Abstract: A noise filling method is provided that includes detecting a frequency band including a part encoded to 0 from a spectrum obtained by decoding a bitstream; generating a noise component for the detected frequency band; and adjusting energy of the frequency band in which the noise component is generated and filled by using energy of the noise component and energy of the frequency band including the part encoded to 0.

Abstract: The present invention disclose a speech/audio bitstream decoding method including: acquiring a speech/audio decoding parameter of a current speech/audio frame, where the foregoing current speech/audio frame is a redundant decoded frame or a speech/audio frame previous to the foregoing current speech/audio frame is a redundant decoded frame; performing post processing on the acquired speech/audio decoding parameter according to speech/audio parameters of X speech/audio frames, where the foregoing X speech/audio frames include M speech/audio frames previous to the foregoing current speech/audio frame and/or N speech/audio frames next to the foregoing current speech/audio frame; and recovering a speech/audio signal by using the post-processed speech/audio decoding parameter of the foregoing current speech/audio frame. The technical solutions of the present invention help improve quality of an output speech/audio signal.

Abstract: Various exemplary embodiments relate to a provider edge node and a method performed on the node including one or more of the following: storing, in a cache on the node, an association between an Internet Protocol (IP) address of the customer edge device and a Media Access Control (MAC) address of the customer edge device; storing, in a backup memory in the node, a copy of the last-known IP address of the customer edge device; removing the stored association from the cache in response to a cache-clearing event, while maintaining the copy of the last-known IP address in the backup memory; sending an address discovery message, the address discovery message requesting an updated MAC address corresponding to the last-known IP address maintained in the backup memory; and updating the cache to reflect the updated MAC address upon receipt of an additional address update message from the customer edge device.

Abstract: A method for processing sound that includes, generating one or more noise component estimates relating to an electrical representation of the sound and generating an associated confidence measure for the one or more noise component estimates. The method further comprises processing, based on the confidence measure, the sound.

Abstract: A method and an apparatus for packet loss concealment, and a decoding method and an apparatus employing same are disclosed. A method for time domain packet loss concealment includes checking whether a current frame is either an erased frame or a good frame after the erased frame, when the current frame is either the erased frame or the good frame after the erased frame, obtaining signal characteristics, selecting one of a phase matching tool and a smoothing tool based on a plurality of parameters including the signal characteristics, and performing a packet loss concealment processing on the current frame based on the selected tool.

Abstract: The invention relates to a method for operating a radio system of a motor vehicle. In one embodiment, the method comprises: specifying an area surrounding the motor vehicle, determining which digital radio stations within this area can be received error-free using a receiving device of the radio system, and displaying only those digital radio stations which can be received error-free within this area. The invention furthermore relates to a radio system for a motor vehicle and to a motor vehicle with a radio system.

Abstract: Electronic system for audio noise processing and noise reduction comprises: first and second noise estimators, selector and attenuator. First noise estimator processes first audio signal from voice beamformer (VB) and generate first noise estimate. VB generates first audio signal by beamforming audio signals from first and second audio pick-up channels. Second noise estimator processes first and second audio signal from noise beamformer (NB), in parallel with first noise estimator and generates second noise estimate. NB generates second audio signal by beamforming audio signals from first and second audio pick-up channels. First and second audio signals include frequencies in first and second frequency regions. Selector's output noise estimate may be a) second noise estimate in the first frequency region, and b) first noise estimate in the second frequency region. Attenuator attenuates first audio signal in accordance with output noise estimate. Other embodiments are also described.

Abstract: A system for cloud acoustic enhancement is disclosed. In particular, the system may leverage metadata and cloud-computing network resources to mitigate the impact of noisy environments that may potentially interfere with user communications. In order to do so, the system may receive an audio stream including an audio signal associated with a user, and determine if the audio stream also includes an interference signal. The system may determine that the audio stream includes the interference signal if a portion of the audio stream correlates with metadata that identifies the interference signal. If the audio stream is determined to include the interference signal, the system may cancel the interference signal from the audio stream by utilizing the metadata and the cloud-computing network resources. Once the interference signal is cancelled, the system may transmit the audio stream including the audio signal associated with the user to an intended destination.

