Abstract: A wireless audio device including two or more earpieces is provided.

Abstract: A wearable electronic device may include at least first and second microphones disposed in a housing to face outside and inside a user's ear, a speaker, a processor, and memory storing instructions. The instructions, when executed, cause the wearable electronic device to output a first audio signal through the speaker, obtain a second audio signal by mixing the first audio signal and a noise signal through the at least one second microphone, based on a result of analyzing the second audio signal, adjust a gain of active noise canceling circuitry and a gain of at least one of transparency circuitry or sound source circuitry, and output, through the speaker, a third audio signal obtained by mixing an output of the gain-adjusted active noise canceling circuitry and an output of the gain-adjusted at least one of the transparency circuitry or the sound source circuitry.

Abstract: An electronic device includes memory storing instructions; and at least one processor; wherein the instructions, when executed by the at least one processor, cause the electronic device to identify a first audio signal including a first plurality of audio sources; identify a first audio source, corresponding to at least one first type, from the first audio signal; based on at least one configuration value corresponding to each of the at least one first type, perform signal processing on the first audio source; generate a second audio signal based on at least a portion of a remaining signal of the first audio signal excluding the first audio source, and the signal-processed first audio source; and output the second audio signal.

Abstract: Proposed are a deep neural network-based non-autoregressive voice synthesizing method and a system therefor. A deep neural network-based non-autoregressive voice synthesizing system according to an embodiment may comprise: a voice feature vector column synthesizing unit which constitutes a non-recursive deep neural network based on multiple decoders, and gradually produces a voice feature vector column through the multiple decoders from a template including temporal information of a voice; and a voice reconstituting unit which transforms the voice feature vector column into voice data, wherein the voice feature vector column synthesizing unit produces a template input, and produces a voice feature vector column by adding, to the template input, sentence data refined through an attention mechanism.

Abstract: Proposed are a deep neural network-based non-autoregressive voice synthesizing method and a system therefor. A deep neural network-based non-autoregressive voice synthesizing system according to an embodiment may comprise: a voice feature vector column synthesizing unit which constitutes a non-recursive deep neural network based on multiple decoders, and gradually produces a voice feature vector column through the multiple decoders from a template including temporal information of a voice; and a voice reconstituting unit which transforms the voice feature vector column into voice data, wherein the voice feature vector column synthesizing unit produces a template input, and produces a voice feature vector column by adding, to the template input, sentence data refined through an attention mechanism.