Abstract: An exemplary implementation includes a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations including receiving a first audio data, processing the first audio data by a first signal separation algorithm, in response to an output of the first signal separation algorithm satisfying at least one parameter, outputting the processed first audio data. In response to the output of the first signal separation algorithm not satisfying the at least one parameter selecting a second signal separation algorithm, which is different than the first signal separation algorithm, receiving a second audio data subsequent in time to receiving the first audio data, processing the second audio data by the second signal separation algorithm, and outputting the processed second audio data.

Abstract: A system includes a first module and a second module. The first module may be configured to perform operations including generating voice data based on an input audio, anonymizing the voice data by applying a first audio transformation, and transmitting the anonymized voice data to a first remote ASR module for generating speech recognition data. The second module may be configured to perform operations including separating the input audio into a first data and a second data, anonymizing the first data by applying a second audio transformation to the first data, generating an anonymized audio data by combining the anonymized first data and the second data, and transmitting the anonymized audio data to a second remote ASR module for generating speech recognition data.

Abstract: An electronic device includes a far-field voice (FFV) processor including a source selection module. The source selection module receives a set of audio signals and determines, for each audio stream, whether the audio stream is relevant to an application. The source selection module receives several separate probability computations, with each probability computation providing a probability of the presence of a particular characteristic. Additionally, the source selection module receives one or more applications as well relevance information (e.g., one or relevant characteristics) associated with the one or applications. The source selection module can used respective probabilities to determine if one or more characteristics are present in an audio signal, and compare the characteristic(s) to the relevance information for the application. Using this information, the source selection module can determine, for each audio signal, to which respective application the audio stream is relevant.