Abstract: An electronic device includes one or more microphones, one or more sensors, and one or more processors operable with the one or more microphones and the one or more sensors. The one or more processors, upon the one or more sensors detecting the electronic device is disposed within a repository container, such as a pocket, apply an audio signal adjustment function to signals received from the one or more microphones, thereby mitigating noise in the signals caused by the repository container.

Abstract: Systems and techniques for removing non-stationary and/or colored noise can include one or more of the three following innovative aspects: (1) detection of an unwanted target signal, or component thereof, within an observed signal; (2) removal of the target (component) from the observed signal; and (3) filling of a gap in the observed signal generated by removal of the unwanted target (component). Removal regions, frequency bands, and/or regions of the observed signal used to train the gap filler can be adapted in correspondence with local characteristics of the observed signal and/or the target signal (component). Related aspects also are described. For example, disclosed noise detection and/or removal methods can include converting an incoming acoustic signal to a corresponding machine-readable form. And, a corrected signal in machine-readable form can be converted to a human-perceivable form, and/or to a modulated signal form conveyed over a communication connection.

Abstract: A method for estimating a noise power level difference (NPLD) between a primary microphone and a reference microphone of an audio device includes obtaining primary and reference channels of an audio signal with primary and reference microphones of an audio device and estimating a noise magnitude of the reference channel of the audio signal to provide a noise variance estimate for one or more frequencies. A modelled probability density function (PDF) of a fast Fourier transform (FFT) coefficient of the primary channel of the audio signal is maximized to provide a NPLD between the noise variance estimate of the reference channel and a noise variance estimate of the primary channel. A modelled PDF of an FFT coefficient of the reference channel of the audio signal is maximized to provide a complex speech power level difference (SPLD) coefficient between the speech FFT coefficients of the primary and reference channel.

Abstract: A method includes receiving first image data at an electronic device, and performing a first image recognition operation on the first image data based on a first image recognition model stored in a memory of the electronic device. The method may include sending an image recognition model update request from the electronic device to a server, in response to determining that a result of the first image recognition operation fails to satisfy a confidence threshold. The method includes receiving image recognition model update information from the server and updating the first image recognition model based on the image recognition model update information to generate a second image recognition model. The method further includes performing a second image recognition operation based on the second image recognition model.

Abstract: The present invention relates to a multi-band noise reduction system for digital audio signals producing a noise reduced digital audio output signal from a digital audio signal. The digital audio signal comprises a target signal and a noise signal, i.e. a noisy digital audio signal. The multi-band noise reduction system operates on a plurality of sub-band signals derived from the digital audio signal and comprises a second or adaptive signal-to-noise ratio estimator which is configured for filtering a plurality of first signal-to-noise ratio estimates of the plurality of sub-band signals with respective time-varying low-pass filters to produce respective second signal-to-noise ratio estimates of the plurality of sub-band signals. A low-pass cut-off frequency of each of the time-varying low-pass filters is adaptable in accordance with a first signal-to-noise ratio estimate determined by a first signal-to-noise ratio estimator and/or the second signal-to-noise ratio estimate of the sub-band signal.

Abstract: Methods and apparatuses for addressing open space noise are disclosed. In one example, a method for masking open space noise includes receiving a plurality of mobile device microphone data from a plurality of mobile devices. A location data associated with each mobile device in the plurality of mobile devices is received. A plurality of stationary microphone data is received from a plurality of stationary microphones. A sound masking noise output is adjusted at one or more loudspeakers responsive to the plurality of mobile device microphone data and the plurality of stationary microphone data.

Abstract: Embodiments of the present invention relate to signal processing. Methods for enhancing intelligibility of speech content in an audio signal are disclosed. One of the methods comprises obtaining reference loudness of the audio signal. The method further comprises enhancing the intelligibility of the speech content by adjusting partial loudness of the audio signal based on the reference loudness and a degree of the intelligibility. Corresponding systems and computer program products are also disclosed.

Abstract: A sound pick-up device of the present disclosure acquires extracted sound as a result of extracting target area sound using non-target area sound present in a target area direction from output of a beam former, divides each of an input signal and the extracted sound into plural bands, computes a power spectrum ratio between the input signal and the extracted sound for each divided band, determines whether or not target area sound is present in the input signal by employing the power spectrum ratios for each divided band, and outputs the extracted sound as a sound pick-up result in cases in which target area sound has been determined to be present.

