Environment adjusted speaker identification
AssigneeMicrosoft Technology Licensing, LLC
InventorAndrew William Lovitt
Life of this patent
Estimating the term…
Abstract
A system estimates environment-specific alterations of a user sound received at the system. The system modifies the received user sound to formulate a modified user sound by at least compensating for the audio modifications and/or formulates an expected audio model of a user by modifying a stored user-dependent audio model of the user with the audio modification. The system is also capable of estimating whether the received user sounds is from a particular user by use of a corresponding user-dependent audio model.
Claims20
A method, implemented by one or more hardware processors of a continuing system, for improving voice identification by modifying a sound file based on environmental conditions where the computing system is located, the method comprising:
- using one or more sensors of the computing system to identify environmental conditions that affect acoustic properties in an environment where the computing system is located;
- identifying audio modifications that are associated with the acoustic properties that affect sound generated in the environment and that is received at the computing system, wherein the one more hardware processors identify at least one of the audio modifications by generating an estimation regarding how the sound changes between a time when the sound is generated and a time when the sound is received by the one or more sensors;
- using the one or more sensors to receive a user sound that is caused by a particular user and that is affected by the environmental conditions before being received at the computing system;
- and
- formulating an expected audio model of a user by modifying a stored user-dependent audio model with the audio modifications.
A method, implemented by one or more hardware processors of a computing system, for improving voice identification by modifying sound based on environmental conditions where the computing system is located, the method comprising:
- using one or more sensors of the computing system to identify environmental conditions that affect acoustic properties in an environment where the computing system is located;
- identifying audio modifications that are associated with the acoustic properties that affect sound generated in the environment and that is received at the computing system, wherein the one or more hardware processors identify at least one of the audio modifications by generating an estimation regarding how the sound changes between a time when the sound is generated and a time when the sound is received by the one or more sensors;
- using the one or more sensors to receive a user sound that is caused by a particular user and that is affected by the environmental conditions before being received at the computing system;
- and
- modifying the received user sound to formulate a modified user sound by at least compensating for the audio modifications.
One or more hardware storage devices having stored thereon computer-executable instructions that are executable by one or more processors of a computing system, to cause the computing system to perform a method for improving voice identification by modifying sound based on environmental conditions, the method comprising:
- using one or more sensors of the computing system to identify environmental conditions that affect acoustic properties in an environment where the computing system is located;
- identifying audio modifications that are associated with the acoustic properties that affect sound generated in the environment and that is received by the one or more sensors of the computing system, where the one or more processors identify at least one of the audio modifications by generating an estimation regarding how the sound changes between a time when the sound is generated and a time when the sound is received by the one or more sensors;
- using the one or more sensors to receive a user sound that is caused by a particular user and that is affected by the environmental conditions before being received at the computing system;
- at least one of (1) modifying the received user sound to formulate a modified user sound by at least compensating for the audio modifications or (2) formulating an expected audio model of a user by modifying a stored user-dependent audio model of the user with the audio modifications;
- and
- estimating whether the user associated with the user-dependent audio model is the same as the particular user that generated the user sound based on a comparison of at least (a) the user sound with the expected audio model or (b) the stored user-dependent audio model with the modified user sound.
Dependencies are inferred from the claim text.