draught or master in the spread of the lengthening of /a/. The results show that word frequency per se has no clear effect on /a/ lengthening in either pre-fricative or pre-nasal environments in eighteenth-century sources. The article also offers a possible relative chronology of the spread of that phenomenon to each phonetic environment within the bath set.


Author(s):  
Natalya Ivanova ◽  
Rimma Kuzmina

The article considers phonetic variants of English proper names that comprise homographic groups, and some impairments during their registration in pronouncing dictionaries. The authors present the results of lexicographic and comparative analysis of units extracted from two pronouncing dictionaries: "Cambridge English Pronouncing Dictionary" by D. Jones and "Longman Pronunciation Dictionary" by J. Wells using the continuous sampling method. Particular attention is focused on the methods of registration and completeness of phonetic notation of homographs pronunciation. A number of peculiarities are noted in recording semantics, phonetic-and-orthographic variations in some homogroups in British and American English. Clear inconsistency and insufficiency of lexicographic parametrization of both homographic proper names and their national and social pronunciation variants, as well as the meanings of common and proper names are revealed. The conclusion is made about the accuracy of "Cambridge English Pronouncing Dictionary" in terms of registering several British and American variants of onyms pronunciation, supplemented by additional comments on the phonetic variants and meanings of numerous types of proper names (anthroponyms, toponyms, ergonyms). The data obtained are required for differentiating the meanings of proper names, correct use of onyms and appellatives in oral speech, as well as for compiling dictionaries and reference books.


2020 ◽  
Author(s):  
Christopher Chu ◽  
Scot Fang ◽  
Kevin Knight

Author(s):  
Наталья Кирилловна Иванова ◽  
◽  
Римма Владимировна Кузьмина ◽  

Исследование омонимии, проводимое более десяти лет на материале словарей English Pronouncing Dictionary (EPD, 1–18 изд., 1917–2012) и Longman Pronunciation Dictionary (LPD, 1–3 изд., 1990–2008), позволило установить частотность фонетических (и графических) вариантов в различных группах омонимов (омографах, омофонах, фонетико-графических омонимах, омонимичных именах собственных, омонимичных аббревиатурах), определить общее и специфическое в подходах Д. Джоунза и Дж. Уэллса к проблемам регистрации вариантности и вариативности произношения, и в частности, феномена омонимии. Кроме омонимов, рассматривались тесно связанные с ними полисемантичные и паронимичные группы как среди хорошо известных лексических единиц, так и среди неологизмов. Было установлено несовершенство лексикографической параметризации рассматриваемых явлений. Последние исследования выявили явную непоследовательность и недостаточность в регистрации как омографичных имен собственных (ИС), так и их национальных и социальных вариантов произношения, а также непоследовательность в представлении значений ИС и имен нарицательных. С использованием ресурсов Oxford English Dictionary предлагается проектный, более полный (комбинированный) словарь омографичных онимов и апеллятивов. Описывается начальный этап составления цифрового словаря и обсуждается структура лемм.


Sign in / Sign up

Export Citation Format

Share Document