Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A loudness of an input voice signal is detected to obtain a reference loudness. Reference loudness gains corresponding to frequency bands are calculated according to the reference loudness and wide dynamic range compression curves corresponding to the frequency bands. Loudnesses of filter signals of the frequency bands are adjusted according to the reference loudness gains of the frequency bands.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A loudness of an input voice signal is detected to obtain a reference loudness. Reference loudness gains corresponding to frequency bands are calculated according to the reference loudness and wide dynamic range compression curves corresponding to the frequency bands. Loudnesses of filter signals of the frequency bands are adjusted according to the reference loudness gains of the frequency bands.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A filtering loudness gain of a filter signal of each frequency band is adjusted according to a wide dynamic range compression curve without an upper output loudness limit. The filtering loudness gain of each frequency band is reduced by lowering a gain decrease adjustment value, so as to reduce a loudness of a loudness adjusted filter signal, and thus a loudness of an output voice signal is lower than a first threshold value.

Abstract: A method for dynamically adjusting recovery time in wide dynamic range compression (WDRC) for use in a hearing aid is provided. The method includes the steps of: receiving an input signal via the hearing aid; applying a band-pass filter on the input acoustic signal to calculate a high-energy ratio; calculating an over-zero rate ratio corresponding to the input acoustic signal; calculating a consonant occurring probability according to the high-frequency energy ratio and the over-zero rate ratio; applying a consonant determination mechanism on the input acoustic signal, and adjusting the consonant occurring probability according to the results of the consonant determination mechanism; calculating a recovery time factor corresponding to the input acoustic signal according to the adjusted consonant occurring probability; and performing a WDRC process on the input acoustic signal according to the recovery time factor to generate an output acoustic signal.

Abstract: A filter gain compensation method for a specific frequency band for use in an electronic device is provided. In the method, a windowed filter is applied on each of a plurality of band-pass filters in a multi-segment band-pass filter corresponding to the high-frequency signal and different frequency bands of the low-frequency signal. In addition, a high-frequency cancellation filter corresponding to the high-frequency signal of an input digital signal is calculated. A compensation gain for the high-frequency cancellation filter and each of the band-pass filters is calculated according to fitting frequency gains and a fitting frequency relationship matrix. The output acoustic signal is synthesized using output signals from the windowed band-pass filters and the high-frequency cancellation filter that are obtained according to updated filter features and compensation gain for the windowed band-pass filters and the high-frequency cancellation filter.

Abstract: An electronic device and a method for dynamically adjusting the output of a headset are provided in the invention. The electronic device includes a first connection interface, a processor and a storage device. When the first connection interface is coupled to the detection device, the first connection interface transmits detection-source signals to the detection device, and receives groups of headset output signals corresponding to the detection-source signals from the detection device. When the first connection interface is coupled to the detection device, the processor obtains gain information according a plurality of groups of measured headset signals corresponding to the groups of headset output signals, and when the first connection interface is coupled to the headset device, the processor dynamically adjusts the output of the headset device according to the gain information. The storage device is coupled to the processor and stores the gain information.

Abstract: An electronic device and a method for dynamically adjusting the output of a headset are provided in the invention. The electronic device includes a first connection interface, a processor and a storage device. The first connection interface is coupled to a detection device, transmits a plurality of detection-source signals to the detection device, and receives a plurality of groups of headset output signals corresponding to the plurality of detection-source signals from the detection device. The processor is coupled to the first connection interface, obtains gain information according a plurality of groups of measured headset signals corresponding to the plurality of groups of headset output signals, and dynamically adjusts the output of a headset according to the gain information. The storage device is coupled to the processor and stores the gain information.

Abstract: An electronic device and a method for dynamically adjusting the output of a headset are provided in the invention. The electronic device includes a first connection interface, a processor and a storage device. The first connection interface is coupled to a detection device, transmits a plurality of detection-source signals to the detection device, and receives a plurality of groups of headset output signals corresponding to the plurality of detection-source signals from the detection device. The processor is coupled to the first connection interface, obtains gain information according a plurality of groups of measured headset signals corresponding to the plurality of groups of headset output signals, and dynamically adjusts the output of a headset according to the gain information. The storage device is coupled to the processor and stores the gain information.

