Abstract: A method includes obtaining a plurality of training samples, determining a minimum integer fixed-bit width representing a maximum quantization of an automatic speech recognition (ASR) model, and training the ASR model on the plurality of training samples using a quantity of random noise. The ASR model includes a plurality of weights that each include a respective float value. The quantity of random noise is based on the minimum integer fixed-bit value. After training the ASR model, the method also includes selecting a target integer fixed-bit width greater than or equal to the minimum integer fixed-bit width, and for each respective weight of the plurality of weights, quantizing the respective weight from the respective float value to a respective integer associated with a value of the selected target integer fixed-bit width. The operations also include providing the quantized trained ASR model to a user device.

Abstract: A method includes obtaining a plurality of training samples that each include a respective speech utterance and a respective textual utterance representing a transcription of the respective speech utterance. The method also includes fine-tuning, using quantization and sparsity aware training with native integer operations, a pre-trained automatic speech recognition (ASR) model on the plurality of training samples. Here, the pre-trained ASR model includes a plurality of weights and the fine-tuning includes pruning one or more weights of the plurality of weights using a sparsity mask and quantizing each weight of the plurality of weights based on an integer with a fixed-bit width. The method also includes providing the fine-tuned ASR model to a user device.

Abstract: A method includes obtaining a plurality of training samples, determining a minimum integer fixed-bit width representing a maximum quantization of an automatic speech recognition (ASR) model, and training the ASR model on the plurality of training samples using a quantity of random noise. The ASR model includes a plurality of weights that each include a respective float value. The quantity of random noise is based on the minimum integer fixed-bit value. After training the ASR model, the method also includes selecting a target integer fixed-bit width greater than or equal to the minimum integer fixed-bit width, and for each respective weight of the plurality of weights, quantizing the respective weight from the respective float value to a respective integer associated with a value of the selected target integer fixed-bit width. The operations also include providing the quantized trained ASR model to a user device.

Abstract: An electronic device includes a sensor, a processor, and a memory configured to store at least one instruction executed by the processor, wherein the processor is configured to collect activity information on a user related to the electronic device by using the sensor, the collecting of the activity information including creating an amount of activity of the user for a specific goal or an activity engagement level for the specific goal by using the activity information, adjust at least one of an output time point, an output cycle, the number of outputs, or the output contents of the activity guide information for the user to an activity guide parameter at least based on the amount of activity or the activity engagement level, and output the activity guide information created by using the adjusted activity guide parameter through an output device operatively connected to the processor.

Abstract: An electronic device includes a sensor, a processor, and a memory configured to store at least one instruction executed by the processor, wherein the processor is configured to collect activity information on a user related to the electronic device by using the sensor, the collecting of the activity information including creating an amount of activity of the user for a specific goal or an activity engagement level for the specific goal by using the activity information, adjust at least one of an output time point, an output cycle, the number of outputs, or the output contents of the activity guide information for the user to an activity guide parameter at least based on the amount of activity or the activity engagement level, and output the activity guide information created by using the adjusted activity guide parameter through an output device operatively connected to the processor.