Method of data reduction in a speech recognition

Claim 2

In a speech processing system, wherein speech is represented as a sequence of original frames, a method for reducing the sequence of original frames into a reduced set of representative frames comprising the steps of: storing a plurality of original frames from the sequence; combining said stored original frames into a plurality of representative frames; generating, for each representative frame, a distortion measure corresponding to the distance between each said representative frame and said original frames combined therein; comparing each said distortion measure to a predetermined distortion threshold; and determining a set of a minimum number of said representative frames representing said stored original frames and each representative frame having a generated distortion measure less than said predetermined distortion threshold.

Claim 3

The method of claim 1, wherein said set of representative frames represents every original frame in the series.

Claim 4

The method of claim 1, further including the step of invalidating all representative frames designated by original frames m through n, where m<n, if said associated distortion measure from a previously determined representative frame designated by original frames i through j, where i≧m, j≦n and i<j, exceeds said distortion threshold by a predetermined constant.

Claim 5

In a speech processing system, wherein speech is represented as a sequence of original frames, a method for reducing the sequence of original frames into a reduced set of representative frames comprising the steps of: forming cluster paths ending at each original frame in the sequence, said frames in sequence designated m through n, where m<n, each said cluster path composed of a series of combined original frames; forming an additional representative frame by combining frames j through n+1, wherein m<j<n and j is an integer designating a frame in the series, said forming of an additional representative frame including the steps of: generating, for said additional representative frame, a distortion measure corresponding to the distance between said additional representative frame and original frames combined therein and comparing said distortion measure to a predetermined distortion threshold; and appending said additional representative frame to said previously formed cluster paths if said distortion measure does not exceed said distortion threshold, whereby the resultant reduced set of representative frames is comprises of said additional representative frame appended to said cluster path formed at frame j-1.

Claim 6

In a speech processing system, wherein speech is represented as a sequence of original frames, a method for reducing the sequence of original frames into a reduced set of representative frames comprising the steps of: forming cluster paths ending at each original frame in the sequence, said frames in sequence designated m through n, where m<n, each said cluster path composed of a series of combined original frames; forming an additional representative frame by combining frames j through n+1, wherein m<j<n and j is an integer designating a frame in the series, said forming of an additional representative frame including the steps of: generating, for said additional representative frame, a distortion measure corresponding to the distance between said additional representative frame and original frames combined therein and comparing said distortion measure to a predetermined distortion threshold; and appending said additional representative frame to said previously formed cluster paths if said distortion measure does not exceed said distortion threshold, whereby the resultant reduced set of representative frames is comprises of said additional representative frame appended to said cluster path formed at frame j-1.

Claim 7

The method of claim 1 or 4, wherein each representative frame includes at least a predetermined minimum number of original frames.

Claim 8

The method of claim 1 or 4, wherein each representative frame includes no more than a predetermined maximum number of original frames.

Claim 9

The method of claim 1 or 4, further including the step of recording the number of original frames combined in each representative frame in the set.

Claim 10

The method of claim 1 or 4, further including the step of recording said distortion measure associated with each representative frame in the set.

Claim 11

The method of claim 1 or 4, wherein at least one said representative frame in the set includes a single frame.

Claim 12

The method of claim 4, further including the step of invalidating at least one said cluster path when another cluster path is determined to have fewer representative frames.

Claim 13

The method of claim 1 or 4, further including the step of designating one or more representative frames in the set as an output frame.

Claim 14

The method of claim 1 or 4, further including the step of connecting said representative frames in the set with pointers.

Claim 15

The method of claim 1 or 4, including the step of generating a peak distortion measure.

Claim 16

The method of claim 1 or 4, further including the step of determining a convergence reference frame.

Claim 17

The method of claim 4, further including the steps of comparing said distortion measures associated with two cluster paths having the same number of representative frames.

Claim 18

The method of claim 4, further including the step of determining a distortion measure associated with the set of representative frames.

Claim 19

The method of claim 4, further including the step of selecting representative frames from one end of said sequence to the other end of said sequence.

Claim 20

In a speech processing system, wherein speech is represented as a sequence of original frames, an arrangement for reducing the sequence of original frames into a reduced set of representative frames comprising: means for storing a plurality of original frames from the sequence; means for combining said stored original frames into a plurality of representative frames; means for generating, for each representative frame, a distortion measure corresponding to the distance between each said representative frame and said original frames combined therein; means for comparing each said distortion measure to a predetermined distortion threshold; and means for determining a set of a minimum number of said representative frames representing said stored original frames, each representative frame having a generated distortion measure less than said predetermined distortion threshold.

