Abstract: A method for a user device, including receiving a first acoustic input of a user speaking a wake-up word in the target language; providing a first acoustic feature derived from the first acoustic input to an acoustic model stored on the user device to obtain a first sequence of speech units corresponding to the wake-up word spoken by the user in the target language, the acoustic model trained on a corpus of training data in a source language different than the target language; receiving a second acoustic input including the wake-up word in the target language; providing a second acoustic feature derived from the second acoustic input to the acoustic model to obtain a second sequence of speech units corresponding to the wake-up word in the target language; and comparing the first and second sequences of speech units to recognize the wake-up word in the target language.

Abstract: A method for a user device, including receiving a first acoustic input of a user speaking a wake-up word in the target language; providing a first acoustic feature derived from the first acoustic input to an acoustic model stored on the user device to obtain a first sequence of speech units corresponding to the wake-up word spoken by the user in the target language, the acoustic model trained on a corpus of training data in a source language different than the target language; receiving a second acoustic input including the wake-up word in the target language; providing a second acoustic feature derived from the second acoustic input to the acoustic model to obtain a second sequence of speech units corresponding to the wake-up word in the target language; and comparing the first and second sequences of speech units to recognize the wake-up word in the target language.

Abstract: A user device configured to perform wake-up word detection in a target language.

Abstract: A user device configured to perform wake-up word detection in a target language.

Abstract: Methods and an apparatus for performing feature extraction on speech in a microphone signal with embedded noise processing to reduce the amount of processing are provided. In embodiments, feature extraction and the noise estimate use an output of the same Fourier Transform, such that the noise filtering of the speech is embedded with the feature extraction of the speech.

Abstract: A brush assembly includes a circuit board, at least two brushes, power connecting terminals for connecting with an external power supply, and a power supply branch circuit connected in series between a corresponding one of the power connecting terminals and a corresponding one of the brushes. The brush assembly further comprises an EMI suppressor connected between the power supply branch circuit and ground. The EMI suppressor is an axial capacitor formed by a conductor core, a cover, and a filling medium. The cover is attached around the conductor core, and the filling medium is filled between the conductor core and the cover. A motor utilizing the brush assembly is also provided.

Abstract: Methods and an apparatus for performing feature extraction on speech in a microphone signal with embedded noise processing to reduce the amount of processing are provided. In embodiments, feature extraction and the noise estimate use an output of the same Fourier Transform, such that the noise filtering of the speech is embedded with the feature extraction of the speech.

Abstract: A user device configured to perform wake-up word detection in a target language.

Abstract: An end cap assembly for an electric motor has a brush assembly, a circuit board, an inductor and a grounded metal element. The brush assembly has a plurality of brushes. The circuit board is fixed relative to the brush assembly. The inductor is electrically connected to the circuit board. The grounded metal element is positioned between the brushes and the inductor to absorb high frequency electromagnetic radiation transmitted from the brushes to the inductor.

Abstract: A commutator has a conductive layer, a segment layer and an insulating layer separating the conductive layer and the segment layer. The segment layer includes multiple commutator segments. A mounting hole is defined along an axis of the commutator passing through the conductive layer. The three-layer structure of the commutator forms a capacitor having an increased confronting area and reduced inter-plate distance. The capacitor thus has a greater capacitance and hence greater EMI absorbing capability, making it possible to reduce EMI emissions without additional EMI reduction components outside the commutator. A rotor and a motor employing the commutator are also disclosed.

Abstract: A brush assembly includes a circuit board, at least two brushes, power connecting terminals for connecting with an external power supply, and a power supply branch circuit connected in series between a corresponding one of the power connecting terminals and a corresponding one of the brushes. The brush assembly further comprises an EMI suppressor connected between the power supply branch circuit and ground. The EMI suppressor is an axial capacitor formed by a conductor core, a cover, and a filling medium. The cover is attached around the conductor core, and the filling medium is filled between the conductor core and the cover. A motor utilizing the brush assembly is also provided.

Abstract: An end cap assembly includes an end cap. The end cap includes an end wall, a sidewall, and a shielding member. The sidewall projects from one side of the end wall. The sidewall defines a cutout for allowing two conducting wires to pass therethrough, and the two conducting wires connect components mounted within the end cap to an external power source. The shielding member is disposed in the cutout. The end cap assembly provides enhanced EMI suppression. In addition, the present invention also provides a motor employing the end cap assembly.

Abstract: A commutator has a conductive layer, a segment layer and an insulatim layer separating the conductive layer and the segment layer. The segment layer includes multiple commutator segments. A mounting hole is defined along an axis of the commutator passing through the conductive layer. The three-layer structure of the commutator forms a capacitor having an increased confronting area and reduced inter-plate distance. The capacitor thus has a greater capacitance and hence greater EMI absorbing capability, making it possible to reduce EMI emissions without additional EMI reduction components outside the commutator. A rotor and a motor employing the commutator are also disclosed.

Abstract: An end cap assembly for an electric motor has a brush assembly, a circuit board, an inductor and a grounded metal element. The brush assembly has a plurality of brushes. The circuit board is fixed relative to the brush assembly. The inductor is electrically connected to the circuit board. The grounded metal element is positioned between the brushes and the inductor to absorb high frequency electromagnetic radiation transmitted from the brushes to the inductor.

Abstract: A motor includes motor terminals for connecting with an external power supply and an internal circuit connected to the motor terminals. The motor further includes a RF filter. The RF filter includes a conductive wire coiled in either a helical manner or a spiral manner. Terminals of the conductive wire at opposite axial ends of the coil are connected to a corresponding one of the motor terminals and the internal circuit, respectively. The intensity of the electromagnetic waves radiated from most parts of the conductive wire of the RF filter is attenuated by reflected electromagnetic waves from other parts of the conductive wire. Therefore, the intensity of the electromagnetic wave radiated from the motor is greatly reduced. A RF filter for the motor is also provided.

Abstract: There is described a method 300 for open vocabulary speech recognition performed by an electronic device (100). The method (300) includes receiving an utterance waveform (320) and Processing the waveform (350) to provide feature vectors representing the waveform. Then a step of comparing (360) is effected, the comparing compares the feature vectors with concatenated isolated word acoustic models from a concatenated isolated word acoustic model list to select a suitable concatenated isolated word acoustic model. Then a providing a response step (370) provides a response depending on the suitable concatenated isolated word acoustic model. The response typically is a control signal for activating a function of the device (100).