Abstract: An electronic device is provided in the invention. The electronic device includes a first connection interface, a second connection interface, a processor and a storage device. The first connection interface is coupled to a third connection interface of a detection device by a headset connector to receive an oscillation signal and headset output signal corresponding to a detection-source signal from the detection device, and transmits the detection-source signal to the detection device. The second connection interface is coupled to a fourth interface to transmit a control signal to the detection device. The processor is coupled to the first connection interface and second connection interface, and obtains the microphone information according to the oscillation signal, and obtains the headset information according to measured headset signals and the microphone information. The storage device is coupled to the processor to store the microphone information and the headset information.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A first sampling point of an mth original frequency-lowered signal frame phase-matched to the sampling point corresponding to a phase reference sampling point number is determined according to the phase reference sampling point number of an (m?1)th original frequency-lowered signal frame corresponding to a middle sampling point of an (m?1)th renovating frequency-lowered signal frame. The q consecutive sampling points starting from the first sampling point are used as the sampling points of an mth renovating frequency-lowered signal frame.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A last sampling point of an mth original frequency-lowered signal frame is determined according to a phase reference sampling point number of the mth original frequency-lowered signal frame. Here, the phase reference sampling point number corresponds to a middle sampling point of an mth renovating frequency-lowered signal frame, and the last sampling point is phase-matched with a sampling point corresponding to the phase reference sampling point number in the mth original frequency-lowered signal frame. P consecutive sampling points starting from the last sampling point are applied as sampling points of an (m+1)th renovating frequency-lowered signal frame.

Abstract: A speech recognition apparatus and a speech recognition method are provided. In the invention, whether an original voice sampling signal corresponding to a target voice frame is a consonant signal is determined according to at least one of a ratio of an energy of a low-pass sampling signal to an energy of the original voice sampling signal and a ratio value of an energy of a second consonant frequency band signal.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A last sampling point of an mth original frequency-lowered signal frame is determined according to a phase reference sampling point number of the mth original frequency-lowered signal frame. Here, the phase reference sampling point number corresponds to a middle sampling point of an mth renovating frequency-lowered signal frame, and the last sampling point is phase-matched with a sampling point corresponding to the phase reference sampling point number in the mth original frequency-lowered signal frame. P consecutive sampling points starting from the last sampling point are applied as sampling points of an (m+1)th renovating frequency-lowered signal frame.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. A first sampling point of an mth original frequency-lowered signal frame phase-matched to the sampling point corresponding to a phase reference sampling point number is determined according to the phase reference sampling point number of an (m?1)th original frequency-lowered signal frame corresponding to a middle sampling point of an (m?1)th renovating frequency-lowered signal frame. The q consecutive sampling points starting from the first sampling point are used as the sampling points of an mth renovating frequency-lowered signal frame.

Abstract: A speech recognition apparatus and a speech recognition method are provided. In the invention, whether an original voice sampling signal corresponding to a target voice frame is a noise signal is determined according to a ratio of an energy of a first consonant frequency band signal to an energy of a second consonant frequency band signal, a ratio of an energy of the first consonant frequency band signal to an energy of the original voice sampling signal and a ratio of an energy of the second consonant frequency band signal to an energy of the original voice sampling signal.

Abstract: An electronic device includes a microphone, a bias-supply device and a voice-recognition device. The bias-supply device is configured to provide a first bias voltage to serve as an operation voltage of the microphone, when the electronic device is operated in a power-saving mode, such that the microphone transforms a voice signal into a first output signal. The voice-recognition device is configured to receive the first output signal and output a control signal, when the first output signal has a predetermined signal, to enable the electronic device be operated in a normal operation mode and the bias-supply device to provide a second bias voltage that is higher than the first bias voltage to serve as the operation voltage of the microphone, such that the microphone transforms the voice signal into a second output signal and outputs the second signal to a core circuit.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. Calculate a value of an interpolation parametric function corresponding to a sampling signal frame according to three consecutive sample values in the sampling signal frame, and calculate an interpolated value between two adjacent sampling points in a frequency-lowered signal frame according to the value of the interpolation parametric function.

Abstract: A speech recognition apparatus and a speech recognition method are provided. In the invention, whether an original voice sampling signal corresponding to a target voice frame is a noise signal is determined according to a ratio of an energy of a first consonant frequency band signal to an energy of a second consonant frequency band signal, a ratio of an energy of the first consonant frequency band signal to an energy of the original voice sampling signal and a ratio of an energy of the second consonant frequency band signal to an energy of the original voice sampling signal.

Abstract: A speech recognition apparatus and a speech recognition method are provided. In the invention, whether an original voice sampling signal corresponding to a target voice frame is a consonant signal is determined according to at least one of a ratio of an energy of a low-pass sampling signal to an energy of the original voice sampling signal and a ratio value of an energy of a second consonant frequency band signal.

Abstract: A voice signal processing apparatus and a voice signal processing method are provided. Each frequency-lowered signal window included in a frequency-lowered sampling voice signal is divided into a first sub signal window that is faded-in and a second sub signal window that is faded-out. The first sub signal window and the second sub signal window that are adjacent to each other and belong to the different frequency-lowered signal windows are overlapped in order to generate an overlapping voice signal. The overlapping voice signal and the sampling voice signal are combined to generate an output signal.