mjohnson/espeak-ng
1
0
Fork 0
mirror of https://github.com/rhasspy/espeak-ng.git synced 2026-11-03 06:12:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix and update the intonation.md documentation.

Browse Source
This commit is contained in:
Reece H. Dunn
2015-12-26 14:17:48 +00:00
parent 75719bf814
commit 2c70000d8a
3 changed files with 133 additions and 189 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Makefile.am
+1
View File
@@ -64,6 +64,7 @@ src/espeak-ng.1: src/espeak-ng.1.ronn
docs: docs/index.html \
docs/add_language.html \
docs/dictionary.html \
docs/intonation.html \
docs/mbrola.html \
docs/phontab.html \
docs/voices.html \
docs/intonation.html
-101
View File
@@ -1,101 +0,0 @@
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<title>eSpeak: Phoneme tables</title>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<A href="docindex.html">Back</A>
<hr>
<h2>INTONATION</h2>
<hr>
In eSpeak's standard intonation model, a "tune" is applied to each clause depending on its punctuation. Other intonation models may be used for some languages, such as tone languages.
<p>
Named tunes are defined in the text file: <b><code>phsource/intonation</code></b>. This file must be compiled for use by eSpeak by using the espeakedit program, using the menu option: <b><code>Compile -> Compile intonation data</code></b>.
<h3>Clauses</h3>
The tunes which are used for a language can be specified by using a <b><code>tunes</code></b> statement in a voice file in <b><code>espeak-data/voices</code></b>. eg:
<p>
<code>tunes &nbsp; s1 &nbsp;c1 &nbsp;q1 &nbsp;e1</code>
<p>
It's parameters are four tune names which are used for clauses which end in:
<ol>
<li>Full-stop.
<li>Comma.
<li>Question mark.
<li>Exclamation mark.
</ol>
<p>
A clause consists of the following parts:
<ul>
<li>Pre-head.<br>These are any unstressed syllables before the first stressed syllable.
<p>
<li>Head.<br>This is the part from the first stressed syllable up to the last syllable before the nucleus.
<p>
<li>Nucleus.<br>This is stressed syllable which is the focus of the clause. eSpeak chooses the last stressed syllable of the clause.
<p>
<li>Tail.<br>These are the syllables after the nucleus.
</ul>
<p>
<h3>Tune definitions</h3>
Here is an example tune definition from the file <b><code>phsource/intonation</code></b>.
<p>
<pre>
tune s1
prehead 46 57
headenv fall 16
head 4 80 55 -8 -5
headextend 0 63 38 13 0
nucleus fall 70 18 24 12
nucleus0 fall 64 8
endtune
</pre>
<p>
It contains:
<dl>
<dt><strong>tune</strong> &lt;tune name&gt;
<dd>
Starts the definition of a tune. The <b><code>tune name</code></b> can be used in a <b><code>tunes</code></b> statements in voice files.
<p>
<dt><strong>endtune</strong> &lt;tune name&gt;
<dd>
Ends the definition of a tune.
<p>
<dt><strong>prehead</strong> &lt;start pitch&gt; &lt;end pitch&gt;
<dd>
Gives the pitch path for any series of unstressed syllables before the first stressed syllable.
<p>
<dt><strong>headenv</strong> &lt;envelope&gt; &lt;height&gt;
<dd>
Gives the pitch envelope which is used for stressed syllables in the head (before the nucleus), including <b><code>onset</code></b> and <b><code>headlast</code></b> syllables if these are specified. <b><code>height</code></b> gives a pitch range for the envelope.
<p>
<dt><strong>head</strong> &lt;steps&gt; &lt;start pitch&gt; &lt;end pitch&gt; &lt;unstressed start&gt; &lt;unstressed end&gt;
<dd>
<b><code>start pitch</code></b> and <b><code>end pitch</code></b> give a pitch path for the stressed syllables of the head. <b><code>steps</code></b> is the maximum number of stressed syllables for which this applies. If there are additional stressed syllables, then the <b><code>headextend</code></b> statement is used for them.<p>
<b><code>unstressed start</code></b> and <b><code>unstressed end</code></b> give a pitch path for unstressed syllables between two stressed syllables. Their values are relative to the pitch of the previous stressed syllable. Values are usually negative, meaning that the unstressed syllables have lower pitch than the previous stressed syllable.
<p>
<dt><strong>headextend</strong> &lt;percentage list&gt;
<dd>
If the head contains more stressed syllables than is specified by <b><code>steps</code></b>, then <b><code>percentage list</code></b> is used. It contains up to 8 numbers which are used repeatedly for the additional stressed syllables. A value of 0 corresponds to the lower the <b><code>start pitch</code></b> and <b><code>end pitch</code></b> values of the <b><code>head</code></b> statement. 100 corresponds to the higher value. Negative values and values greater than 100 are allowed.
