Abstract: Technologies are generally described for systems and methods effective to output video content. In some examples, a content output device may be effective to receive a first request for first video content including a first identifier and a first category. The device may receive a zoom selection for the first video content including a first zoom level assigned to the first video content. The selection may be based on the first identifier or the first category. The device may store the zoom selection in a memory and receive a second request for second video content including a second identifier and a second category. The device may analyze the memory to determine a second zoom level for the second video content based on the first zoom level and the first identifier or the first category. The device may output the second video content at the second zoom level.

Abstract: A method and apparatus for integrating a personal information device (PID) on a mobile computer that includes activating a first mode to display data originating with the PID in a first display area of a display. The mobile computer switches to a second mode to display data associated with the second mode in a second display area of the display.

Abstract: The stereoscopic image display includes a control voltage generator and a control voltage compensator. The control voltage generator generates a discharge control voltage to be applied to a discharge control line at a slight-on level, which is higher than a gate low voltage and is lower than a gate high voltage, and periodically reduces the discharge control voltage to a level of the gate low voltage in the 3D mode. The control voltage compensator receives the discharge control voltage from the control voltage generator, amplifies a feedback discharge control voltage supplied from a first part of a display panel based on the received discharge control voltage, and applies the amplified feedback discharge control voltage, as a compensated discharge control voltage, to a second part opposite the first part of the display panel.

Abstract: Provided is a display device including: a display panel, a timing controller, a gate driver, and a data driver. The display panel includes a display area configured to display an image and a non-display area adjacent to one side of the display area. The display area includes oblique lines, intersectional lines crossing and isolated from at least a part of the oblique lines, and pixels. Pixels coupled to the oblique lines or the intersectional lines and arranged along a line in one direction are defined into pixel rows. The display area further includes a plurality of areas divided by the pixel rows being successive. The number of pixels constituting one of adjacent ones of the pixel rows in at least one of the plurality of areas is different from the number of pixels constituting another thereof.

Abstract: A system and method of driving images on displays includes receiving image content in a processing unit. When a peak data condition is identified, pixel rows of at least one display are updated in a non-sequential order in response to identifying the peak data condition.

Abstract: A display controller device for processing image data has a data processor for generating a display signal. The device has a writeback unit having an input coupled to the display signal and an output coupled to a debug interface. The writeback unit has a slice controller for defining a set of slices of the image and consecutively selecting slices of the set, and a slice selector for sampling pixel data from a selected slice. A slice buffer is coupled between the slice selector and the debug output for temporarily storing the selected pixel data. The slice controller transfers the selected pixel data to the debugger and subsequently selects a next slice until all slices of the set have been transferred. The debug system receives the slices and regenerates and displays the image.

Abstract: A server receives and analyzes analytics data from an application of one or more devices. The application corresponds to a content generator. The server generates, using the content generator, a visualization content dataset based on the analysis of the analytics data. The visualization content dataset comprises a set of images, along with corresponding analytics virtual object models to be engaged with an image of a physical object captured with the one or more devices and recognized in the set of images. The analytics data and the visualization content dataset may be stored in a storage device of the server.

Abstract: A dynamically reconfigurable heterogeneous systolic array is configured to process a first image frame, and to generate image processing primatives from the image frame, and to store the primatives and the corresponding image frame in a memory store. A characteristic of the image frame is determined. Based on the characteristic, the array is reconfigured to process a following image frame.

Abstract: Techniques are disclosed relating to asymmetric circuits. In some embodiments, a storage element is configured to maintain a first input value as an input to an asymmetric circuit during a time interval. For example, in one embodiment, the time interval may correspond to a frame of video data and the storage element may be configured to store a filter coefficient for the frame of video data. In some embodiments, the storage element may be configured to store the value as a constant for multiple operations by the asymmetric circuit. In some embodiments, the asymmetric circuit is configured to generate a plurality of output values based on the first input value and respective ones of a set of second input values. In some embodiments, the asymmetric circuit is leakage power asymmetric and/or critical path asymmetric. This may increase performance and/or reduce power consumption.

