Abstract: The present disclosure relates to an electric toothbrush, including a shell, a toothbrush head, a first spiral bevel gear, a second spiral bevel gear, and a drive motor. The toothbrush head is connected with the second spiral bevel gear; the first spiral bevel gear and the second spiral bevel gear are in transmission connection; the first spiral bevel gear is arranged above the drive motor and is in transmission connection with the drive motor; a central axis of the first spiral bevel gear is perpendicular to a central axis of the second spiral bevel gear; and the drive motor has a stepped shaft connected to the first spiral bevel gear. The first spiral bevel gear and the second spiral bevel gear are used to drive the toothbrush head to rotate, so that the drive is steady and the transmission efficiency is high. A main shaft of the drive motor adopts the stepped shaft, which can improve the transmission efficiency, so that the transmission is steadier.

Abstract: Techniques for performing spoken language understanding (SLU) processing are described. An SLU component may include an audio encoder configured to perform an audio-to-text processing task and an audio-to-NLU processing task. The SLU component may also include a joint decoder configured to perform the audio-to-text processing task, the audio-to-NLU processing task and a text-to-NLU processing task. Input audio data, representing a spoken input, is processed by the audio encoder and the joint decoder to determine NLU data corresponding to the spoken input.

Abstract: Techniques for performing spoken language understanding (SLU) processing are described. An SLU component may include an audio encoder configured to perform an audio-to-text processing task and an audio-to-NLU processing task. The SLU component may also include a joint decoder configured to perform the audio-to-text processing task, the audio-to-NLU processing task and a text-to-NLU processing task. Input audio data, representing a spoken input, is processed by the audio encoder and the joint decoder to determine NLU data corresponding to the spoken input.