Abstract: A method for selective sound field environment processing for one or more wireless earpieces, each of the one or more wireless earpieces including comprising a plurality of microphones is provided. The method includes receiving audio input of a sound field environment from the plurality of microphones of each of the one or more wireless earpieces, identifying background noise in the sound field environment, identifying audio from at least one sound source within the sound field environment, processing the audio input using one or more processors of at least one of the wireless earpieces to reduce the background noise and processing the audio input using one or more processors of the at least one of the wireless earpieces to enhance the audio from the at least one sound source within the sound field environment to provide processed audio, and transducing the processed audio at one or more speakers of the one or more wireless earpieces.

Abstract: Method and systems are provided for interpreting speech data. A method and system for recognizing speech involving a filter module to generate a set of processed audio data based on raw audio data; a translation module to provide a set of translation results for the raw audio data; and a decision module to select the text data that represents the raw audio data. A method for minimizing noise in audio signals received by a microphone array is also described. A method and system of automatic entry of data into one or more data fields involving receiving a processed audio data; and operating a processing module to: search in a trigger dictionary for a field identifier that corresponds to the trigger identifier; identify a data field associated with a data field identifier corresponding to the field identifier; and providing content data associated with the trigger identifier to the identified data field.

Abstract: An apparatus to measure signal-to-thermal noise ratio (SNR) and signal-to-pulse noise ratio (SPNR), the apparatus including a quadrature mixer, a pulse noise reduction unit, an SNR estimation unit and an offset compensation unit, connected in series, the quadrature mixer receiving the input radio signal and outputting an in-phase component and a quadrature component; a pulse noise separation unit, and an SPNR estimation unit connected series, the pulse noise reduction unit and the pulse noise separation unit inputting the in-phase and quadrature components; the SPNR estimation unit inputting a filtered in-phase component from the pulse noise reduction unit. The offset compensation unit outputs a current SNR. The SPNR estimation unit outputs a current SPNR. The pulse noise separation unit includes a first LPF, an impulse noise separator and an HPF, connected in series; and a second LPF, a pulse noise detection unit and an inverter, connected in series.

Abstract: An abnormal frame detection method and apparatus are disclosed. In an embodiment the method includes obtaining a signal frame from a speech signal, and dividing the signal frame into at least two subframes; obtaining a local energy value of a subframe of the signal frame; obtaining, according to the local energy value of the subframe, a first characteristic value used to indicate a local energy trend of the signal frame; performing singularity analysis on the signal frame to obtain a second characteristic value; and determining the signal frame as an abnormal frame if the first characteristic value meets a first threshold and the second characteristic value meets a second threshold. It is implemented whether distortion occurs in a speech signal is detected.

Abstract: Systems and methods for speech recognition incorporating environmental variables are provided. The systems and methods capture speech to be recognized. The speech is then recognized utilizing a variable component deep neural network (DNN). The variable component DNN processes the captured speech by incorporating an environment variable. The environment variable may be any variable that is dependent on environmental conditions or the relation of the user, the client device, and the environment. For example, the environment variable may be based on noise of the environment and represented as a signal-to-noise ratio. The variable component DNN may incorporate the environment variable in different ways. For instance, the environment variable may be incorporated into weighting matrices and biases of the DNN, the outputs of the hidden layers of the DNN, or the activation functions of the nodes of the DNN.

Abstract: A method of controlling a sound system installed in a plurality of vehicles is disclosed that includes recognizing a plurality of sound systems respectively installed in a plurality of vehicles, determining relative positions of the plurality of vehicles, and controlling operations of the plurality of sound systems according to the relative positions and specifications of each of the plurality of vehicles.

Abstract: A nearend speech detector for classifying speech at a communication system receiving a microphone signal from a nearend microphone and a farend signal from a farend communication system, the nearend speech detector comprising: a signal processor configured to transform the microphone and farend signals into the frequency domain; a calculation unit configured to form: an estimate of a nearend signal representing nearend speech present in the microphone signal; and a measure of gain between the microphone signal and the nearend signal; and a signal classifier configured to classify speech at the communication system in dependence on a measure of variance of the gain and a measure of variance of the nearend signal.

