Patent US5737725A successfully refreshed from Google Patents.
US5737725A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and system for automatically generating new voice files corresponding to new text from a script
Assignee: Qwest Communications International Inc
•
Filing: 1996-01-09
•
Granted: 1998-04-07
•
Expires: 2016-01-09
Abstract
Abstract A method and system for automatically generating at least one new voice file corresponding to at least one new text from a script incorporating a plurality of known text having corresponding preexisting voice files associated therewith. A plurality of phonetic sequences corresponding to the plurality of known text is stored in a first memory. A text input corresponding to a textual version of the script is provided and a text-to-phonetic translator translates the text input to obtain a corresponding textual phonetic sequence based on the plurality of phonetic sequences stored in the first memory. An audio input of the script is provided and a speech recognizer generates an audio phonetic sequence of the audio input. A text-to-speech aligner aligns the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input. The at least one new voice file is generated based on the alignment. The at least one new voice file may be stored in a second memory with the plurality of pre-existing voice files for use with a concatenated voice playback system.
Inventors
- 👤 Eliot M. Case
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 04:54
CPC Classifications
G; G10; G10L; G10L13/00; G10L13/08; G06; G06Q; G06Q30/00; G06Q30/06; G06Q30/0601; G10L13/02; G10L13/033; G10L13/06; G10L13/07
Claims Analysis
Total Claims: 71
Claim 1
Independent Claim
173 words
A method for automatically generating a new voice file from a script having at least one new speech pattern and a plurality of known speech patterns each having a known phonetic sequence associated therewith, the script having a text input and an audio input, the method comprising: translating the text input to obtain a corresponding textual phonetic sequence in order to identify at least one new textual phonetic sequence corresponding to the at least one new speech pattern based on the plurality of known speech patterns; translating the audio input to obtain a corresponding audio phonetic sequence; aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input of the script to identify at least one new audio phonetic sequence corresponding to the new at least one speech pattern; and generating the new voice file containing a portion of the audio input based on the at least one new audio phonetic sequence.
Claim 2
Independent Claim
173 words
A method for automatically generating a new voice file from a script having at least one new speech pattern and a plurality of known speech patterns each having a known phonetic sequence associated therewith, the script having a text input and an audio input, the method comprising: translating the text input to obtain a corresponding textual phonetic sequence in order to identify at least one new textual phonetic sequence corresponding to the at least one new speech pattern based on the plurality of known speech patterns; translating the audio input to obtain a corresponding audio phonetic sequence; aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input of the script to identify at least one new audio phonetic sequence corresponding to the new at least one speech pattern; and generating the new voice file containing a portion of the audio input based on the at least one new audio phonetic sequence.
Claim 3
Independent Claim
26 words
The method as recited in claim wherein the step of translating the text input includes the step of marking the at least one new speech pattern.
Claim 4
Dependent Claim
25 words
The method as recited in claim 2 wherein the step of marking includes the step of comparing the text input with the known phonetic sequences.
Claim 5
Dependent Claim
32 words
The method as recited in claim 2 further comprising the step of adding at least one new textual phonetic sequence corresponding to the at least one new speech pattern to a memory.
Claim 6
Dependent Claim
30 words
The method as recited in claim 2 wherein the step of generating includes the step of comparing the marked at least one new speech pattern with the aligned audio input.
Claim 7
Dependent Claim
24 words
The method as recited in claim 1 further comprising the step of editing the new voice file according to a predetermined set of rules.
Claim 8
Dependent Claim
32 words
The method as recited in claim 6 wherein the predetermined set of rules include reducing a level of at least one breath sound of the new voice file by a predetermined amount.
Claim 9
Dependent Claim
23 words
The method as recited in claim 6 wherein the predetermined set of rules include editing the new voice file at a zero crossing.
Claim 10
Dependent Claim
28 words
The method as recited in claim 6 wherein the predetermined set of rules include editing the new voice file in an inactive portion of the new voice file.
Claim 11
Dependent Claim
28 words
The method as recited in claim 6 wherein the predetermined set of rules include editing the new voice file in an active portion of the new voice file.
Claim 12
Dependent Claim
33 words
The method as recited in claim 10 wherein the predetermined set of rules include editing a beginning of the new voice file at a zero crossing in a zero to a positive direction.
Claim 13
Dependent Claim
33 words
The method as recited in claim 11 wherein the predetermined set of rules include editing an ending of the new voice file at a zero crossing in a negative to a zero direction.
Claim 14
Dependent Claim
33 words
The method as recited in claim 10 wherein the predetermined set of rules include editing a beginning of the new voice file at a zero crossing in a zero to a negative direction.
Claim 15
Dependent Claim
33 words
The method as recited in claim 13 wherein the predetermined set of rules include editing an ending of the new voice file at a zero crossing in a positive to a zero direction.
