US7212972B2
Expired / Lapsed
US
⏱️ 0.0 years remaining
Audio features description method and audio video features description collection construction method
Assignee: KDDI Corp
•
Filing: 2000-12-07
•
Granted: 2007-05-01
•
Expires: 2020-12-07
Abstract
Abstract A feature description method capable of high-speed, efficiently searching audio data or grasping a summary of the audio data by giving considerations to elements and characteristics peculiar to the audio data, is provided. Also, an audio video data feature description collection construction method for collecting feature descriptions from multiple pieces of audio video data based on a specific feature type makes it possible to efficiently, clearly describe a feature description collection.
Inventors
- 👤 Masaru Sugano
- 👤 Yasuyuki Nakajima
- 👤 Hiromasa Yanagihara
- 👤 Akio Yoneyama
- 👤 Haruhisa Kato
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-25 06:34
CPC Classifications
G; G06; G06F; G06F16/00; G06F16/60; G06F16/68; G06F16/683; G06F16/64
Claims Analysis
Total Claims: 35
Claim 1
Independent Claim
72 words
A compressed or uncompressed audio data feature description scheme, wherein audio features are hierarchically represented by setting entire audio data which corresponds to one audio program at the highest hierarchy and describing the audio features in metadata in order from higher to lower hierarchies, and wherein said hierarchies are represented by one or more audio programs having a semantically continuous content and at least either an audio scene or an audio shot.
Claim 2
Dependent Claim
72 words
A compressed or uncompressed audio data feature description scheme, wherein audio features are hierarchically represented by setting entire audio data which corresponds to one audio program at the highest hierarchy and describing the audio features in metadata in order from higher to lower hierarchies, and wherein said hierarchies are represented by one or more audio programs having a semantically continuous content and at least either an audio scene or an audio shot.
Claim 3
Dependent Claim
46 words
A compressed or uncompressed audio data feature description scheme according to claim 1 , wherein said hierarchy is described by at least a hierarchy identifier and a feature which includes an audio type, a feature type and audio segment information classified according to the feature types.
Claim 4
Dependent Claim
42 words
A compressed or uncompressed audio feature description scheme according to claim 2 , wherein said audio segment information is described by either of a combination of start time code and end time code, or a combination of start time code and duration.
Claim 5
Dependent Claim
78 words
A compressed or uncompressed audio data feature description scheme, wherein audio features are hierarchically represented by setting entire audio data which corresponds to one audio program at the highest hierarchy and describing the audio features in metadata in order from higher to lower hierarchies, and wherein said hierarchy is described by at least a hierarchy identifier and a feature which includes an audio data type, a feature type and audio segment information classified according to the feature types.
Claim 6
Dependent Claim
78 words
A compressed or uncompressed audio data feature description scheme, wherein audio features are hierarchically represented by setting entire audio data which corresponds to one audio program at the highest hierarchy and describing the audio features in metadata in order from higher to lower hierarchies, and wherein said hierarchy is described by at least a hierarchy identifier and a feature which includes an audio data type, a feature type and audio segment information classified according to the feature types.
Claim 7
Dependent Claim
42 words
A compressed or uncompressed audio data feature description scheme according to claim 4 , wherein said audio segment information is described by either of a combination of start time code and end time code, a combination of start time code and duration.
Claim 8
Dependent Claim
88 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; an audio feature of each hierarchy is represented by an audio thumbnail indicating either one or more audio pieces or images; the audio thumbnail is declared and described as a feature type; if the audio thumbnail is the audio pieces, segment information of one or more audio pieces are described; and if the audio thumbnail is the images, one or more file names of the images are described.
Claim 9
Dependent Claim
88 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; an audio feature of each hierarchy is represented by an audio thumbnail indicating either one or more audio pieces or images; the audio thumbnail is declared and described as a feature type; if the audio thumbnail is the audio pieces, segment information of one or more audio pieces are described; and if the audio thumbnail is the images, one or more file names of the images are described.
Claim 10
Dependent Claim
89 words
A compressed or uncompressed audio data feature description scheme, wherein an audio feature of at least one audio scene or one audio shot is represented by an audio clip which is at least one audio piece having an arbitrary length equal to or shorter than that of the audio scene or the audio shot, respectively, said audio scenes and/or audio shots are described through one or more hierarchies, and wherein at least one audio clip representing said audio scenses or audio shots is represented as the key audio clip.
