Back to results
US 9,792,927 B2Granted
Apparatuses and methods for multi-channel signal compression during desired voice activity detection
AssigneeKopin Corporation
InventorDashen Fan
Life of this patent
Estimating the term…
Abstract
Apparatuses and methods are described to identify desired audio. A first input of an apparatus is configured to receive a main signal. A second input of the apparatus is configured to receive a reference signal. A normalizer is configured to normalize a compressed main signal by a compressed reference signal to create a normalized main signal. A single channel normalized voice threshold comparator is configured to receive as an input the normalized main signal and to output a desired voice activity detection signal.
Claims45
An apparatus to identify desired audio, comprising:
- a first signal compressor, the first signal compressor is configured to receive a main acoustic signal and to output a compressed main acoustic signal;
- a second signal compressor, the second signal compressor is configured to receive a reference acoustic signal and to output a compressed reference acoustic signal;
- a normalizer, the normalizer is configured to normalize the compressed main acoustic signal by the compressed reference acoustic signal to create a normalized main signal;
- and
- a single channel normalized voice threshold comparator (SC-NVTC), the SC-NVTC is configured to receive as an input the normalized main signal and to output a desired voice activity detection signal.
2 more elements
A method to identify desired audio, comprising:
- normalizing a compressed main acoustic signal by a compressed reference acoustic signal to form a normalized compressed main acoustic signal;
- inputting the normalized compressed main acoustic signal into a single channel normalized voice threshold comparator (SC-NVTC);
- and
- outputting a desired voice activity detection signal from the SC-NVTC.
1 more element
An apparatus to identify desired audio, comprising:
- a data processing system, the data processing system is configured to process acoustic signals;
- and
- a computer readable medium containing executable computer program instructions, which when executed by the data processing system, cause the data processing system to perform a method comprising:
- normalizing a compressed main acoustic signal by a compressed reference acoustic signal to form a normalized compressed main acoustic signal;
- inputting the normalized compressed main acoustic signal into a single channel normalized voice threshold comparator (SC-NVTC);
- and
- outputting a desired voice activity detection signal from the SC-NVTC.
4 more elements
An apparatus to identify desired audio, comprising:
- means for normalizing a compressed main acoustic signal;
- means for outputting a desired voice activity signal from a single channel normalized voice threshold comparator.
An apparatus to identify desired audio, comprising:
- a first input, the first input is configured to receive a main acoustic signal;
- a second input, the second input is configured to receive a reference acoustic signal;
- a normalizer, the normalizer is configured to normalize a compressed main acoustic signal by a compressed reference acoustic signal to create a normalized main acoustic signal;
- a single channel normalized voice threshold comparator (SC-NVTC), the SC-NVTC is configured to receive as an input the normalized main acoustic signal and to output a desired voice activity detection signal;
- a first signal compressor, the first signal compressor is configured to output the compressed main acoustic signal;
- and
- a first short-term power detector, an output of the first short-term power detector is input into the first signal compressor, wherein the first short-term power detector outputs approximately an instantaneous power of a signal on its input.
4 more elements
An apparatus to identify desired audio, comprising:
- a first input, the first input is configured to receive a main acoustic signal;
- a second input, the second input is configured to receive a reference acoustic signal;
- a normalizer, the normalizer is configured to normalize a compressed main acoustic signal by a compressed reference acoustic signal to create a normalized main acoustic signal;
- a single channel normalized voice threshold comparator (SC-NVTC), the SC-NVTC is configured to receive as an input the normalized main acoustic signal and to output a desired voice activity detection signal;
- a second signal compressor, the second signal compressor is configured to output the compressed reference acoustic signal;
- and
- a second short-term power detector, an output of the second short-term power detector is input into the second signal compressor, wherein the second short-term power detector outputs approximately an instantaneous power of a signal on its input.
4 more elements
An apparatus to identify desired audio, comprising:
- a first input, the first input is configured to receive a main acoustic signal;
- a second input, the second input is configured to receive a reference acoustic signal;
- a normalizer, the normalizer is configured to normalize a compressed main acoustic signal by a compressed reference acoustic signal to create a normalized main signal;
- a single channel normalized voice threshold comparator (SC-NVTC), the SC-NVTC is configured to receive as an input the normalized main signal and to output a desired voice activity detection signal;
- a threshold value;
- and
- logic, the SC-NVTC is configured to receive as an input the normalized main signal, the SC-NVTC creates a long-term normalized power estimate from the normalized main signal, the logic to utilize the threshold value, the long-term normalized power estimate and the normalized main signal to output a desired voice activity detection signal.
4 more elements
Dependencies are inferred from the claim text.