Abstract: An object analyzing method applied to an object analyzing system. The object analyzing method comprises: (a) applying at least one analyzing parameter extracting process according to an object type for an target object, to extract at least one analyzing parameter for the target object; (b) selecting least one analyzing model according to the object type; and (c) applying the analyzing model selected in the step (b), to analyze the analyzing parameter and accordingly generate an analyzing result.

Abstract: A voice wakeup detecting device for an electronic product includes a digital microphone and an application processor. The digital microphone has a function of judging whether a digital voice signal contains a subword according to subword model parameters. If the digital microphone confirms that the digital voice signal contains the subword, the digital microphone generates a first interrupt signal and outputs the digital voice signal. The application processor is enabled in response to the first interrupt signal. The application processor judges whether the digital voice signal contains a keyword according to keyword model parameters. If the application processor confirms that the digital voice signal contains the keyword, the electronic product is waked up from a sleep state to a normal working state under control of the application processor.

Abstract: A voice wakeup detecting device for an electronic product includes a front end detecting circuit, a speech recognition processor and a main processor. The front end detecting circuit judges whether a voice signal contains a sub-keyword according to sub-keyword model parameters. If the front end detecting circuit confirms that the voice signal contains the sub-keyword, then it generates a first interrupt signal. In response to the first interrupt signal, the speech recognition processor is enabled to judge whether the voice signal contains a keyword according to keyword model parameters. If the speech recognition processor confirms that the voice signal contains the keyword, then it generates a second interrupt signal. In response to the second interrupt signal, the main processor is enabled. Consequently, the electronic produce is waked up from a sleep state to a normal working state.

Abstract: A keyword spotting system includes a decoder having a storage device and a decoding circuit. The storage device is used to store a log-likelihood table and a plurality of dynamic programming (DP) tables generated for recognition of a designated keyword. The decoding circuit is used to refer to features in one frame of an acoustic data input to calculate the log-likelihood table and refer to at least the log-likelihood table to adjust each of the DP tables when recognition of the designated keyword is not accepted yet, where the DP tables are reset by the decoding circuit at different frames of the acoustic data input, respectively.

Abstract: An electronic device includes a receiver and an activator. The receiver includes a microphone; and a signal detector, coupled to the microphone, for determining whether a valid input signal received from the microphone is a voice signal or an ultrasonic signal by comparing a frequency of the valid input signal with at least two frequency bands, and accordingly passing the valid input signal. The activator includes a voice detection module, for performing a voice activated process; and an ultrasonic detection module, for performing an ultrasound activated process. The voice detection module and the ultrasonic detection module are enabled by the signal detector simultaneously or separately.

Abstract: The invention provides a system for speech keyword detection and associated method. The system includes a speech keyword detector, an activity predictor and a decision maker. The activity predictor obtains sensor data provided by a plurality of sensors, and processes the sensor data to provide an activity prediction result indicating a probability for whether a user is about to give voice keyword. The decision maker processes the activity prediction result and a preliminary keyword detection result of the speech keyword detection to provide a keyword detection result.

Abstract: A voice verifying system, which comprises: a microphone, which is always turned on to output at least one voice signal; a speech determining device, for determining if the voice signal is valid or not according to a reference value, wherein the speech determining device passes the voice signal if the voice signal is valid; and a verifying module, for verifying a speech signal generated from the voice signal and for outputting a device activating signal to activate a target device if the speech signal matches a predetermined rule; and a reference value generating device, for generating the reference value according to speech signal information from the verifying module.

Abstract: An embodiment of the invention provides a calibration control method performed by a microphone system. The microphone system includes a plurality of microphones configured to generate a plurality of microphone signals. First, the microphone system equalize the microphone signals to generate a plurality of equalized microphone signals. Next, the microphone system calculates a set of similarity indicators based on the equalized microphone signals. Then, the microphone system compares the set of similarity indicators with a set of predetermined thresholds to determine whether to calibrate the microphone signals.

Abstract: An embodiment of the invention provides an electronic device. The electronic device is configured to protect a set of private data of an authorized user of the electronic device. The electronic device includes a biometric sampler, a biometric authenticator, and a data provider. The biometric sampler is configured to covertly collect a set of biometric samples from a current user of the electronic device. The biometric authenticator is configured to covertly use the set of biometric samples of the current user and a set of biometric data of the authorized user to verify whether the current user is the authorized user. The data provider is configured to give the current user access to a set of fake data instead of the set of private data if the current user is not the authorized user.

Abstract: An embodiment of the invention provides a method of preparing for speaker authentication. The method includes: receiving speech data that represents an utterance made by a user; extracting side information; examining the side information to determine whether to allow speaker model training using the speech data; and generating a feedback message for the user based on the side information if speaker model training using the speech data is not allowed.

Abstract: An electronic device for browsing a document is disclosed. The document being browsed includes a plurality of command-associated text strings. First, a text string selector of the electronic device selects a plurality of candidate text strings from the command-associated text strings. Afterward, an acoustic string provider of the electronic device prepares a candidate acoustic string for each of the candidate text strings. Thereafter, a microphone of the electronic device receives a voice command. Next, a speech recognizer of the electronic device searches the candidate acoustic strings for a target acoustic string that matches the voice command, wherein the target acoustic string corresponds to a target text string of the candidate text strings. Finally, a document browser of the electronic device executes a command associated with the target text string.

Abstract: A disclosed embodiment provides a speech recognition method to be performed by an electronic device. The method includes: collecting user-specific information that is specific to a user through the user's usage of the electronic device; recording an utterance made by the user; letting a remote server generate a remote speech recognition result for the recorded utterance; generating rescoring information for the recorded utterance based on the collected user-specific information; and letting the remote speech recognition result rescored based on the rescoring information.