Claim 16
Dependent Claim
33 words
The method as recited in claim 6 wherein the predetermined set of rules include editing the new voice file at a predetermined amount of time before a beginning of the new voice file.
Claim 17
Dependent Claim
33 words
The method as recited in claim 6 wherein the predetermined set of rules include editing the new voice file at a predetermined amount of time after an ending of the new voice file.
Claim 18
Dependent Claim
22 words
The method as recited in claim 1 further comprising the step of storing the new voice file in a voice file memory.
Claim 19
Dependent Claim
24 words
The method as recited in claim 17 wherein the step of storing includes the step of assigning an identifier to the new voice file.
Claim 20
Dependent Claim
35 words
The method as recited in claim 1 further comprising the step of concatenating the new voice file with a selected portion of the plurality of known speech patterns to obtain a natural sounding voice message.
Claim 21
Dependent Claim
27 words
The method as recited in claim 1 wherein the step of translating the audio input includes the step of recording the script to obtain a voice recording.
Claim 22
Dependent Claim
47 words
The method as recited in claim 1 wherein the step of translating the audio input includes the step of providing a television audio signal and wherein the step of translating the text input includes the step of providing a closed caption decoding of the television audio signal.
Claim 23
Independent Claim
272 words
A method for automatically generating at least one new voice file corresponding to at least one new text from a script incorporating a plurality of known text having corresponding pre-existing voice files associated therewith, the method comprising: storing a plurality of phonetic sequences corresponding to the plurality of known text in a first memory; providing a text input corresponding to a textual version of the script; translating the text input to obtain a corresponding textual phonetic sequence based on the plurality of phonetic sequences stored in the first memory; comparing the text input with the plurality of phonetic sequences stored in the first memory; marking the at least one new text; adding at least one new textual phonetic sequence corresponding to the at least one new text in the first memory, the at least one new textual phonetic transcript corresponding to the audio phonetic transcript of the at least one new text; providing an audio input corresponding to an audio version of the script; generating an audio phonetic sequence of the audio input by comparing the marked at least one new text with the aligned audio input; aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input of the script; generating the at least one new voice file based on the alignment; and editing the at least one new voice file according to a predetermined set of rules, including reducing a level of at least one breath sound of the at least one new voice file by a predetermined amount.
Claim 24
Independent Claim
272 words
A method for automatically generating at least one new voice file corresponding to at least one new text from a script incorporating a plurality of known text having corresponding pre-existing voice files associated therewith, the method comprising: storing a plurality of phonetic sequences corresponding to the plurality of known text in a first memory; providing a text input corresponding to a textual version of the script; translating the text input to obtain a corresponding textual phonetic sequence based on the plurality of phonetic sequences stored in the first memory; comparing the text input with the plurality of phonetic sequences stored in the first memory; marking the at least one new text; adding at least one new textual phonetic sequence corresponding to the at least one new text in the first memory, the at least one new textual phonetic transcript corresponding to the audio phonetic transcript of the at least one new text; providing an audio input corresponding to an audio version of the script; generating an audio phonetic sequence of the audio input by comparing the marked at least one new text with the aligned audio input; aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input of the script; generating the at least one new voice file based on the alignment; and editing the at least one new voice file according to a predetermined set of rules, including reducing a level of at least one breath sound of the at least one new voice file by a predetermined amount.
Claim 25
Dependent Claim
26 words
The method as recited in claim 22 wherein the predetermined set of rules include editing the at least one new voice file at a zero crossing.
Claim 26
Dependent Claim
34 words
The method as recited in claim 22 wherein the predetermined set of rules include editing the at least one new voice file in an inactive portion of the at least one new voice file.
Claim 27
Dependent Claim
34 words
The method as recited in claim 22 wherein the predetermined set of rules include editing the at least one new voice file in an active portion of the at least one new voice file.
Claim 28
Dependent Claim
36 words
The method as recited in claim 25 wherein the predetermined set of rules include editing a beginning of the at least one new voice file at a zero crossing in a zero to a positive direction.
Claim 29
Dependent Claim
36 words
The method as recited in claim 26 wherein the predetermined set of rules include editing an ending of the at least one new voice file at a zero crossing in a negative to a zero direction.
Claim 30
Dependent Claim
36 words
The method as recited in claim 25 wherein the predetermined set of rules include editing a beginning of the at least one new voice file at a zero crossing in a zero to a negative direction.
Claim 31
Dependent Claim
36 words
The method as recited in claim 28 wherein the predetermined set of rules include editing an ending of the at least one new voice file at a zero crossing in a positive to a zero direction.
Claim 32
Dependent Claim
39 words
The method as recited in claim 22 wherein the predetermined set of rules include editing the at least one new voice file at a predetermined amount of time before a beginning of the at least one new voice file.
