Method for encoding multiple microphone signals into a source-separable audio signal for network transmission and an apparatus for directed source separation

Abstract

A method is provided for encoding multiple microphone signals into a composite source-separable audio (SSA) signal, conducive for transmission over a voice network. The embodiments enable the processing of source separation of the target voice signal from its ambient sound to be performed at any point in the voice communication network, including the internet cloud. A multiplicity of processing is possible over the SSA signal, based on the intended voice application. The level of processing is adapted with the availability of the processing power at the chosen processing node in the network in one embodiment. An apparatus for separating out the target source voice from its ambient sound is also provided. The apparatus includes a directed source separation (DSS) unit, which processes the two virtual microphone signals in the SSA representation, to generate a new SSA signal including the enhanced target voice and the enhanced ambient noise.

What is claimed is: 
     
       1. A method for network transmission of voice captured through a plurality of microphones spatially disposed in a first group and a second group, comprising:
 combining two digital audio signals into a composite source separable audio (SSA) signal, each digital audio signal of the two digital audio signals representing an independent mixture of a target source voice and an ambient noise, wherein outputs of the plurality of microphones within the first group are summed together as a first output digital audio signal of the two digital audio signals and the outputs of the plurality of microphones within the second group are summed together as a second output digital audio signal of the two digital audio signals, thereby defining a first virtual microphone and a second virtual microphone, respectively, and wherein the combining process comprises interleaving the two digital audio signals to generate the composite SSA signal; and 
 separating the two digital audio signals within the composite SSA signal into two mono audio signals by performing a first instance of directed source separation (DSS) on the composite SSA signal, the DSS comprising:
 generating one or more control signals indicating an instantaneous signal-to-noise ratio, in the composite SSA signal, between the target source voice and the ambient noise; 
 under direction of the one or more control signals, separating the target source voice of the composite SSA signal into a first mono audio signal; and 
 under direction of the one or more control signals, separating the ambient noise of the composite SSA signal into a second mono audio signal. 
 
 
     
     
       2. A method of  claim 1 , further comprising:
 separating the two audio signals within the composite SSA signal into two mono audio signals by performing directed source separation (DSS).   
     
     
       3. A method of  claim 1 , wherein the two audio signals are analog signals and the combining process comprises delaying the second audio signal and summing the a first output of a first microphone of the first group is delayed before being summed with a second output of a second audio signal with the first audio signal to generate the composite SSA signal microphone of the first group to generate the first digital audio signal. 
     
     
       4. A method of  claim 1 , wherein the composite SSA signal is intelligible for human listening without requiring any further processing. 
     
     
       5. A method of  claim 2 , comprising:
 performing a first ambient sound separation process for human listening intelligibility; and   performing a second ambient sound separation process for a machine voice application.   
     
     
       6. A method of  claim 1 , wherein a quality of ambient sound separation is traded off gracefully, depending on the an availability of processing power. 
     
     
       7. A method of  claim 1 , wherein the separating is performed in an intermediate server in a network cloud. 
     
     
       8. The method of claim 1, comprising:
 separating the two digital audio signals within the composite SSA signal into another two mono audio signals by performing a second instance of DSS on the composite SSA signal;   wherein the two mono audio signals include a first level of the ambient noise of the composite SSA signal;   wherein the other two mono audio signals include a second level of the ambient noise of the composite SSA signal;   wherein the first level is different than the second level.   
     
     
       9. The method of claim 1, wherein the separating is performed in an intermediate server in a network cloud.