1、 55556.6 2013 . III (MPEG4 AUDIO) (TTSI) ISO/IEC 14496-3:2009 (NEQ) 53556.6 2013 II 1 - - ( ) 2 480 3 22 2013 . 1703- 4 / 14496-3:2009 . . 3. (ISO/IEC14496-3:2009 Information technology - Coding of audio-visual objects - Part 3: Audio (NEQ) 5 1.0 2012 ( 8). ( 1 ) , . () . , (gost.ru) , 2014 , 53556.
2、6 2013 1 . III (MPEG4 AUDIO) (TTSI) Sound broadcasting digital. Coding of signals of sound broadcasting with reduction of redundancy for transfer on digital communication channels. A part III (MPEG4 audio). Te to speech interface (TTSI) 20140901 1 MPEG4 Audio (-TTS) , . -TTS, (FA) (MP) . -TTS , . FA
3、 , . (TTS) . TTS , . , TTS (FA) / (MP) . TTS FA MP . MPEG4 TTS FA/MP. -TTS TTS. TTS . : , , . -TTS, , TTS , , TTS FA MP. 2 , 53556.0-2009. 53556.6 2013 2 3 F0 ( ) DEMUX FA FAP ID IPA MP -TTS TTS MPEG4 Audio STOD TTS 4 MPEG4 Audio 4.1 TTSSpecificConfig MPEG4 Audio TTSSpecificConfig () TTS_Sequence ()
4、 1 - TTS_Sequence () TTS_Sequence () TTS_Sequence_ID; Language_Code; Gender_Enable; Age_Enable; Speech_Rate_Enable; Prosody_Enable; Video_Enable; Lip_Shape_Enable; Trick_Mode_Enable; 5 18 1 1 1 1 1 1 1 uimsbf uimsbf bslbf bslbf bslbf bslbf bslbf bvslbf bslbf 4.2 MPEG4 Audio AlPduPayload TTS_Sentence
5、 (); 2 TTS_Sentence () TTS_Sentence () TTS_Sentence_ID; 10 uimsbf Silence; 1 bslbf if (Silence) SilenceDuration; 12 uimsbf else if (Gender_Enable) Gender; 1 bslbf if (Age_Enable) 3 uimsbf Age; 53556.6 2013 3 2 if (!Video_Enable 4 uimsbf Length_of_Text; 12 uimsbf for (j = 0; j , . , , FAP, TtsFAPInte
6、rface . , . Dur_Enable , 1, . F0_Contour_Enable , 1, . Energy_Contour_Enable , 1, . Number_of_Phonemes - , . Phonemes_Symbols_Length - Phonemes_Symbols ( IPA) , IPA . Phoneme_Symbols - Unicode 2,0. IPA. IPA , , , . Dur_each_Phoneme - , . Num_F0 - F0, . F0_Contour_each_Phoneme - F0, , F0_Contour_each
7、_Phoneme_Time. F0_Contour_each_Phoneme_Time - , , F0_Contour_each_Phoneme. Energy_Contour_each_Phoneme - 8- , . X 1050logint ,xp- pA - . Sentence_Duration - , . Position_in_Sentence - , . Offset - , . Number_of_Lip_Shape - , . Lip_Shape_in_Sentence - , . Lip_Shape - , . 6 MPEG4 Audio -TTS , -TTS. :
8、; ; ; ; / FAP. 6.1 , -TTS 53556.6 2013 6 . 6.2 -TTS, . -TTS: FA MP : : () , : , trick pseudo-C . 6.3 . 32767 + 32768. 6.4 , . MP ttsControl, : 4 ttsControl () ttsControl() ttsPlay(); ttsForward(); ttsBackward(); ttsStopSyllable(); ttsStopWord(); ttsStopPhrase(); TtsChangeSpeedRate(); TtsChangePitchD
9、ynamicRange(); TtsChangePitchHeight(); TtsChangeGender(); ttsChangeAge(); ttsPlay , ttsForward ttsBackword . ttsStopSyllable, ttsStopWord ttsStopPhrase , , , . ttsChangeSpeechRate . 1 16. ttsChangePitchDynamicRange . , , 1 16. 1 16 ttsChangePitchHeight. ttsChangeGender ttsChangeAge , , . 6.5 / FAP M
10、PEG4 . . TTS phonemeSymbol phonemeDuration, Phoneme/Bookmark-to-FAP. / FAP phonemeSymbol, phonemeDuration . . TTS. Lip_Shape_Enable , 53556.6 2013 7 Lip_Shape_in_Sentence , phonemeDuration. TTS . / wordBegin, , / , . MTTS_Text TtsFAPInterface . , TtsFAPInterface . , 40 . starttime , , -TTS, . ttsFAP
11、Interface phoneme-to-FAP. 5 TtsFAPInterface () TtsFAPInterface () PhonemeSymbol; 8 uimsbf PhonemeDuration; 12 uimsbf f0Average; 8 uimsbf ; 1 bslbf WordBegin; 1 bslbf ; char Starttime; long int 53556.6 2013 8 A () MPEG4 Audio A.1 -TTS. A.2 : MPEG4 (STOD) STOD , -. STOD -TTS MPEG4 . , , (, ). , , . -TTS MPEG4 -TTS MPEG4. A.3 :
