Method and system to identify, quantify, and display acoustic transformational structures in speech
OwnerDaniel M. Begelinventor
Life of this patent
Estimating the term…
Abstract
The invention for processing speech that is described herein measures the periodic changes of multiple acoustic features in a digitized utterance without regard for lexical, sublexical, or prosodic features. These measurements of periodic, simultaneous changes of multiple acoustic features are assembled into transformational structures. Various types of transformational structures are identified, quantified, and displayed by the invention. The invention is useful for the study of such speaker characteristics as cognitive, emotional, linguistic, and behavioral functioning, and may be employed in the study of other phenomena of interest to the user.
Claims24
1) A method for identifying a first-order transformational structure in human speech, the method comprising:
- a) computing with a computer the values of at least two acoustic features of a digitized utterance at a plurality of equal periodic intervals throughout the digitized utterance,
- b) computing with a computer transitions between successive computed values of the at least two acoustic features of the digitized utterance at the plurality of equal periodic intervals throughout the digitized utterance,
- c) selecting with a computer those of the computations of the transitions between the successive computed values that derive from spoken portions of the digitized utterance, and
- d) composing with a computer a first-order transformational structure by juxtaposing the selected computations of the transitions between the successive computed values of at least two of the at least two acoustic features,
- wherein the first-order transformational structure contains a temporal sequence of data points, each data point of which is defined by at least two values corresponding to the at least two of the at least two acoustic features, describing the simultaneous transitions of the at least two of the at least two acoustic features at the plurality of equal periodic intervals of the spoken portions of the digitized utterance.
7) A system for identifying a first-order transformational structure in human speech, the system comprising:
- a) a computerized component for receiving a digitized utterance,
- b) a computational component for computing the values of at least two acoustic features of the digitized utterance at a plurality of equal periodic intervals throughout the digitized utterance,
- c) a computational component for computing transitions between successive computed values of the at least two acoustic features of the digitized utterance at the plurality of equal periodic intervals throughout the digitized utterance,
- d) computerized component for selecting those computations of the transitions between the successive computed values that derive from spoken portions of the digitized utterance, and
- e) a computerized component for composing a first-order transformational structure by juxtaposing the selected computations of the transitions between the successive computed values of at least two of the at least two acoustic features,
- wherein the first-order transformational structure contains a temporal sequence of data points, each data point of which is defined by at least two values corresponding to the at least two of the at least two acoustic features, describing the simultaneous transitions of the at least two of the at least two acoustic features at the plurality of equal periodic intervals of the spoken portions of the digitized utterance.
16) A computer readable medium having stored therein computer readable instructions which when executed cause a computer to perform a set of operations for identifying a first-order transformational structure in human speech, the set of operations comprising:
- a) computing the values of at least two acoustic features of a digitized utterance at a plurality of equal periodic intervals throughout the digitized utterance,
- b) computing transitions between successive computed values of the at least two acoustic features of the digitized utterance at the plurality of equal periodic intervals throughout the digitized utterance,
- c) selecting those of the computations of the transitions between the successive computed values that derive from spoken portions of the digitized utterance, and
- d) composing a first-order transformational structure by juxtaposing the selected computations of the transitions between the successive computed values of at least two of the at least two acoustic features,
- wherein the first-order transformational structure contains a temporal sequence of data points, each data point of which is defined by at least two values corresponding to the at least two of the at least two acoustic features, describing the simultaneous transitions of the at least two of the at least two acoustic features at the plurality of equal periodic intervals of the spoken portions of the digitized utterance.
Dependencies are inferred from the claim text.