Abstract: A power mitigation algorithm in a loudspeaker amplification system that includes a loudspeaker driver, an audio amplifier, and a constant output power, power supply. A power requirement for the amplifier to output an audio signal is determined. A gain adjustment signal is then determined based on a difference between the power requirement and a power budget of the amplifier. Gain of the audio signal is adjusted according to the gain adjustment signal, for output through the loudspeaker driver. As a result, a peak level of the power consumption of the amplifier while outputting the gain-adjusted audio signal becomes less than the power budget. Other embodiments are also described and claimed.

Abstract: Embodiments of the present disclosure provide a method and a device for cancelling an echo, and a computer readable storage medium. The device includes a loudspeaker configured to play an acoustic signal corresponding to an analog audio signal. The device further includes a microphone configured to convert a mixed acoustic signal received into a mixed audio signal. The mixed acoustic signal includes an echo of the acoustic signal played and an acoustic signal from a user. The device further includes an analog-to-digital converter configured to convert the analog audio signal into a digital signal as an echo reference signal. The device further includes an echo canceller, configured to cancel an echo component from the mixed audio signal using the echo reference signal to obtain a user audio signal corresponding to the acoustic signal from the user.

Abstract: Audio device systems and methods are provided to enhance speech pick-up from a user. The systems and methods include a plurality of left signals and right signals from microphones coupled to left and right earpieces. Various of the signals are combined to provide a primary signal having enhanced acoustic response in the direction of a selected location, such as the user's mouth. Additionally, the left signals are combined to provide a left reference signal having reduced acoustic response from the selected location, and the right signals are combined to provide a right reference signal also having reduced acoustic response from the selected location. Each of the left and right reference signals are filtered to provide left and right noise estimates, respectively, and the left and right noise estimates are subtracted from the primary signal.

Abstract: A method of mixing microphone signals. First and second microphone signals are obtained from respective first and second microphones. In at least one affected subband, the first and second microphone signals are mixed to produce first and second mixed signals. At least one reference subband of the first and second microphone signals is processed in order to identify a binaural cue between the first and second microphone signals, the reference subband being distinct from the or each affected subband. The affected subband in the first and second mixed signals is modified in order to re-emphasize the identified binaural cue.

Abstract: A headphone system is provided that includes a left and right earpiece having a left and right microphone, respectively, to receive left and right acoustic signals and provide left and right signals for processing. The left and right signals are added to provide a principal signal, and the left and right signals are subtracted to provide a reference signal. A detection circuit compares the principal signal to the reference signal and selectively indicates whether a user is speaking.

Abstract: Techniques for altering audio being output by a voice-controlled device, or another device, to enable more accurate automatic speech recognition (ASR) by the voice-controlled device. For instance, a voice-controlled device may output audio within an environment using a speaker of the device. While outputting the audio, a microphone of the device may capture sound within the environment and may generate an audio signal based on the captured sound. The device may then analyze the audio signal to identify speech of a user within the signal, with the speech indicating that the user is going to provide a subsequent command to the device. Thereafter, the device may alter the output of the audio (e.g., attenuate the audio, pause the audio, switch from stereo to mono, etc.) to facilitate speech recognition of the user's subsequent command.

Abstract: The present invention relates to a microphone apparatus (10) with a main beamformer (F, BF) that provides a directional audio output (SF) by combining microphone signals (X, Y) from multiple microphones (11, 12). The quality of beamformed microphone signals normally depends on the individual microphones having equal sensitivity characteristics across the used frequency range. The invention enables automatic adaptation of the main beamformer (F, BF) to variations in microphone sensitivity and to changes in the alignment of the microphone apparatus (10) with respect to the user's mouth (7).

Abstract: Systems and methods are described herein for automatically changing the priority of a media asset using a continuous listening device. The system may receive an audio clip of a conversation a user, and then determine whether that conversation relates to any of the programs recorded or scheduled to be recorded on a storage device associated with the user. In response to determining that the media asset does relate to one of the programs recorded or scheduled to be recorded on the storage device, a user profile may be consulted to determine past instances of the user discussing the media asset, and, if a measure of the total number of instances the user discussed the media asset meets a threshold measure, the priority of the media asset may be updated.