Claim 33
Dependent Claim
38 words
The method as recited in claim 22 wherein the predetermined set of rules include editing the at least one new voice file at a predetermined amount of time after ending of the at least one new voice file.
Claim 34
Independent Claim
174 words
A system for automatically generating new voice file from a script having at least one new speech pattern and a plurality of known speech patterns each having a known phonetic sequence associated therewith, the script having a text input and an audio input, the system comprising: means for translating the text input to obtain a corresponding textual phonetic sequence in order to identify at least one new textual phonetic sequence corresponding to the at least one new speech pattern based on the plurality of known speech patterns; means for translating the audio input to obtain a corresponding audio phonetic sequence; means for aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input to identify at least one new audio phonetic sequence corresponding to the new speech pattern; and means for generating the new voice file containing a portion of the audio input based on the at least one new audio phonetic sequence.
Claim 35
Independent Claim
174 words
A system for automatically generating new voice file from a script having at least one new speech pattern and a plurality of known speech patterns each having a known phonetic sequence associated therewith, the script having a text input and an audio input, the system comprising: means for translating the text input to obtain a corresponding textual phonetic sequence in order to identify at least one new textual phonetic sequence corresponding to the at least one new speech pattern based on the plurality of known speech patterns; means for translating the audio input to obtain a corresponding audio phonetic sequence; means for aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input to identify at least one new audio phonetic sequence corresponding to the new speech pattern; and means for generating the new voice file containing a portion of the audio input based on the at least one new audio phonetic sequence.
Claim 36
Dependent Claim
27 words
The system as recited in claim 32 wherein the means for translating the text input further includes means for marking the at least one new speech pattern.
Claim 37
Dependent Claim
24 words
The system as recited in claim 33 wherein the means for translating the text input compares the text input with the known phonetic sequences.
Claim 38
Dependent Claim
31 words
The system as recited in claim 33 further comprising means for adding at least one new textual phonetic sequence corresponding to the at least one new speech pattern to a memory.
Claim 39
Dependent Claim
29 words
The system as recited in claim 33 wherein the means for generating includes means for comparing the marked at least one new speech pattern with the aligned audio input.
Claim 40
Dependent Claim
23 words
The system as recited in claim 32 further comprising means for editing the new voice file according to a predetermined set of rules.
Claim 41
Dependent Claim
32 words
The system as recited in claim 37 wherein the predetermined set of rules include reducing a level of at least one breath sound of the new voice file by a predetermined amount.
Claim 42
Dependent Claim
23 words
The system as recited in claim 37 wherein the predetermined set of rules include editing the new voice file at a zero crossing.
Claim 43
Dependent Claim
28 words
The system as recited in claim 37 wherein the predetermined set of rules include editing the new voice file in an inactive portion of the new voice file.
Claim 44
Dependent Claim
28 words
The system as recited in claim 37 wherein the predetermined set of rules include editing the new voice file in an active portion of the new voice file.
Claim 45
Dependent Claim
33 words
The method as recited in claim 41 wherein the predetermined set of rules include editing a beginning of the new voice file at a zero crossing in a zero to a positive direction.
Claim 46
Dependent Claim
33 words
The method as recited in claim 42 wherein the predetermined set of rules include editing an ending of the new voice file at a zero crossing in a negative to a zero direction.
Claim 47
Dependent Claim
33 words
The method as recited in claim 41 wherein the predetermined set of rules include editing a beginning of the new voice file at a zero crossing in a zero to a negative direction.
Claim 48
Dependent Claim
32 words
The method as recited in claim 44 wherein the predetermined set of rules editing an ending of the new voice file at a zero crossing in a positive to a zero direction.
Claim 49
Dependent Claim
33 words
The system as recited in claim 37 wherein the predetermined set of rules include editing the new voice file at a predetermined amount of time before a beginning of the new voice file.
Claim 50
Dependent Claim
33 words
The system as recited in claim 37 wherein the predetermined set of rules include editing the new voice file at a predetermined amount of time after an ending of the new voice file.
Claim 51
Dependent Claim
21 words
The system as recited as recited in claim 22 further comprising a voice file memory for storing the new voice file.
Claim 52
Dependent Claim
19 words
The system as recited in claim 48 further comprising means for assigning an identifier to the new voice file.
Claim 53
Dependent Claim
34 words
The system as recited in claim 48 further comprising means for concatenating the new voice file with a selected portion of the plurality of known speech patterns to obtain a natural sounding voice message.
Claim 54
Dependent Claim
26 words
The system as recited in claim 32 wherein the means for translating the audio input include means for recording the script to obtain a voice recording.
Claim 55
Dependent Claim
15 words
The system as recited in claim 51 wherein the means for recording in a microphone.
Claim 56
Dependent Claim
31 words
The system as recited in claim 32 wherein the audio input is a television audio signal and wherein the text input is a closed caption decoding of the television audio signal.
