Method and apparatus for recording prosody for fully concatenated speech
View Patent ↗A method of making a digital voice library utilized for converting text to concatenated voice in accordance with a set of playback rules includes generating a complex tone that reflects a particular inflection required for a particular voice recording of a particular speech item. The complex tone is composed of portions of a recording of a voice talent uttering a vocal sequence. The voice talent is recorded reciting the particular speech item to make the particular voice recording. The voice talent uses the complex tone as a guide to allow the voice talent to recite the particular speech item in accordance with the particular inflection.
1. A method of making a digital voice library utilized for converting text to concatenated voice in accordance with a set of playback rules, the digital voice library including a plurality of speech items and a corresponding plurality of voice recordings wherein each speech item corresponds to at least one available voice recording, wherein multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item, the method comprising:
establishing a vocal sequence;
recording a voice talent uttering the vocal sequence;
generating a complex tone that reflects a particular inflection required for a particular voice recording of a particular speech item, the complex tone being composed of portions of the recording of the voice talent uttering the vocal sequence; and
recording the voice talent reciting the particular speech item to make the particular voice recording, the voice talent using the complex tone as a guide to allow the voice talent to recite the particular speech item in accordance with the particular inflection, the particular voice recording being utilized in the digital voice library for converting text to concatenated voice in accordance with the set of playback rules.
2. The method of claim 1 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of words; and
recording the voice talent speaking the sequence of words.
3. The method of claim 1 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of tones; and
recording the voice talent humming the sequence of tones.
4. The method of claim 1 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of words; and
recording the voice talent singing the sequence of words.
5. The method of claim 1 wherein the particular speech item is a phoneme.
6. The method of claim 1 wherein the particular speech item is a syllable.
7. The method of claim 1 wherein the particular speech item is a word.
8. The method of claim 1 wherein the particular speech item is a phrase.
9. The method of claim 1 wherein the particular speech item is a sentence.
10. A digital voice library utilized for converting text to concatenated voice in accordance with a set of playback rules, the digital voice library including a plurality of speech items and a corresponding plurality of voice recordings wherein each speech item corresponds to at least one available voice recording, wherein multiple voice recordings that correspond to a single speech item represent various inflections of that single speech item, the digital voice library further comprising a particular voice recording of a particular speech item, the particular voice recording requiring a particular inflection and being made by:
establishing a vocal sequence;
recording a voice talent uttering the vocal sequence;
generating a complex tone that reflects the particular inflection required for the particular voice recording of the particular speech item, the complex tone being composed of portions of the recording of the voice talent uttering the vocal sequence; and
recording the voice talent reciting the particular speech item to make the particular voice recording, the voice talent using the complex tone as a guide to allow the voice talent to recite the particular speech item in accordance with the particular inflection, the particular voice recording being utilized in the digital voice library for converting text to concatenated voice in accordance with the set of playback rules.
11. The digital voice library of claim 10 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of words; and
recording the voice talent speaking the sequence of words.
12. The digital voice library of claim 10 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of tones; and
recording the voice talent humming the sequence of tones.
13. The digital voice library of claim 10 wherein establishing the vocal sequence and recording the voice talent further comprise:
establishing the vocal sequence as a sequence of words; and
recording the voice talent singing the sequence of words.
14. The digital voice library of claim 10 wherein the particular speech item is a phoneme.
15. The digital voice library of claim 10 wherein the particular speech item is a syllable.
16. The digital voice library of claim 10 wherein the particular speech item is a word.
17. The digital voice library of claim 10 wherein the particular speech item is a phrase.
18. The digital voice library of claim 10 wherein the particular speech item is a sentence.