Back to results
US 10,818,308 B1Granted
Speech characteristic recognition and conversion
AssigneeSnap Inc.
InventorWei Chu
Life of this patent
Estimating the term…
Abstract
Systems, devices, media, and methods are presented for converting sounds in an audio stream. The systems and methods receive an audio conversion request initiating conversion of one or more sound characteristics of an audio stream from a first state to a second state. The systems and methods access an audio conversion model associated with an audio signature for the second state. The audio stream is converted based on the audio conversion model and an audio construct is compiled from the converted audio stream and a base audio segment. The compiled audio construct is presented at a client device.
Claims20
A method, comprising:
- receiving an audio conversion request configured to initiate conversion of one or more sound characteristics of an audio stream from a first state to a second state, the first state comprising spoken words and the second state comprising sung lyrics;
- generating, using an audio signature for the second state, an audio conversion model based on an image of a musical score;
- converting the audio stream based on the audio conversion model that is generated based on the image or text of the musical score, the converting comprising:
- determining that a first segment comprising acoustic syllables of the spoken words in audio stream is of an insufficient duration to determine a pitch value for the segment;
- in response to determining that the segment is of the insufficient duration to determine the pitch value for the segment, merging a set of additional segments comprising acoustic syllables of the spoken words with the first segment to form a merged segment that is of a sufficient duration to determine the pitch value of the merged segment;
- compiling an audio construct from the converted audio stream and a base audio segment, the compiling comprising aligning a first syllable of the acoustic syllables to a plurality of beats;
- and
- causing presentation of the compiled audio construct at a client device.
5 more elements
A system, comprising:
- one or more processors;
- and
- a machine-readable non-transitory processor-readable storage medium storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
- receiving an audio conversion request configured to initiate conversion of one or more sound characteristics of an audio stream from a first state to a second state, the first state comprising spoken words and the second state comprising sung lyrics;
- generating, using an audio signature for the second state, an audio conversion model based on an image of a musical score;
- converting the audio stream based on the audio conversion model that is generated based on the image or text of the musical score, the converting comprising:
- determining that a first segment comprising acoustic syllables of the spoken words in audio stream is of an insufficient duration to determine a pitch value for the segment;
- in response to determining that the segment is of the insufficient duration to determine the pitch value for the segment, merging a set of additional segments comprising acoustic syllables of the spoken words with the first segment to form a merged segment that is of a sufficient duration to determine the pitch value of the merged segment;
- compiling an audio construct from the converted audio stream and a base audio segment, the compiling comprising aligning a first syllable of the acoustic syllables to a plurality of beats;
- and
- causing presentation of the compiled audio construct at a client device.
8 more elements
A non-transitory processor-readable storage medium storing processor executable instructions that, when executed by a processor of a machine, cause the machine to perform operations comprising:
- receiving an audio conversion request configured to initiate conversion of one or more sound characteristics of an audio stream from a first state to a second state, the first state comprising spoken words and the second state comprising sung lyrics;
- generating, using an audio signature for the second state, an audio conversion model based on an image of a musical score;
- converting the audio stream based on the audio conversion model that is generated based on the image or text of the musical score, the converting comprising:
- determining that a first segment comprising acoustic syllables of the spoken words in audio stream is of an insufficient duration to determine a pitch value for the segment;
- in response to determining that the segment is of the insufficient duration to determine the pitch value for the segment, merging a set of additional segments comprising acoustic syllables of the spoken words with the first segment to form a merged segment that is of a sufficient duration to determine the pitch value of the merged segment;
- compiling an audio construct from the converted audio stream and a base audio segment, the compiling comprising aligning a first syllable of the acoustic syllables to a plurality of beats;
- and
- causing presentation of the compiled audio construct at a client device.
5 more elements
Dependencies are inferred from the claim text.