mahta.fetrat
/
HomoFast-eSpeak-Persian
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
252 Commits
1 Branch
Tree: eb7b132e9a
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'eb7b132e9a'
${ noResults }
HomoFast-eSpeak-Persian/docs/add_language.html

add_language.html 8.2KB
Raw Blame History

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128 
  1. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">

  2. <HTML>

  3. <HEAD>

  4. 	<META HTTP-EQUIV="CONTENT-TYPE" CONTENT="text/html; charset=utf-8">

  5. 	<TITLE>eSpeak: Adding a Language</TITLE>

  6. </HEAD>

  7. <BODY LANG="en-GB" DIR="LTR">

  8. <A href="docindex.html">Back</A>

  9. <HR>

  10. <H2>6. ADDING OR IMPROVING A LANGUAGE</H2>

  11. <HR>

  12. Most of the work doesn't need any programming knowledge.  Just an understanding of the language, an

  13. awareness of its features, patience and attention to detail.  Wikipedia is a good source of basic phonetic information, eg

  14. <a href="http://en.wikipedia.org/wiki/Vowel">http://en.wikipedia.org/wiki/Vowel</a>

  15. <P>

  16. In many cases it should be fairly easy to add a rough implementation of a new language, hopefully

  17. enough to be intelligible.<p>

  18. After that it's a gradual process of improvement to:

  19. <ul>

  20. <li>Make the spelling-to-phoneme translation rules more accurate, including the position of stressed

  21. syllables within words. Some languages are easier than others. I expect most are easier than English.

  22. <p><li>Improve the sounds of the phonemes.  It may be that a phoneme should sound different depending on adjacent sounds, or whether it's at the start or the end of a word, between vowels, etc.  This may consist of making small adjustments to vowel and diphthong quality,

  23. or adjusting the strength of consonants.  Bigger changes may be recording new or replacement consonant

  24. sounds, or even writing program code to implement new types of sounds.

  25. <p><li>Some common words should be added to the dictionary (the *_list file for the language) with an "unstressed" attribute (eg. in English, words such as "the", "is", "had", "my", "she", "of", "in", "some"), or should be preceded

  26. by a short pause (such as "and", "but", "which"), or have other attributes, in order to make the speech flow better.

  27. <p><li>Improve the rhythm of the speech by adjusting the relative lengths of vowels in different contexts, eg. stressed/unstressed syllable,

  28. or depending on the following phonemes.  This is important for making the speech sound good for the language.

  29. <p><li>Identify or implement new functions in the program to improve the speech, or to deal with

  30. characteristics of the language which are not currently implemented.  For example, a different intonation module.

  31. </ul>

  32. <b><em>If you are interested in working on a language, please contact me so that I can set up the initial data and discuss the features of the language.</em></b>

  33. <p>

  34. For most of the eSpeak voices, I do not speak or understand the language, and I do not know how it should sound.  I can only make improvements as a result of feedback from speakers of that language.  If you want to help to improve a language, listen carefully and try to identify individual errors, either in the spelling-to-phoneme translation, the position of stressed syllables within words, or the sound of phonemes, or problems with rhythm and vowel lengths.

  35. <HR>

  36. <H3>6.1 Language Code</H3>

  37. <P>Generally, the language's international <a href="http://en.wikipedia.org/wiki/ISO_639-1">ISO 639-1 code</a> is used to

  38. identify the language. It is used in the filenames which

  39. contains the language's data. In the examples below the code &quot;<B>en</B>&quot;

  40. (English) is used as an example. Replace this with the code of your

  41. language.<p>

  42. It is possible to have different variants of a language, for example where the sound of some phonemes changed,

  43. or where some of the pronunciation rules differ.

  44. <HR>

  45. <H3>6.2 Phoneme File</H3>

  46. <P>You must first decide on the set of phonemes to be used for the

  47. language. These should be listed and defined in a phonemes file such as

  48. <B>ph_english</B>. A reference to this file is then included at the end of

  49. the <B>phonemes,</B> file (the master phoneme file), eg:</P>

  50. <PRE>   phonemetable  en  base

  51.    include  ph_english</PRE><P>

  52. This example defines a phoneme table &quot;<B>en</B>&quot; which inherits

  53. the contents of phoneme table &quot;<B>base</B>&quot;. Its contents are

  54. found in the file <B>ph_english</B>.</P>

  55. <P>The <B>base</B> phoneme table contains definitions of a basic set of

  56. consonants, and also some &quot;control&quot; phonemes such as stress marks and