<p>
<dt><strong>nucleus</strong> &lt;envelope&gt; &lt;top pitch&gt; &lt;bottom pitch&gt; &lt;tail start&gt; &lt;tail end&gt;
<dd>
This gives the pitch envelope and pitch range of the last stressed syllable of the clause. <b><code>tail start</code></b> and <b><code>tail end</code></b> give a pitch path for the unstressed syllables which are after the last stressed syllable.
<p>
<dt><strong>nucleus0</strong> &lt;envelope&gt; &lt;top pitch&gt; &lt;bottom pitch&gt;
<dd>
This is used instead of <b><code>nucleus</code></b> if there are no unstressed syllables after the last stressed syllable. In this case, the pitch changes of the nucleus and the tail and both included in the nucleus.
</dl>
<p>
The following attributes may also be included:
<dl>
<dt><strong>onset</strong> &lt;pitch&gt; &lt;unstressed start&gt; &lt;unstressed end&gt;
<dd>
This specifies the pitch for the first stressed syllable of the head. If the <b><code>onset</code></b> statement is present, then the <b><code>head</code></b> statement used for the stressed syllables after the first.
<p>
<dt><strong>headlast</strong> &lt;pitch&gt; &lt;unstressed start&gt; &lt;unstressed end&gt;
<dd>
This specifies the pitch for the last stressed syllable of the head (i.e. the stressed syllable before the nucleus).
<p>
</dl>
docs/intonation.md
+132 -88
View File
@@ -1,116 +1,160 @@
# Table of contents
* [Intonation](#intonation)
* [Clauses](#clauses)
* [Tune definitions](#tune-definitions)
# Intonation
- [Clauses](#clauses)
- [Tune Definitions](#tune-definitions)
- [tune](#tune)
- [endtune](#endtune)
- [prehead](#prehead)
- [headenv](#headenv)
- [head](#head)
- [headextend](#headextend)
- [nucleus](#nucleus)
- [onset](#onset)
- [headlast](#headlast)
----------
In eSpeak NG's standard intonation model, a "tune" is applied to each
clause depending on its punctuation. Other intonation models may be used
for some languages, such as tone languages.
Named tunes are defined in the text file:
`phsource/intonation`. This file must be compiled for use by
eSpeak NG by using the espeakedit program, using the menu option:
**Compile -> Compile intonation data**.
Named tunes are defined in the text file `phsource/intonation`. This file
must be compiled for use by eSpeak NG by using:
espeak-ng --compile-intonations
## Clauses
The tunes which are used for a language can be specified by using a
`tunes` statement in a voice file in `espeak-data/voices`. eg:
`tunes` statement in a voice file in `espeak-data/voices`. e.g.:
`tunes   s1  c1  q1  e1`
tunes   s1  c1  q1  e1
It's parameters are four tune names which are used for clauses which end
in:
1. Full-stop.
1. Comma.
1. Question mark.
1. Exclamation mark.
2. Comma.
3. Question mark.
4. Exclamation mark.
A clause consists of the following parts:
* **Pre-head.**
These are any unstressed syllables before the first stressed syllable.
* **Head**
This is the part from the first stressed syllable up to the last syllable before the nucleus.
* **Nucleus**
This is stressed syllable which is the focus of the clause. eSpeak chooses the last stressed syllable of the clause.
* **Tail**
These are the syllables after the nucleus.
Pre-head
## Tune definitions
These are any unstressed syllables before the first stressed syllable.
Here is an example tune definition from the file `phsource/intonation`.
Head
```
tune s1
prehead 46 57
headenv fall 16
head 4 80 55 -8 -5
headextend 0 63 38 13 0
nucleus fall 70 18 24 12
nucleus0 fall 64 8
endtune
```
This is the part from the first stressed syllable up to the last syllable
before the nucleus.
It contains:
Nucleus
* **tune** \<tune name\>
Starts the definition of a tune. The `tune name` can
be used in a `tunes` statements in voice files.
* **endtune** \<tune name\>
Ends the definition of a tune.
* **prehead** \<start pitch\> \<end pitch\>
Gives the pitch path for any series of unstressed syllables before
the first stressed syllable.
* **headenv** \<envelope\> \<height\>
Gives the pitch envelope which is used for stressed syllables in the
head (before the nucleus), including `onset` and
`headlast` syllables if these are specified.
`height` gives a pitch range for the envelope.