Claim 21

In a speech processing system, wherein speech is represented as a sequence of original frames, an arrangement for reducing the sequence of original frames into a reduced set of representative frames comprising: means for storing a plurality of original frames from the sequence; means for combining said stored original frames into a plurality of representative frames; means for generating, for each representative frame, a distortion measure corresponding to the distance between each said representative frame and said original frames combined therein; means for comparing each said distortion measure to a predetermined distortion threshold; and means for determining a set of a minimum number of said representative frames representing said stored original frames, each representative frame having a generated distortion measure less than said predetermined distortion threshold.

Claim 22

The arrangement of claim 18, wherein said set of representative frames represents every original frame in the series.

Claim 23

The arrangement of claim 18, further including means for invalidating all representative frames designated by original frames m through n, where m<n, if said associated distortion measure from a previously determined representative frame designated by original frames i through j, where i≧m, j≦n and i<j, exceeds said distortion threshold by a predetermined constant.

Claim 24

In a speech processing system, wherein speech is represented as a sequence of original frames, a method for reducing the sequence of original frames into a reduced set of representative frames comprising: means for forming cluster paths ending at each original frame in the sequence, said frames in sequence designated m through n, where m<n, each said cluster path composed of a series of combined original frames; means for forming an additional representative frame by combining frames j through n+1, where m<j<n and j is an integer designating a frame in the series, said means for forming of an additional representative frame including: means for generating, for said additional representative frame, a distortion measure corresponding to the distance between said additional representative frame and the original frames combined therein and means for comparing said distortion measure to a predetermined distortion threshold; and means for appending said additional representative frame to said previously formed cluster paths is said distortion measure does not exceed said distortion threshold, whereby the resultant reduced set of representative frames is comprised of said additional representative frame appended to said cluster path formed at frame j-1.

Claim 25

In a speech processing system, wherein speech is represented as a sequence of original frames, a method for reducing the sequence of original frames into a reduced set of representative frames comprising: means for forming cluster paths ending at each original frame in the sequence, said frames in sequence designated m through n, where m<n, each said cluster path composed of a series of combined original frames; means for forming an additional representative frame by combining frames j through n+1, where m<j<n and j is an integer designating a frame in the series, said means for forming of an additional representative frame including: means for generating, for said additional representative frame, a distortion measure corresponding to the distance between said additional representative frame and the original frames combined therein and means for comparing said distortion measure to a predetermined distortion threshold; and means for appending said additional representative frame to said previously formed cluster paths is said distortion measure does not exceed said distortion threshold, whereby the resultant reduced set of representative frames is comprised of said additional representative frame appended to said cluster path formed at frame j-1.

Claim 26

The arrangement of claim 18 or 21, wherein each representative frame includes at least a predetermined minimum number of original frames.

Claim 27

The arrangement of claim 18 or 21, wherein each representative frame includes no more than a predetermined maximum number of original frames.

Claim 28

The arrangement of claim 18 or 21, further including means for recording the number of original frames combined in each representative frame in the set.

Claim 29

The arrangement of claim 18 or 21, further including means for recording said distortion measure associated with each representative frame in the set.

Claim 30

The arrangement of claim 18 or 21, wherein at least one said representative frame in the set includes a single frame.

Claim 31

The arrangement of claim 21, further including means for invalidating at least one said cluster path when another cluster path is determined to have fewer representative frames.

Claim 32

The arrangement of claim 18 or 21, further including means for designating one or more representative frames in the set as an output frame.

Claim 33

The arrangement of claim 18 or 21, further including means for connecting said representative frames in the set with pointers.

Claim 34

The arrangement of claim 18 or 21, including means for generating a peak distortion measure.

Claim 35

The arrangement of claim 18 or 21, further including mean for determining a convergence reference frame.

Claim 36

The arrangement of claim 21, further including means for comparing said distortion measures associated with two cluster paths having the same number of representative frames.

Claim 37

The arrangement of claim 21, further including means for determining a distortion measure associated with the set of representative frames.

Claim 38

The arrangement of claim 21, further including means for selecting representative frames from one end of said sequence to the other end of said sequence.