Claim 57
Dependent Claim
18 words
The system as recited in claim 32 wherein the means for translating text input is a text-to-phonetic translator.
Claim 58
Dependent Claim
19 words
The system as recited in claim 32 wherein the means for translating the audio input is a speech recognizer.
Claim 59
Dependent Claim
16 words
The system as recited in claim 32 wherein the means for aligning is a text-to-speech aligner.
Claim 60
Dependent Claim
24 words
The system as recited in claim 32 wherein the means for translating the audio input and the means for aligning is a text-to-speech aligner.
Claim 61
Independent Claim
282 words
A system for automatically generating at least one new voice file corresponding to at least one new text from a script incorporating a plurality of known text having corresponding pre-existing voice files associated therewith, the system comprising: first memory for storing a plurality of phonetic sequences corresponding to the plurality of known text; means for providing a text input corresponding to a textual version of the script; means for translating text input to obtain a corresponding textual phonetic sequence based on a comparison of the textual version of the script with the plurality of phonetic sequences stored in the first memory; means for marking the at least one new text; means for adding at least one new textual phonetic sequence corresponding to the at least one new text in the first memory, the new textual phonetic transcript corresponding to the audio phonetic transcript of the at least one new text; means for providing an audio input corresponding to an audio version of the spirit; first means for generating an audio phonetic sequence of the audio input; means for aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input; second means for generating the at least one new voice file based on the alignment based on a comparison of the marked at least one new text with the aligned audio input; and means for editing the at least one new voice file according to a predetermined set of rules, including reducing a level of at least one breath sound of the at least one new voice file by a predetermined amount.
Claim 62
Independent Claim
282 words
A system for automatically generating at least one new voice file corresponding to at least one new text from a script incorporating a plurality of known text having corresponding pre-existing voice files associated therewith, the system comprising: first memory for storing a plurality of phonetic sequences corresponding to the plurality of known text; means for providing a text input corresponding to a textual version of the script; means for translating text input to obtain a corresponding textual phonetic sequence based on a comparison of the textual version of the script with the plurality of phonetic sequences stored in the first memory; means for marking the at least one new text; means for adding at least one new textual phonetic sequence corresponding to the at least one new text in the first memory, the new textual phonetic transcript corresponding to the audio phonetic transcript of the at least one new text; means for providing an audio input corresponding to an audio version of the spirit; first means for generating an audio phonetic sequence of the audio input; means for aligning the text input and the corresponding textual phonetic sequence with the audio input and the corresponding audio phonetic sequence to obtain an alignment of the text input and the audio input; second means for generating the at least one new voice file based on the alignment based on a comparison of the marked at least one new text with the aligned audio input; and means for editing the at least one new voice file according to a predetermined set of rules, including reducing a level of at least one breath sound of the at least one new voice file by a predetermined amount.
Claim 63
Dependent Claim
23 words
The system as recited in claim 58 wherein the predetermined set of rules include editing the new voice file at a zero crossing.
Claim 64
Dependent Claim
28 words
The system as recited in claim 58 wherein the predetermined set of rules include editing the new voice file in an inactive portion of the new voice file.
Claim 65
Dependent Claim
28 words
The system as recited in claim 58 wherein the predetermined set of rules include editing the new voice file in an active portion of the new voice file.
Claim 66
Dependent Claim
36 words
The system as recited in claim 61 wherein the predetermined set of rules include editing a beginning of the at least one new voice file at a zero crossing in a zero to a positive direction.
Claim 67
Dependent Claim
36 words
The system as recited in claim 62 wherein the predetermined set of rules include editing an ending of the at least one new voice file at a zero crossing in a negative to a zero direction.
Claim 68
Dependent Claim
36 words
The system as recited in claim 61 wherein the predetermined set of rules include editing a beginning of the at least one new voice file at a zero crossing in a zero to a negative direction.
Claim 69
Dependent Claim
36 words
The system as recited in claim 64 wherein the predetermined set of rules include editing an ending of the at least one new voice file at a zero crossing in a positive to a zero direction.
Claim 70
Dependent Claim
33 words
The system as recited in claim 58 wherein the predetermined set of rules include editing the new voice file at a predetermined amount of time before a beginning of the new voice file.
Claim 71
Dependent Claim
32 words
The system as recited in claim 58 wherein the predetermined set of rules include editing the new voice file at predetermined amount of time after an ending of the new voice file.
References Cited (Backward Citations)
US4785408A
Cited
US5526259A
Cited
US5278943A
Cited
US5131045A
Cited
US5400434A
Cited
US5283731A
Cited
US5384893A
Cited
US5592585A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2001-04-06 | 2001-10-06 | 2002-04-07 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-04-06 | 2005-10-06 | 2006-04-07 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-04-06 | 2009-10-06 | 2010-04-07 | $7700.00 | Window Closed / Lapsed |