Abstract: An optimal listening position for the multi-channel audio sound system is determined. A listening area and other audio playback controls may also be defined or modified by a listener. During subsequent audio playback, an imager captures images of at least a portion of the listener. When the listener has moved to a position that is different from a previous position, one or more audio parameters are adjusted for at least one channel in the multi-channel audio system in order to reposition the initial or previous optimal listening position to the current position of the listener. When the listener moves outside the listening area, an out of bounds response is initiated to disable or control the audio playback until the listener moves to a position within the listening area.

Abstract: A remote controller and a power control method are disclosed. The remote controller includes a voice recognizer a voice recognizer configured to recognize a voice utterance, a user interface configured to receive a user command; and a controller configured to, when a user command is input through the user interface to enter a voice recognition mode, convert a stand-by mode into an active mode, and convert the active mode into the stand-by mode depending on whether the utterance is recognized within a preset critical time. Accordingly, the remote controller, enabling an operation mode of a voice recognition module which recognizes a user voice utterance to be maintained as an active mode, can reduce power unnecessarily consumed.

Abstract: A circuit and method is disclosed for filtering an audio signal. The circuit has a first quadrature source and multipliers for multiplying the input signal by the I and Q outputs of the quadrature source. The multiplied inputs are then passed through a pair of low pass filters, which may have an adjustable Q factor. The outputs of the low pass filters are then multiplied in a second pair of multipliers by the I and Q outputs, respectively, of a second quadrature source, which will typically be of the same frequency, but different amplitude and phase, of the first quadrature source. The twice-multiplied signals are then summed by an adder to provide an output signal. The circuit may be modified to include a companding circuit between the low pass filters and the second pair of multipliers that determines the amplitude of the input signal, filters it, and compands the signal in a compandor. The compandor may have adjustable parameters.

Abstract: An audio signal enhancement method includes: acquiring an audio signal; estimating a signal-to-noise ratio (SNR) of an audio frame of the audio signal; determining a SNR threshold for the audio frame; selecting an audio signal processing technique according to a comparison of the SNR threshold to the estimated SNR of the audio frame; filtering the audio frame using a Wiener filter applying the selected signal processing technique; and outputting the audio frame filtered using the Wiener filter applying the selected signal processing technique. A first-in, first-out (FIFO) signal processing technique is selected when the estimated SNR of the audio frame is less than the SNR threshold, and a log-energy voice activity detection (VAD) signal processing technique is selected when the estimated SNR of the audio frame is greater than the SNR threshold.

Abstract: Devices that include light assemblies for providing visual feedback to users that operate the electronic devices. In some instances, the devices comprise voice-controlled devices and, therefore, include one or more microphones for receiving audible commands from the users. After receiving a command, for instance, one such voice-controlled device may cause a corresponding light assembly of the device to illuminate in some predefined manner. This illumination may indicate to the user that device has received the command. In other instances, the devices may illuminate the lighting assembly for an array of other purposes. For instance, one such device may illuminate the corresponding light assembly when powering on or off, playing music, outputting information to a user (e.g., via a speaker or display), or the like.

Abstract: A method and apparatus for associating a query to a direction is provided herein. During operation, a virtual partner will attempt to determine a direction the query originated from. When answering the query, the virtual partner will adjust multiple speaker outputs so that the reply is perceived to come from the same direction as the query originated from. Additionally, if another follow-on query is made from a particular direction, the follow-on query will be associated with the prior query originating from the same particular direction.

Abstract: An audio signal classification method and apparatus, where the method includes determining, according to voice activity of a current audio frame, whether to obtain a frequency spectrum fluctuation of the current audio frame and store the frequency spectrum fluctuation in a frequency spectrum fluctuation memory, and updating, according to whether the audio frame is percussive music or activity of a historical audio frame, frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory, and classifying the current audio frame as a speech frame or a music frame according to statistics of a part or all of effective data of the frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory.

Abstract: A voice interaction architecture has a hands-free, electronic voice controlled assistant that permits users to verbally request information from cloud services. The voice controlled assistant may be positioned in a room to receive voice commands from the user. The voice controlled assistant may also pick up background sources of speech, music, or other noise, such as from a television or stereo system, which may adversely impact the user's intended vocal input to the assistant. The assistant transmits the aggregated audio data (user command and background noise) over a network to the cloud services, which implements noise cancellation functionality to remove the background noise while isolating and preserving the user's command. Once isolated, the cloud serves can process and interpret the user input to perform some function, and return the response over the network to the voice controlled assistant for audible output to the user.

