Abstract: Certain aspects of the present disclosure provide techniques for efficient broadcasted residual machine learning. An input tensor comprising a frequency dimension and a temporal dimension is received, and the input tensor is processed with a first convolution operation to generate a multidimensional intermediate feature map comprising the frequency dimension and the temporal dimension. The multidimensional intermediate feature map is converted to a one-dimensional intermediate feature map in the temporal dimension using a frequency dimension reduction operation, and the one-dimensional intermediate feature map is processed using a second convolution operation to generate a temporal feature map. The temporal feature map is expanded to the frequency dimension using a broadcasting operation to generate a multidimensional output feature map, and the multidimensional output feature map is augmented with the multidimensional intermediate feature map via a first residual connection.

Abstract: System and method for operating an always-on ASR (automatic speech recognition) system by selecting target keywords and continuously detecting the selected target keywords in voice commands in a mobile device are provided. In the mobile device, a processor is configured to collect keyword candidates, collect usage frequency data for keywords in the keyword candidates, collect situational usage frequency data for the keywords in the keyword candidates, select target keywords from the keyword candidates based on the usage frequency data and the situational usage frequency data, and detect one or more of the target keywords in a voice command using continuous detection of the target keywords.

Abstract: A mobile terminal and a method of controlling the mobile terminal are disclosed. According to the embodiment of the present invention, when a touching event for a touch input to a touch screen is generated, a writing sound source corresponding to the generated touching event is selected from a memory, and a feedback sound is output in real time, that is generated by changing a sound property of the writing sound source that is selected according to a pressure of a touch applied to the touch screen and a moving speed of the touch. This enables the user to feel as if he/she performed the writing input in the actual analog environment, and provides the use with a yearning for the analog environment and a pleasure to experience it.

Abstract: A mobile terminal and a method of controlling the mobile terminal are disclosed. According to the embodiment of the present invention, when a touching event for a touch input to a touch screen is generated, a writing sound source corresponding to the generated touching event is selected from a memory, and a feedback sound is output in real time, that is generated by changing a sound property of the writing sound source that is selected according to a pressure of a touch applied to the touch screen and a moving speed of the touch. This enables the user to feel as if he/she performed the writing input in the actual analog environment, and provides the use with a yearning for the analog environment and a pleasure to experience it.