Abstract: A speech-processing apparatus includes: a sound source localization unit that localizes a sound source based on an acquired speech signal; and a speech zone detection unit that performs speech zone detection based on localization information localized by the sound source localization unit.

Abstract: A method and an apparatus for signal extraction of audio signal are provided. An audio signal is converted into a plurality of frames, and the frames are arranged in a chronological order. Spectral data of each of the frames is obtained. The spectral data of each of N frames is extracted in the chronological order, and a spectral connectivity operation is executed for the N frames. Finally, the signal including the frames having the spectral connectivity between adjacent frames in each of the frames is determined as an ideal signal.

Abstract: A vehicle includes: an input unit configured to receive an execution command for speech recognition; a calculator configured to calculate a time in which the vehicle is expected to arrive at an obstacle existing on a road on which the vehicle travels; and a speech recognition controller configured to compare the calculated time in which the vehicle is expected to arrive at the obstacle to a time in which a voice command input is expected to be completed to determine whether to perform dynamic noise removal pre-processing.

Abstract: Method and apparatus are provided for reconstructing a noise component of a speech/audio signal. A bitstream, is received and decoded to obtain a speech/audio signal. A first speech/audio signal is determined according to the speech/audio signal. A symbol of each sample value in the first speech/audio signal and an amplitude value of each sample value in the first speech/audio signal is determined. An adaptive normalization length and an adjusted amplitude value of each sample value are determined according to the adaptive normalization length and the amplitude value of each sample value. A second speech/audio signal is determined according to the symbol of each sample value and the adjusted amplitude value of each sample value.

Abstract: Embodiments include a wearable device, such as a head-worn device. The wearable device includes a first microphone to receive a first sound signal from a wearer of the wearable device; a second microphone to receive a second sound signal from the wearer of the wearable device; and a processor to process the first sound signals and the second sound signals to determine that the first and second sound signals originate from the wearer of the wearable device.

Abstract: The present disclosure discloses an image processing method of a mobile terminal, and a mobile terminal. To process an image, an audio signal is collected using a sensor of the mobile terminal. Air-blowing signal intensity is acquired by performing a windowed fast Fourier transform (FFT) on the audio signal to obtain a frequency domain signal of the audio signal. The frequency domain signal of the audio signal is divided into at least one time-slice frequency domain signal. It is then identified whether the audio signal is an air-blowing signal according to the at least one time-slice frequency domain signal and a preset property of the air-blowing signal. The air-blowing signal intensity is acquired according to the at least one time-slice frequency domain signal when the audio signal is identified as an air-blowing signal. An image is acquired according to the air-blowing signal intensity.

Abstract: A sound processing circuit comprises a first input for receiving a first input signal, and a second input for receiving a second input signal. A first adaptive filter receives the first input signal, and an error calculation block calculates an error between the second input signal and the output of the first adaptive filter, and outputting an error signal. A second adaptive filter receives the error signal, and an output calculation block subtracts an output of the second adaptive filter from the first input signal to generate an output signal. The adaptation of first and second adaptive filters is controlled based on a magnitude coherence between the first and second input signals.

Abstract: A system and method for processing an audio signal captured from a microphone may reproduce a known audio signal with an audio transducer into an acoustic space. The known audio signal may include content from one or more audio sources. A microphone audio signal may be captured from the acoustic space where the microphone audio signal comprises the known audio signal and one or more unknown audio signals. Processing control information may be accessed. The known audio signal may be reduced in the microphone audio signal responsive to the processing control information where the processing control information indicates one or more characteristics of a downstream audio processor that processes the microphone audio signal.

Abstract: A system including first and second gain modules, an operator module, and a priori and posteriori modules. The first gain module applies a non-linear function to generate a gain signal based on an amplitude of a first speech signal and an estimated a priori variance of noise included in the first speech signal. The operator module generates an operator based on the gain signal and the estimated a priori variance of noise. The a priori module determines an a priori signal-to-noise ratio based on the operator. The posteriori module determines a posteriori signal-to-noise ratio based on the amplitude of the first speech signal and (ii) the estimated a priori variance of noise.