Abstract: An earpiece for use in voice dictation includes a speaker disposed within the earpiece housing, a microphone, and a processor disposed within the earpiece housing and operatively connected to the microphone and the speaker, wherein the processor is adapted to capture a voice stream from the microphone. The earpiece may further include a wireless transceiver disposed within the earpiece housing, the wireless transceiver operatively connected to the processor. The earpiece is configured to be controlled by a user through a plurality of different user interfaces to perform voice dictation.

Abstract: System and methods for providing dynamic positional audio are disclosed. Methods can comprise determining availability of one or more devices to output audio and determining a location of the one or more available devices. Audio information can be received and at least a portion of the audio information can be configured to generate assigned audio information based on the determined location of the available devices. The assigned audio information can be transmitted to the available devices.

Abstract: Background noise estimators and methods are disclosed for estimating background noise in an audio signal. Some methods include obtaining at least one parameter associated with an audio signal segment, such as a frame or part of a frame, based on a first linear prediction gain, calculated as a quotient between a residual signal from a 0th-order linear prediction and a residual signal from a 2nd-order linear prediction for the audio signal segment. A second linear prediction gain is calculated as a quotient between a residual signal from a 2nd-order linear prediction and a residual signal from a 16th-order linear prediction for the audio signal segment. Whether the audio signal segment comprises a pause is determined based at least on the obtained at least one parameter; and a background noise estimate is updated based on the audio signal segment when the audio signal segment comprises a pause.

Abstract: Method and apparatus to determine a speaker activity detection measure from energy-based characteristics of signals from a plurality of speaker-dedicated microphones, detect acoustic events using power spectra for the microphone signals, and determine a robust speaker activity detection measure from the speaker activity measure and the detected acoustic events.

Abstract: A hearing assistance system includes a pair of left and right hearing assistance devices to be worn by a wearer and uses both of the left and right hearing assistance devices to detect the voice of the wearer. The left and right hearing assistance devices each include first and second microphones at different locations. Various embodiments detect the voice of the wearer using signals produced by the first and second microphones of the left hearing assistance device and the first and second microphones of the right hearing assistance device. Various embodiments use outcome of detection of the voice of the wearer performed by the left hearing assistance device and the outcome of detection of the voice of the wearer performed the right hearing assistance device to determine whether to declare a detection of the voice of the wearer.

Abstract: Provided is a speech recognition device that executes a speech recognition method capable of improving speech recognition accuracy. The speech recognition device includes a trigger generation unit for generating a trigger signal on the basis of at least mouth movement and a speech recognition unit which extracts a sound signal on the basis of the trigger signal and starts speech recognition for speech in the extracted sound signal. When the trigger generation unit is generating a trigger signal solely on the basis of opening of the mouth, the trigger generation unit generates the trigger signal so as to precede the opening of the mouth by a predetermined period. Alternatively, when the trigger generation unit is generating a trigger signal on the basis of opening of the mouth and changes in eye orientation, the trigger generation unit generates the trigger signal from the moment any of the above occurs.

Abstract: The systems, devices, and processes described herein may identify a beam of a voice-controlled device that is directed toward a reflective surface, such as a wall. The beams may be created by a beamformer. An acoustic echo canceller (AEC) may create filter coefficients for a reference sound. The filter coefficients may be analyzed to identify beams that include multiple peaks. The multiple peaks may indicate presence of one or more reflective surfaces. Using the amplitude and the time delay between the peaks, the device may determine that it is close to a reflective surface in a direction of the beam.

Abstract: An embodiment provides a method, including: accepting, at an audio receiver of an information handling device, voice input of a user; interpreting, using a processor, the voice input; thereafter receiving, at the audio receiver, repeated voice input of the user; identifying a correction using the repeated voice input; and correcting, using the processor, the voice input using the repeated voice input, wherein the corrective voice input does not include a predetermined voice command. Other aspects are described and claimed.

