0001-Added-proto-sandbox-rst-audition-Phoneme-Utterance3.patch

S. Schulz, 11/04/2015 02:21 PM

Download (3.2 KB)

View differences:

proto/sandbox/rst/audition/Phoneme.proto
1
package rst.audition;
2

  
3
option java_outer_classname = "PhonemeType";
4

  
5
/**
6
 * Objects of this represent a single phoneme-duration pair.
7
 *
8
 * A list of elements of this type can be used to describe words or
9
 * whole sentences of speech.
10
 *
11
 * @author Simon Schulz <sschulz@techfak.uni-bielefeld.de>
12
 */
13
 // @create_collection
14
message Phoneme {
15

  
16
    /**
17
     * A single phone symbol (such as aI, E, C, R, _, ...).
18
     *
19
     * e.g. see https://en.wikipedia.org/wiki/Phoneme
20
     *      or http://www.phon.ucl.ac.uk/home/sampa/german.htm (german) examples
21
     */
22
    required string symbol = 1;
23

  
24
    /**
25
     * The duration of this symbol.
26
     */
27
    // @unit(millisecond)
28
    required uint32 duration = 2;
29

  
30
}
proto/sandbox/rst/audition/Utterance.proto
1
package rst.audition;
2

  
3
import "rst/audition/Phoneme.proto";
4
import "rst/audition/SoundChunk.proto";
5

  
6
option java_outer_classname = "UtteranceType";
7

  
8
/**
9
 * Objects of this represent a single utterances of speech.
10
 *
11
 * The data describes a single utterance in three different forms:
12
 *
13
 * * @ref .phonemes describes the utterance as list of phone symbols
14
 *   and durations (useful for lip animation).
15
 *
16
 * * @ref .audio is a @ref SoundChunk that can be played back on audio
17
 *   devices containing the realization (e.g. by a TTS system) 
18
 *   of the included phoneme list
19
 *
20
 * * @ref .description is a textual description of the utterance for
21
 *   debugging purposes.
22
 *
23
 * @author Simon Schulz <sschulz@techfak.uni-bielefeld.de>
24
 */
25
message Utterance {
26

  
27
    /**
28
     * A collection of phonemes. Will be played back in the same ordering as given by @ref .Phoneme
29
     */
30
    required PhonemeCollection phonemes = 1;
31

  
32
    /**
33
     * a chunk of audio data that can be played back
34
     * containing the realization (e.g. by a TTS system) of the included phoneme list
35
     */
36
    required SoundChunk audio = 2;
37

  
38
    /**
39
     * Textual representation of the utterance
40
     */
41
    required string description = 3;
42

  
43
}
0
-