Abstract: A system for identifying a periodicity-related attribute in a multi-frequency signal. The system is configured to produce phase and delay modulated signals from a complex input signal. The system is designed to combine these phase and delay modulated signals to identify a periodicity-related attribute associated with the multi-frequency signal. The system is configured to produce a physically perceptible output based on the identified periodicity-related attribute.

Abstract: Techniques for identifying a location of a voice-controlled device within an environment. After identifying a location of the device, the device may receive a voice command from a user within the environment and may determine a response to the command based in part on the location, may determine how to output a response based in part on the location or may determine how to interact with the user based in part on the location.

Abstract: Methods and corresponding apparatuses for transmitting and receiving audio signals are described. A transformation is performed on the audio signals in units of frame in order to obtain transformed audio data of each frame, said transformed audio data consisting of multiple signal components in the frequency domain. These signal components of each frame are distributed into multiple adjacent packets in order to generate packets in which signal components distributed from multiple frames are interleaved. Subsequently, the generated packets are transmitted. Accordingly, in case that packet loss occurs during transmission, the audio signals can be recovered based on the received signal components without consuming additional bandwidth. Therefore, robustness against packet loss can be achieved with little overhead.

Abstract: A system that performs noise estimation for an audio adjustment application comprises a coherence calculator that determines at least one coherence value between microphone signals generated by at least two microphones that each independently senses acoustic energy in a listening space. A first microphone of the at least two microphones generates a first microphone signal from the acoustic energy and a second microphone of the at least two microphones generates a second microphone signal from the acoustic energy. The acoustic energy comprises a combination of an audio signal transduced by one or more speakers and environmental noise of the acoustic energy that is local to the listening space. A noise estimate computation processor determines an estimate of a level of the environmental noise based on the at least one coherence value.

Abstract: A speech recognition system for resolving impaired utterances can have a speech recognition engine configured to receive a plurality of representations of an utterance and concurrently to determine a plurality of highest-likelihood transcription candidates corresponding to each respective representation of the utterance. The recognition system can also have a selector configured to determine a most-likely accurate transcription from among the transcription candidates. As but one example, the plurality of representations of the utterance can be acquired by a microphone array, and beamforming techniques can generate independent streams of the utterance across various look directions using output from the microphone array.

Abstract: An audio signal processing device that includes: a processor configured to execute a procedure, the procedure comprising: detecting a speech segment of an audio signal; suppressing noise in the audio signal; and adjusting an amount of suppression of noise such that the amount of suppression during a specific period, which starts from a position based on a terminal end of the detected speech segment and is a period shorter than a period spanning from the terminal end of the detected speech segment to a starting end of a next speech segment, becomes greater than in other segments, and a memory configured to store audio signals before and after noise suppression and the amount of suppression before and after adjustment.

Abstract: In a wireless communication system, a secure communication link is provided by selecting a decoy data signal for transmission, generating a precoding matrix from a message to be sent; and multiplying the decoy data signal by the precoding matrix to produce a precoded signal. A clean version of the decoy data may be transmitted to an intended receiver. The receiver can distinguish between the information-bearing precoding and the natural random channel distortions of the transmission medium to decrypt the information, while an eavesdropper would find it difficult to distinguish between the natural channel distortions and information-bearing precoding in the signals it receives.

Abstract: The present invention discloses a howling suppression method and device applied to an ANR earphone. The method comprises: collecting signals by using a first microphone and a second microphone; wherein the first microphone is arranged in a position outside an auditory meatus when said ANR earphone is worn, and the second microphone is arranged in a position inside the auditory meatus when the ANR earphone is worn; according to a relation between signals collected by the first microphone and the second microphone, judging whether the current state of said ANR earphone is a state unable to produce a howling or a state able to produce a howling; and when the current state of said ANR earphone is a state able to produce a howling, starting processing for preventing howling production. The technical scheme can achieve that the ANR earphone does not produce a howling all the time.

Abstract: An audio capture device selects between multiple microphones to generate an output audio signal depending on detected conditions. When the presence of wind noise or other uncorrelated noise is detected, the audio capture device selects, for each of a plurality of different frequency sub-bands, an audio signal having the lowest noise and combines the selected frequency sub-bands signals to generate an output audio signal. When wind noise or other uncorrelated noise is not detected, the audio capture device determines whether each of a plurality of microphones are wet or dry and selects one or more audio signals from the microphones depending on their respective conditions.