Abstract: An apparatus, system, and computer readable media for data pre-processing and processing for voice recognition are described herein. The apparatus includes logic to pre-process multi-channel audio data and logic to resolve a source location. The apparatus also includes logic to perform wide range adaptive beam forming, and logic to perform full voice recognition.

Abstract: Apparatus, including a sensor which is configured to be fixed to a neck of an operator of equipment in a location suitable for sensing a voiceless alaryngeal speech vibration generated by the operator during operation of the equipment, The apparatus further includes a processor which is configured to receive and process a signal output by the sensor so as to measure the voiceless alaryngeal speech vibration and so as to generate a control signal for the equipment responsively to the measured voiceless alaryngeal speech vibration.

Abstract: The invention relates to a background noise estimator and a method therein, for supporting sound activity detection in an audio signal segment. The method comprises reducing a current background noise estimate when the audio signal segment is determined to comprise music and the current background noise estimate exceeds a minimum value. This is to be performed when an energy level of an audio signal segment is more than a threshold higher than a long term minimum energy level, lt_min, which is determined over a plurality of preceding audio signal segments, or, when the energy level of the audio signal segment is less than a threshold higher than lt_min, but no pause is detected in the audio signal segment.

Abstract: The invention provides a new method to supply a power to a device which is used by connecting to a mobile terminal. The invention also provides a connective device which is connected and enables the mobile terminal to reproduce contents such as music on the mobile terminal. The connective device stores unique identifying information and is detachably connected to the mobile terminal provided with a communication function. The connective device is having a plug terminal connected to an earphone socket of the mobile terminal, and the plug terminal acquires a power from an audio output channel of the earphone socket and output the identifying information via a microphone channel of the earphone socket.

Abstract: A hands-free audio system for a vehicle and method of using the system is described. The method includes controlling the directionality of a vehicle microphone. The steps of the method may include: (a) receiving a sensor value from at least one of a vehicle seat position sensor, a vehicle seat orientation sensor, or a vehicle mirror orientation sensor; (b) based on the received sensor value(s) of step (a), determining an origin of a vehicle user's speech; and (c) controlling the microphone sensitivity directionality based on the determined origin.

Abstract: Embodiments of the present invention disclose a data interface configuration method and a terminal device. The configuration method includes: receiving, by a second device, an application program command word sent by a first device; parsing the application program command word, to obtain a type of a function module corresponding to the application program command word according to a preset mapping relationship; and connecting a data interface to a corresponding function module according to a parsing result; where the data interface is a data interface on the second device, and the function module is a function module in the second device. By using solutions provided by the present invention, a terminal device may automatically configure a data interface according to an application program that currently needs to be run on a computer side.

Abstract: An audio device may include an electrical terminal for coupling a transducer device to the audio device and an audio circuit for generating an analog audio signal coupled to the electrical terminal. The audio circuit may include a pre-amplifier stage, an amplifier, and a gain selector. The pre-amplifier stage may apply a selectable gain to an audio input signal to generate a pre-amplified analog audio signal, wherein the pre-amplifier stage is powered by a first power supply. The amplifier may amplify the pre-amplified analog audio signal to generate the analog audio signal, wherein the amplifier is powered from a second power supply isolated from the first power supply. The gain selector may select the selectable gain based on a level of the first power supply, such that a difference between the second power supply and the analog audio signal is more than a predetermined headroom threshold voltage.

Abstract: An example information processing device determines a sound input to a microphone. The information processing device includes an obtaining section, a mean amplitude calculation section, and a determination section. The obtaining section obtains data of a sound detected by the microphone. For a sound of a predetermined determination segment, the mean amplitude calculation section calculates a mean amplitude, which is an average amplitude, for each of a plurality of partial segments included in the determination segment. The determination section determines whether or not the sound input to the microphone is a predetermined type of a sound (e.g., a sound made by breath blowing) based on the mean amplitudes for the partial segments.

Abstract: A system for reproducing synthetic engine sound in at least one listening position of a listening room is described. In accordance an example of, the system includes a model parameter database including various pre-defined sets of model parameters. An engine sound synthesizer receives at least one guide signal and is configured to select one set of model parameters in accordance with the at least one guide signal. The engine sound synthesizer generates a synthetic engine sound signal in accordance with the selected set of model parameters. At least one loudspeaker is used for reproducing the synthetic engine sound. The system further includes one of the following: (1) an equalizer and (2) a model parameter and the effect of the listening room on the resulting acoustic signal is approximately compensated at the one listening position.