Claim 11
Dependent Claim
89 words
A compressed or uncompressed audio data feature description scheme, wherein an audio feature of at least one audio scene or one audio shot is represented by an audio clip which is at least one audio piece having an arbitrary length equal to or shorter than that of the audio scene or the audio shot, respectively, said audio scenes and/or audio shots are described through one or more hierarchies, and wherein at least one audio clip representing said audio scenses or audio shots is represented as the key audio clip.
Claim 12
Dependent Claim
93 words
A compressed or uncompressed audio data feature description scheme according to claim 7 , wherein the key audio clip is declared and described as a feature type; if an audio type of the key audio clips is voice or speech, a voice or a speech representing the key audio clips is represented as the key word and the content of the key word is described by textual information; the key word is declared and described as a feature sub type; and at least one audio segment corresponding to the key word is described.
Claim 13
Dependent Claim
76 words
A compressed or uncompressed audio feature description scheme according to claim 7 , wherein the key audio clip is declared and described as a feature type; if an audio data type of the key audio clips is music, a music representing the key audio clips is represented as the key note; the key note is declared and described as a feature sub type; and at least one audio segment corresponding to the key note is described.
Claim 14
Dependent Claim
96 words
A compressed or uncompressed audio data feature description scheme wherein at least one audio clip representing said audio scenes or audio shots is represented as the key audio clip according to claim 7 , wherein the key audio clip is declared and described as a feature type; if an audio type of the key audio clips is sound, a sound representing the key audio clips is represented as the key sound; the key sound is declared and described as a feature sub type; and at least one audio segment corresponding to the key sound is described.
Claim 15
Dependent Claim
58 words
A compressed or uncompressed audio data feature description scheme, wherein if audio data consists of multiple channels or tracks, a representative channel or track of the audio data is represented as the key stream; the key stream is declared and described as a feature type; and at least one audio segment corresponding to the key stream is described.
Claim 16
Dependent Claim
58 words
A compressed or uncompressed audio data feature description scheme, wherein if audio data consists of multiple channels or tracks, a representative channel or track of the audio data is represented as the key stream; the key stream is declared and described as a feature type; and at least one audio segment corresponding to the key stream is described.
Claim 17
Dependent Claim
60 words
A compressed or uncompressed audio data feature description scheme, wherein an audio clip representing an event in audio data is represented as the key event; the key event is declared and described as a feature type; a content of the key event is described by textual information; and at least one audio segment corresponding to the key event is described.
Claim 18
Dependent Claim
60 words
A compressed or uncompressed audio data feature description scheme, wherein an audio clip representing an event in audio data is represented as the key event; the key event is declared and described as a feature type; a content of the key event is described by textual information; and at least one audio segment corresponding to the key event is described.
Claim 19
Dependent Claim
64 words
A compressed or uncompressed audio data feature description scheme, wherein an audio clip from a representative audio source in audio data is represented as the key object; the key object is declared and described as a feature type; a content of the key object is declared and described by textual information; and at least one audio segment corresponding to the key object is described.
Claim 20
Dependent Claim
64 words
A compressed or uncompressed audio data feature description scheme, wherein an audio clip from a representative audio source in audio data is represented as the key object; the key object is declared and described as a feature type; a content of the key object is declared and described by textual information; and at least one audio segment corresponding to the key object is described.
Claim 21
Dependent Claim
82 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; at least one introduction or representative audio piece of each hierarchy corresponding to an audio program, an audio scene or an audio shot is represented as an audio segment; a sequence of the audio segments is represented as an audio slide; the audio slide is declared and described as a feature type; and the audio segments composing the audio slide are described.
Claim 22
Dependent Claim
82 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; at least one introduction or representative audio piece of each hierarchy corresponding to an audio program, an audio scene or an audio shot is represented as an audio segment; a sequence of the audio segments is represented as an audio slide; the audio slide is declared and described as a feature type; and the audio segments composing the audio slide are described.
