# US 2012/0239391 A1 · Automatic equalization of coloration in speech recordings > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2012/0239391 A1 - Document ID: US20120239391A1 - Status: Published application - Kind: A1 - Application number: 13/047,422 - Filed: 2011-03-14 - Published: 2012-09-20 - Earliest claimed: 2011-03-14 - Assignees: Adobe Systems Incorporated - Inventors: Sven Duwenhorst; Martin Schmitz - Web page: https://patentgrep.com/patent/US20120239391A1 ## CPC - H04R 3/00: Circuits for transducers (arrangements for producing a reverberation or echo sound G10K15/08; amplifiers H03F) - H04S 2400/15: Aspects of sound capture and related signal processing for recording or reproduction - H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K) - H04S: STEREOPHONIC SYSTEMS ## Abstract Systems and methods to automatically equalize coloration in speech recordings is provided. In example embodiments, a reference spectral shape based on a reference signal is determined. An estimated spectral shape for an input signal is derived. Using the estimated spectral shape and the reference spectral shape a comparison is performed to determine gain settings. The gain settings comprise a gain value for each filter of a filter system. Using gain values associated with the gain setting, automatic equalization is performed on the input signal. ## Claims ### Claim 1 A method comprising: defining a reference spectral shape based on a reference signal; deriving an estimated spectral shape for an input signal; comparing, using one or more processors, the estimated spectral shape to the reference spectral shape to determine gain settings, the gain settings comprising a gain value for each filter of a filter system; and automatically performing equalization on the input signal using gain values associated with the gain setting. ### Claim 2 (depends on 1) The method of claim 1, further comprising normalizing the input signal based on a normalization threshold prior to driving the estimated spectral shape. ### Claim 3 (depends on 1) The method of claim 1, wherein the deriving of the estimated spectral shape comprises using a plurality of averagers to measure the input signal, each of the plurality of averagers having a different time constant. ### Claim 4 (depends on 3) The method of claim 3, further comprising comparing values of each individual band of each of the plurality of averagers to determine a measured value used to derive the estimated spectral shape. ### Claim 5 (depends on 4) The method of claim 4, wherein the comparing comprises setting a long time constant value equal to a short time constant value or mid time constant value based on the short time constant value of the mid time constant value exceeding the long time constant value. ### Claim 6 (depends on 3) The method of claim 3, wherein the deriving comprises averaging values of each of the plurality of averagers. ### Claim 7 (depends on 3) The method of claim 3, further comprising: using a short time constant averager of the plurality of averagers to determine a short time constant value; using a mid time constant averager of the plurality of averagers to determine a mid time constant value; and using a long time constant averager of the plurality of averagers to determine a long time constant value. ### Claim 8 (depends on 1) The method of claim 1, further comprising: determining whether each gain value of the gain setting exceeds a gain threshold; and based on a gain value exceeding the gain threshold, setting the gain value to the gain threshold to generate a modified gain value. ### Claim 9 (depends on 8) The method of claim 8, wherein automatically performing equalization comprises using a plurality of filters to automatically apply the gain values and the modified gain value to the input signal ### Claim 10 A system comprising: a reference model module configured to define a reference spectral shape based on a reference signal; an input model module configured to derive an estimated spectral shape for an input signal; a comparison module configured to compare, using one or more processors, the estimated spectral shape to the reference spectral shape to determine gain settings, the gain settings comprising a gain value for each filter of a filter system; and a filter system configured to automatically perform equalization on the input signal using gain values associated with the gain setting. ### Claim 11 (depends on 10) The system of claim 10, further comprising a normalizer configured to normalize the input signal based on a normalization threshold prior to driving the estimated spectral shape. ### Claim 12 (depends on 10) The system of claim 10, further comprising a plurality of averagers configured to measure the input signal, each of the plurality of averagers having a different time constant. ### Claim 13 (depends on 12) The system of claim 12, wherein the input model module is further configured to compare values of each individual band of each of the plurality of averagers to determine a measured value used to derive the estimated spectral shape. ### Claim 14 (depends on 10) The system of claim 10, further comprising a gain controller configured to determine whether each gain value of the gain setting exceeds a gain threshold, and based on a gain value exceeding the gain threshold, setting the gain value to the gain threshold to generate a modified gain value. ### Claim 15 (depends on 10) The system of claim 10, wherein the plurality of averagers comprises a short time constant averager, a mid time constant averager, and a long time constant averager. ### Claim 16 A non-transitory machine-readable storage medium in communication with at least one processor, the machine-readable storage medium storing instructions which, when executed by the at least one processor, performs a method comprising: defining a reference spectral shape based on a reference signal; deriving an estimated spectral shape for an input signal; comparing, using one or more processors, the estimated spectral shape to the reference spectral shape to determine gain settings, the gain settings comprising a gain value for each filter of a filter system; and automatically performing equalization on the input signal using gain values associated with the gain setting. ### Claim 17 (depends on 16) The non-transitory machine-readable medium of claim 16, wherein the method further comprises normalizing the input signal based on a normalization threshold prior to driving the estimated spectral shape. ### Claim 18 (depends on 16) The non-transitory machine-readable medium of claim 16, wherein the deriving of the estimated spectral shape comprises using a plurality of averagers to measure the input signal, each of the plurality of averagers having a different time constant. ### Claim 19 (depends on 18) The non-transitory machine-readable medium of claim 18, wherein the method further comprises comparing values of each individual band of each of the plurality of averagers to determine a measured value used to derive the estimated spectral shape. ### Claim 20 (depends on 19) The non-transitory machine-readable medium of claim 19, wherein the method further comprises: determining whether each gain value of the gain setting exceeds a gain threshold; and based on a gain value exceeding the gain threshold, setting the gain value to the gain threshold to generate a modified gain value.