Abstract: An apparatus and a corresponding method for voice processing are provided. The apparatus includes a sound receiver, a camera, and a processor. The sound receiver receives a sound signal. The camera takes a video. The processor is coupled to the sound receiver and the camera. The processor obtains a voice onset time (VOT) of the sound signal, detects a human face in the video, detects a change time of a mouth contour of the human face, and verifies at least one preset condition. When all of the preset conditions are true, the processor performs speech recognition on the sound signal. The at least one preset condition includes that a difference between the VOT and the change time is smaller than a threshold value.

Abstract: Some embodiments of the present invention provide a method of adjusting an output of a media player comprising capturing an ambient audio signal; processing the ambient audio signal to determine whether one or more characteristic forms are present within the ambient audio signal; and reducing an output of a media player from a first volume to a second volume if the one or more characteristic forms are present within the ambient audio signal. The characteristic forms may be, for example, a name or personal identifier of a user of the media player, the voice of a user of the media player, or an alarm or siren.

Abstract: Apparatus and methods to implement a technique for using voice input to control a network-enabled device. In one implementation, this feature allows the user to conveniently register and manage an IPTV device using voice input rather than employing a bulky remote control or a separate registration website.

Abstract: Appliance systems and methods for using visual cues to improve appliance audio recognition are provided. One example method performed by an appliance includes identifying one or more visual cues included in imagery captured by a camera of the appliance. The one or more visual cues indicate that a user of the appliance is seeking to provide a voice command to the appliance. The method includes communicating with one or more devices over a network to reduce background noise associated with the one or more devices upon identifying the one or more visual cues. The method includes receiving the voice command from the user. The method includes determining that the user has finished providing the voice command. The method includes communicating with the one or more devices over the network to resume standard operations upon determining that the user has finished providing the voice command.

Abstract: A method and system for improved audio quality in teleconferencing are provided. The method includes analyzing the audio signal of multiple input lines in a teleconferencing system to detect if any two input lines contain substantially the same audio signal with a delay shorter than that of a conventional echo caused by an input line's own audio feedback via a teleconferencing server. The method further includes selecting the input line with the higher amplitude audio signal or the earlier received audio signal when two input lines with substantially the same audio signal are detected.

Abstract: An audio signal processing circuit and an electronic device are provided. A noise detection circuit determines if the first input audio signal and a second input audio signal contain noise. The noise cancellation circuit (i), when no noise is detected, outputs a first intermediate audio signal corresponding to the first input audio signal and a second intermediate audio signal corresponding to the second input audio signal without detected noise; (ii) when noise is detected, generates a third intermediate audio signal after performing a specific noise modification process upon the first input audio signal and the second input audio signal, and outputs the first intermediate audio signal including the third input audio signal and the second intermediate audio signal including the third input audio signal. A beamforming circuit performs a beamforming process according to a differential signal of the first intermediate audio signal and the second intermediate audio signal.

Abstract: Described herein is a microphone assembly for an electronic device incorporating a microphone. The microphone assembly includes a microphone interface that enables direct coupling of inputs from the microphone to a preamplifier. For the purpose, the microphone interface includes a DC servo loop. The DC servo loop provides a DC path for supplying a DC bias current to the microphone and an AC path to receive the AC output obtained from the microphone. The AC path and the DC path allow separation of the AC output of the microphone from the DC bias current. The microphone interface is implemented using reduced number of IC pin interfaces and external components to achieve compactness of the device.

Abstract: A device including a processor and a memory is disclosed. The memory includes programming instructions which when executed by the processor perform an operation. The operation includes detecting relative position of two earphones when connected to the device, determining if a binaural signal processing mode is appropriate based on the detected relative position and switching to the binaural signal processing mode. If it is determined that the binaural signal processing mode is not appropriate, switching to monaural processing mode.