* **head** \<steps\> \<start pitch\> \<end pitch\> \<unstressed start\> \<unstressed end\>
`start pitch` give a pitch
path for the stressed syllables of the head. `steps` is
the maximum number of stressed syllables for which this applies. If
there are additional stressed syllables, then the
`headextend` statement is used for them.
`unstressed start` give
a pitch path for unstressed syllables between two stressed
syllables. Their values are relative to the pitch of the previous
stressed syllable. Values are usually negative, meaning that the
unstressed syllables have lower pitch than the previous stressed
syllable.
* **headextend** \<percentage list\>
If the head contains more stressed syllables than is specified by
`steps` is used. It
contains up to 8 numbers which are used repeatedly for the
additional stressed syllables. A value of 0 corresponds to the lower
the `start pitch` values of the
`head` statement. 100 corresponds to the higher value.
Negative values and values greater than 100 are allowed.
* **nucleus** \<envelope\> \<top pitch\> \<bottom pitch\> \<tail start\> \<tail end\>
This gives the pitch envelope and pitch range of the last stressed
syllable of the clause. `tail start` and
`tail end` give a pitch path for the unstressed syllables
which are after the last stressed syllable.
* **nucleus0** \<envelope\> \<top pitch\> \<bottom pitch\>
This is used instead of `nucleus` if there are no
unstressed syllables after the last stressed syllable. In this case,
the pitch changes of the nucleus and the tail and both included in
the nucleus.
This is stressed syllable which is the focus of the clause. eSpeak chooses
the last stressed syllable of the clause.
The following attributes may also be included:
Tail
* **onset** \<pitch\> \<unstressed start\> \<unstressed end\>
This specifies the pitch for the first stressed syllable of the
head. If the `onset` statement is present, then the
`head` statement used for the stressed syllables after the
first.
* **headlast** \<pitch\> \<unstressed start\> \<unstressed end\>
This specifies the pitch for the last stressed syllable of the head
(i.e. the stressed syllable before the nucleus).
These are the syllables after the nucleus.
## Tune Definitions
Here is an example tune definition from the file `phsource/intonation`:
tune s1
prehead 46 57
headenv fall 16
head 4 80 55 -8 -5
headextend 0 63 38 13 0
nucleus fall 70 18 24 12
nucleus0 fall 64 8
endtune
### tune
tune <tune name>
Starts the definition of a tune. The `tune name` can be used in a `tunes`
statements in voice files.
### endtune
endtune <tune name>
Ends the definition of a tune.
### prehead
prehead <start pitch> <end pitch>
Gives the pitch path for any series of unstressed syllables before the first
stressed syllable.
### headenv
headenv <envelope> <height>
Gives the pitch envelope which is used for stressed syllables in the head
(before the nucleus), including `onset` and `headlast` syllables if these
are specified.
`height` gives a pitch range for the envelope.
### head
head <steps> <start pitch> <end pitch> <unstressed start> <unstressed end>
`start pitch` give a pitch path for the stressed syllables of the head.
steps` is the maximum number of stressed syllables for which this applies. If
there are additional stressed syllables, then the `headextend` statement is used
for them.
`unstressed start` give a pitch path for unstressed syllables between two stressed
syllables. Their values are relative to the pitch of the previous stressed syllable.
Values are usually negative, meaning that the unstressed syllables have lower pitch
than the previous stressed syllable.
### headextend
headextend <percentage list>
If the head contains more stressed syllables than is specified by `steps` is used.
Itmcontains up to 8 numbers which are used repeatedly for the additional stressed
syllables. A value of 0 corresponds to the lower the `start pitch` values of the
`head` statement. 100 corresponds to the higher value.
Negative values and values greater than 100 are allowed.
### nucleus
nucleus <envelope> <top pitch> <bottom pitch> <tail start> <tail end>
This gives the pitch envelope and pitch range of the last stressed syllable of
the clause. `tail start` and `tail end` give a pitch path for the unstressed
syllables which are after the last stressed syllable.
### nucleus0
nucleus0 <envelope> <top pitch> <bottom pitch>
This is used instead of `nucleus` if there are no unstressed syllables after
the last stressed syllable. In this case, the pitch changes of the nucleus and
the tail and both included in the nucleus.
### onset
onset <pitch> <unstressed start> <unstressed end>
This specifies the pitch for the first stressed syllable of the head. If the
`onset` statement is present, then the `head` statement used for the stressed
syllables after the first.
### headlast
headlast <pitch> <unstressed start> <unstressed end>
This specifies the pitch for the last stressed syllable of the head (i.e. the
stressed syllable before the nucleus).