Translating a voice signal into an output representation of discrete tones
AssigneeNellymoser, Inc.
InventorsJohn Puterbaugh, Eric J. Puterbaugh, Peter Velikonja, Robert Baxter
Life of this patent
Estimating the term…
Abstract
A system and method for creating a ring tone for an electronic device takes as input a phrase sung in a human voice and transforms it into a control signal controlling, for example, a ringer on a cellular telephone. Time-varying features of the input signal are analyzed to segment the signal into a set of discrete notes and assigning to each note a chromatic pitch value. The set of note start and stop times and pitches are then translated into a format suitable for controlling the device.
Claims19
An apparatus for generating an identification signal comprising:
- a voice signal receiver;
- and
- a translator having as its input a voice signal received by said voice signal receiver and having as its output a representation of discrete tones where an audio presentation of said discrete tones would be human-recognizable as a translation of said voice signal;
- wherein said translator further comprises a feature estimation module to determine values for at least one time-varying feature of said input signal;
- wherein said translator further comprises a segmented module responsive to output of said feature estimation module and energy of said input to segment said input signal into notes and a pitch assignment module responsive to signal energy in each segment output by said segmentation module;
- wherein said pitch assignment module comprises an intranote pitch assignment subsystem and an internote pitch assignment subsystem;
- and
- wherein said intranote pitch assignment subsystem determines pitch in response to time-domain energy, voicing probability, median, and mode of each said segment output by said segmentation module.
A method for generating an identification signal, comprising:
- accepting as input a voice signal;
- translating said voice signal to a representation of discrete tones, where an audio presentation of said discrete tones would be human-recognizable as a translation of said voice signal;
- determining values for at least one time-varying feature of said voice signal;
- in response to the determined values and energy of said voice signal, segmenting said voice signal into notes;
- and
- in response to signal energy in each segment, determining pitch assignment including determining intranote pitch assignment and determining internote pitch assignment;
- wherein determining intranote pitch assignment comprises determining pitch in response to time-domain energy, voicing probability, median, and mode of each said segment.
Dependencies are inferred from the claim text.