Abstract: An apparatus comprising a camera, a microphone, a speaker and a processor. The camera may be mounted to a first portion of a pair of eyeglasses. The microphone may be mounted to a second portion of the pair of eyeglasses. The speaker may be mounted to the pair of eyeglasses. The processor may be electronically connected to the camera, the microphone and the speaker. The processor may be configured to (i) associate a visual display of the movement of the lips of a target received from the camera with an audio portion of the target received from the microphone, (ii) filter sounds not related to the target, and (iii) play sounds not filtered through the speaker.

Abstract: A non-intrusive speech quality estimation technique is based on statistical or probability models such as Gaussian Mixture Models (“GMMs”). Perceptual features are extracted from the received speech signal and assessed by an artificial reference model formed using statistical models. The models characterize the statistical behavior of speech features. Consistency measures between the input speech features and the models are calculated to form indicators of speech quality. The consistency values are mapped to a speech quality score using a mapping optimized using machine learning algorithms, such as Multivariate Adaptive Regression Splines (“MARS”). The technique provides competitive or better quality estimates relative to known techniques while having lower computational complexity.

Abstract: A voice processing apparatus includes: a feature amount acquisition unit configured to acquire a spectrum of an audio signal for each frame; an utterance state determination unit configured to determine an utterance state for each frame on the basis of the audio signal; and a spectrum normalization unit configured to calculate a normalized spectrum in a current utterance by normalizing a spectrum for each frame in the current utterance using at least an average spectrum acquired until the present time.

Abstract: Acoustic noise in an audio signal is reduced by calculating a speech probability presence (SPP) factor using minimum mean square error (MMSE). The SPP factor, which has a value typically ranging between zero and one, is modified or warped responsive to a value obtained from the evaluation of a sigmoid function, the shape of which is determined by a signal-to-noise ratio (SNR), which is obtained by an evaluation of the signal energy and noise energy output from a microphone over time.

Abstract: An audio metadata providing apparatus and method and a multichannel audio data playback apparatus and method to support a dynamic format conversion are provided. Dynamic format conversion information may include information about a plurality of format conversion schemes that are used to convert a first format set by an author of multichannel audio data into a second format that is based on a playback environment of the multichannel audio data and that are each set for corresponding playback periods of the multichannel audio data. The audio metadata providing apparatus may provide audio metadata including the dynamic format conversion information. The multichannel audio data playback apparatus may identify the dynamic format conversion information from the audio metadata, may convert the first format of the multichannel audio data into the second format based on the identified dynamic format conversion information, and may play back the multichannel audio data in the second format.

Abstract: Acoustic noise in an audio signal is reduced by calculating a speech probability presence (SPP) factor using minimum mean square error (MMSE). The SPP factor, which has a value typically ranging between zero and one, is modified or warped responsive to a value obtained from the evaluation of a sigmoid function, the shape of which is determined by a signal-to-noise ratio (SNR), which is obtained by an evaluation of the signal energy and noise energy output from a microphone over time. The shape and aggressiveness of the sigmoid function is determined using an extrinsically-determined SNR, not determined by the MMSE determination.

Abstract: A system for identifying a periodicity-related attribute in a multi-frequency signal. The system is configured to produce phase and delay modulated signals from a complex input signal. The system is designed to combine these phase and delay modulated signals to identify a periodicity-related attribute associated with the multi-frequency signal. The system is configured to produce a physically perceptible output based on the identified periodicity-related attribute.

Abstract: An information processing apparatus includes: an acquisition unit adapted to acquire activities corresponding to a plurality of bases from an audio signal; a determination unit adapted to determine whether the plurality of acquired activities have a specific characteristic; and an output unit adapted to output an audio signal obtained by separating, from the audio signal, a component corresponding to an activity which is determined to have the specific characteristic by the determination unit.

Abstract: A multi-object audio encoding and decoding apparatus supporting a post downmix signal may be provided. The multi-object audio encoding apparatus may include: an object information extraction and downmix generation unit to generate object information and a downmix signal from input object signals; a parameter determination unit to determine a downmix information parameter using the extracted downmix signal and the post downmix signal; and a bitstream generation unit to combine the object information and the downmix information parameter, and to generate an object bitstream.