Claim 23
Dependent Claim
85 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; at least one introduction or representative audio piece of each hierarchy corresponding to an audio program, an audio scene or an audio shot is saved as an audio file; a sequence of the audio files is represented as an audio slide; the audio slide is declared and described as a feature type; and file names of the audio files composing the audio slide are described.
Claim 24
Dependent Claim
85 words
A compressed or uncompressed audio data feature description scheme, wherein an audio program is described through one or more hierarchies; at least one introduction or representative audio piece of each hierarchy corresponding to an audio program, an audio scene or an audio shot is saved as an audio file; a sequence of the audio files is represented as an audio slide; the audio slide is declared and described as a feature type; and file names of the audio files composing the audio slide are described.
Claim 25
Dependent Claim
58 words
A compressed or uncompressed audio data feature description scheme, wherein if a feature type is any of a shot, a key audio clip, a key word, a key note, or a key sound, value indicating level of the feature types is described; and multiple audio data with said feature types are described hierarchically according to the level values.
Claim 26
Dependent Claim
58 words
A compressed or uncompressed audio data feature description scheme, wherein if a feature type is any of a shot, a key audio clip, a key word, a key note, or a key sound, value indicating level of the feature types is described; and multiple audio data with said feature types are described hierarchically according to the level values.
Claim 27
Dependent Claim
67 words
A compressed or uncompressed audio video data feature collection description scheme, wherein feature descriptions based on various feature types are associated with each audio video program; the feature descriptions are extracted from multiple audio video programs based on a specific feature type; a feature collection description is constructed by using multiple extracted feature descriptions; and the feature collection description is described as a feature collection description file.
Claim 28
Dependent Claim
67 words
A compressed or uncompressed audio video data feature collection description scheme, wherein feature descriptions based on various feature types are associated with each audio video program; the feature descriptions are extracted from multiple audio video programs based on a specific feature type; a feature collection description is constructed by using multiple extracted feature descriptions; and the feature collection description is described as a feature collection description file.
Claim 29
Dependent Claim
67 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 17 , wherein the feature type is a summary type; summary descriptions associated with each audio video programs are extracted from multiple audio video programs based on a specific summary type; a summary collection is aggregated using multiple extracted summary descriptions; and the summary collection is described as a summary collection description file.
Claim 30
Dependent Claim
58 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 18 , wherein the summary types for summary collection descriptions and contents of the summary types are described altogether in a nested structure, whereby the summary collection can described based on different summary types, or based on different contents among the same summary type.
Claim 31
Dependent Claim
75 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 17 , wherein as an element for describing the feature collection description in the feature collection description file, the feature types for feature collection descriptions and contents of the feature types are described at a higher level; and the audio video program identifiers referred to by each feature description and each corresponding segment information in the audio video programs are described.
Claim 32
Dependent Claim
84 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 20 , wherein if the feature is a summary of audio video data, summary types for summary collection and contents of the summary types are described at a higher level as an element for describing the summary collection in the summary collection file; the audio video program identifiers referred to by each summary description and each corresponding segment information in the audio video programs are described at a lower level.
Claim 33
Dependent Claim
58 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 21 , wherein the summary types for summary collection descriptions and contents of the summary types are described altogether in a nested structure, whereby the summary collection can described based on different summary types or based on different contents among the same summary type.
Claim 34
Dependent Claim
59 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 20 , wherein the feature types for feature collection descriptions and contents of the feature types are described altogether in a nested structure, whereby the feature collection can be described based on different feature types, or based on different contents among the same feature type.
Claim 35
Dependent Claim
59 words
A compressed or uncompressed audio video data feature collection description scheme according to claim 17 , wherein the feature types for feature collection descriptions and contents of the feature types are described altogether in a nested structure, whereby the feature collection can be described based on different feature types, or based on different contents among the same feature type.
References Cited (Backward Citations)
US5737308A
Cited
US6199076B1
Cited
US5864870A
Cited
US6714909B1
Cited
US6236395B1
Cited
US6411724B1
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2010-04-30 | 2010-10-30 | 2011-05-01 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2014-04-30 | 2014-10-30 | 2015-05-01 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2018-04-30 | 2018-10-30 | 2019-05-01 | $7700.00 | Window Closed / Lapsed |