Abstract: An input from a manually initiated action within a computing system can be received. The system can be associated with a speech component. The input can be associated with a system function. The function can be an operation within the computing system and can be linked to a function identifier. The identifier can be translated to a command data. The command data can be associated with a command identifier, a command, and an alternative command. The command data can be a speech command registered within the speech component. The command data can be presented within a speech interface responsive to the translating. The speech interface can be associated with the speech component.

Abstract: Various energy harvesting and control techniques are used to power and control electronic accessories from the audio output channels and microphone input channel of mobile digital devices while preserving audio input and output functionality. One technique uses one of the stereophonic audio channels to generate power, and the other in conjunction with the microphone jack to enable bi-directional communications while preserving audio input and output. Another technique allows a low powered electronic accessory with bi-directional communications to be supported while simultaneously supporting audio input & stereo output. These techniques facilitate the ability to play music, narration and instruction and to receive oral responses and instruction with no perceived loss or gaps, even while using the audio jack of a mobile digital device to harvest energy and bi-directional communication.

Abstract: An audio device may be configured to produce output audio and to also capture input audio for speech recognition. Beamforming may be used to produce directional audio signals that emphasize sounds received from different directions. Acoustic echo cancellation (AEC) may be used to remove components of output audio from the directional input signals. AEC may be implemented by an adaptive filter based on dynamically optimized filter coefficients. The filter coefficients may be analyzed to detect the presence of potentially problematic reflective surfaces near the audio device. When such a reflective surface is detected, the user may be notified by illuminating a directional indicator on a housing of the audio device, where the directional indicator indicates the direction of the potentially problematic surface relative to the audio device.

Abstract: Provided is a remote control comprising a housing, a keyboard (20) mounted on the housing, a processor (106) electrically connected to the keyboard (20), an analog-digital converter (103) and a high-frequency wireless transmission unit (108) electrically connected to the processor (106), a sampling circuit (102) electrically connected to the analog-digital converter (103) and a microphone interface (30) electrically connected to the sampling circuit (102). Also disclosed is a television system. The remote control and television system in the present solution are simple to operate and can satisfy user's multi-function requirements.

Abstract: A security system can be used to trigger appliances. The security system can comprise a light socket camera that can be rotatably attached to a light socket of a building. The light socket camera can receive an audible instruction from a user, and in response to receiving the audible instruction from the user, the security system can trigger the appliance to perform an operation.

Abstract: A signal processing apparatus feeding a frame of a signal in frequency domain of a reception voice signal into a sound echo canceler includes a first reception section for receiving frames of the reception voice signal in frequency domain before having a rate-of-speech change process applied; a second reception section for receiving frames of a signal in time domain having the rate-of-speech change process applied by units of frames; and a frequency-domain frame synthesis section for synthesizing a frame of the signal in frequency domain of the reception voice signal based on the signal in time domain having the rate-of-speech change process applied at a frame currently being processed by the signal processing apparatus, and a frame of the reception voice signal in frequency domain corresponding to the signal in time domain having the rate-of-speech change process applied.

Abstract: The present invention discloses a flat speaker output device and a method for starting the same. Wherein, a plurality of flat speakers utilizes an initial delay unit and a plurality of intermediary delay units connected in series. The initial delay unit connects with the power controller and a first one of the flat speakers. The intermediary delay units respectively connect with the residual each flat speakers. The power controller controls a power source to the initial delay unit to delay the start of the first one of flat speakers, and outputs the power source to the intermediary delay units to sequentially delay the starts time of the residual each flat speaker. The present invention can sequentially start flat speakers without using a high-output power supply device and thus decrease the required capacity of the external power supply device.

Abstract: Remote surveillance systems can include an outward portion that faces away from a power outlet and can include an inward portion with electrical prongs that protrude into the power outlet. The power outlet can mechanically support the inward portion and a camera assembly. The remote surveillance system can take videos using the camera and can send the videos to a remotely located computing device.

Abstract: A system and method of operating an automatic speech recognition application over an Internet Protocol network is disclosed. The ASR application communicates over a packet network such as an Internet Protocol network or a wireless network. A grammar for recognizing received speech from a user over the IP network is selected from a plurality of grammars according to a user-selected application. A server receives information representing speech over the IP network, performs speech recognition using the selected grammar, and returns information based upon the recognized speech. Sub-grammars may be included within the grammar to recognize speech from sub-portions of a dialog with the user.