  57. pauses. The phoneme table for a language will generally inherit this,

  58. or alternatively it may inherit the phoneme table of another language

  59. which in turn inherits the <B>base</B> phoneme table.</P>

  60. <P>The phonemes file for the language defines those additional

  61. phonemes which are not inherited (generally the vowels and diphthongs, plus any additional

  62. consonants), or phonemes whose definitions differ from the

  63. inherited version (eg. the redefinition of a consonant).</P>

  64. <P>Details of the contents of phonemes files are given in

  65. <A href="phontab.html">phontab.html</A>.</P>

  66. The <B>Compile phoneme data</B> function of the <B>espeakedit</B>

  67. program compiles the phonemes files to produce the files

  68. <B>espeak-data/phontab</B>, <B>phonindex</B>, and <B>phondata.</B><P>

  69. For information on how to analyse recorded sounds of the language and to

  70. prepare the corresponding phoneme data, see <a href="editor_if.html">espeakedit</a> and <a href="analyse.html">analysis</a>).<p>

  71. For an initial draft a language will often be able to use vowels and

  72. consonants which have already been set up for another language.

  73. <HR>

  74. <H3>6.3 Dictionary Files</H3>

  75. <P STYLE="font-weight: medium">Once the language's phonemes have been

  76. defined, then pronunciation dictionary data can be produced in order

  77. to translate the language's source text into phonemes. This consists

  78. of two source files: <B>en_rules</B> (the spelling to phoneme rules) and

  79. <B>en_list</B> (an exceptions list, and attributes of certain words). The corresponding compiled data

  80. file is <B>espeak-data/en_dict</B> which is produced from <B>en_rules</B>

  81. and <B>en_list</B> sources by the command: <B>speak&nbsp; --compile=en</B>.</P>

  82. <P STYLE="font-weight: medium">Details of the contents of the

  83. dictionary files are given in <A href="dictionary.html">dictionary.html</A>.</P>

  84. <P STYLE="font-weight: medium">The <B>en_list</B> file contains not

  85. only pronunciation exceptions, but also gives attributes to specific

  86. words, Most notable of these are:</P>

  87. <P STYLE="font-weight: medium"><B>$u </B>Some common words should be

  88. marked as &quot;unstressed&quot; in order to make the speech flow better.

  89. These words generally include articles (eg: a, the, this, that),

  90. auxillary verbs (eg: is, have, will, can, may), pronouns and

  91. possessive adjectives (eg: he, his), some common prepositions (eg:

  92. of, to, in, of), some common conjunctions (eg. and, or, if), some

  93. common adverbs and adjectives (eg. any, already)</P>

  94. <P><B>$pause </B>Some words should be marked to have a short pause

  95. before then, in order to produce natural pauses in long sentences.

  96. These include conjunctions (eg. and, or, but, however, which) and perhaps

  97. some prepositions.</P>

  98. <HR>

  99. <H3>6.4 Voice File</H3>

  100. <P STYLE="font-weight: medium">Each language should have one or more

  101. voice files in <B>espeak-data/voices</B>. The filename of the default voice

  102. for a language should be the same as the language code.</P>

  103. <P STYLE="font-weight: medium">Details of the contants of voice files

  104. are given in <A href="voices.html">voices.html</A>.</P>

  105. <P STYLE="font-weight: medium">The simplest voice file would contain

  106. just a single line to give the language code, eg:</P>

  107. <PRE STYLE="margin-bottom: 0.5cm">   language en</PRE><P STYLE="font-weight: medium">

  108. This language code specifies the phoneme table (i.e. <b>phonemetable  en</b> and the

  109. dictionary (i.e. <B>espeak-data/en_dict</B>) to be used. If needed, these can be

  110. overridden by <B>phonemes</B> and <B>dictionary</B> attributes in the

  111. voices file.</P>

  112. <HR>

  113. <H3>6.5 Program Code</H3>

  114. <P STYLE="font-weight: medium">The behaviour of the speak program is

  115. controlled by various options (eg. whether words are stressed on the first,

  116. last, or penultimate syllable). The function <B>SetTranslator()</B> at the

  117. start of the <B>tr_languages.cpp</B> file recognizes the language

  118. code and sets the appropriate set of options.</P>

  119. <P STYLE="font-weight: medium">For a new language, you would add its

  120. language code and the required options in <B>SetTranslator()</B>. However, this

  121. may not be necessary during testing because most of the options can also be

  122. set from the voice file in

  123. <B>espeak-data/voices</B>.</P>

  124. 

  125. 

  126. 

  127. </BODY>

  128. </HTML>