Abstract: A hammer device of an electronic piano with keys which swing in accordance with key depression, includes a hammer support that is made of a synthetic resin and has a fulcrum shaft, and a hammer having a shaft hole part for being fitted on the fulcrum shaft and configured to pivotally move about the fulcrum shaft in a manner interlocked with the swinging key. The fulcrum shaft has an outer peripheral surface formed by a pair of arcuately-curved surface portions opposite to each other and a pair of planar surface portions each extending between the pair of arcuately-curved surface portions and parallel to each other.

Abstract: Embodiments of the present disclosure relate generally to guitars or other string instruments that incorporate materials that are lighter than wood. Rather than achieving weight reduction by solely removing wood, which can weaken the structural integrity of the guitar and negatively alter sound quality, this disclosure provides replacement of removed wood with materials commonly used in aerospace.

Abstract: A string bender includes a base portion configured to anchor a plurality of strings and to be removably (or releasably) mounted to a guitar body without requiring drilling or cutting of the guitar body. The string bender can also include at least one bar extending from the base portion in a direction substantially toward a top of the guitar body, the at least one bar being attached to at least one corresponding cam and disposed so as to be able to rotate relative to the base portion such that a rotation of the at least one bar causes a rotation of the cam and a change in tension of a string associated with the cam. The string bender can be constructed to bend one or more strings, for example the B and/or G strings. The string bender can also be constructed to fit a variety of guitar styles, such as the Gibson Les Paul-style and the Fender Telecaster-style guitars.

Abstract: A drum counterhoop clamping device, which is to be fixed to a drum counterhoop, comprises a base, a clamping block and a locking member. The base includes a sliding chute and a first clamping plate extending outward and vertically to the sliding chute. The clamping block includes a sliding post slidably installed inside the sliding chute and a second clamping plate extending outward and vertically to the sliding post. The first clamping plate and the second clamping plate are disposed corresponding to each other. The locking member drives the base and the clamping block to approach to each other and enforces the sliding post to pass through the sliding chute to decrease the distance between the first clamping plate and the second clamping plate. Thereby, the present invention uses the plane-like first clamping plate and second clamping plate to increase stability and strength of clamping the drum counterhoop.

Abstract: A system and method for rendering music is provided. The method includes: receiving a request for electronic content; parsing the electronic content to determine a music notation element; translating the music notation; creating a music notation object based on the translation; and rendering the music notation object via a browser application. The system includes: a connection module configured to receive a request for electronic content; a parser configured to parse the electronic content to determine a music notation element; an object module configured to translate the music notation and create a music notation object based on the translation; and a rendering module configured to render the music notation object to be displayed by a browser application.

Abstract: The present invention discloses a guitar hanger apparatus, including a fixed base and a hanger body fixedly connects to the fixed base; the fixed hanger body further includes a fixing holder, applied to support the guitar and move down following the weight of the guitar, a self-locking mechanism connecting to and driven by the fixing holder; the self-locking mechanism comprises rotating shaft assemblies, built in the main body of the hanger, and swing arms connecting to the rotating shaft assemblies; the fixed holder comprises positioning casts, applied to fix the guitar, while a driving unit is arranged in the positioning cast, applied to drive the rotating shaft assemblies. The present invention achieves fixation and protection to a guitar by the weight of the guitar, which has a simple structure, and enables mass production thus brings benefits to the manufacturer.

Abstract: An automatic composition apparatus includes a processing unit. The processing unit performs a note pitch shift process, a matching-level calculating process and a melody generating process. The note pitch shift process performs pitch shift on pitches of individual note data items included in an input phrase. The matching-level calculating process calculates a matching level between a phrase including note data items subjected to the pitch shift and a designated chord progression data item, with reference to a plurality of note connection rules each of which defines a connection relation of consecutive note types, if the pitch shift is performed. The melody generating process generates a melody based on the phrase which includes the note data items subjected to the pitch shift and which is selected based on the calculated matching level.

Abstract: A multimedia apparatus, a music composing method thereof, and a song correcting method thereof are provided. A music composing method includes setting a type of musical instrument digital interface (MIDI) data according to a user's input, sensing a user interaction, analyzing the sensed user interaction and determining a beat and a pitch of the user interaction, and generating MIDI data using the set type of MIDI data and the determined beat and pitch.

Abstract: A music generating system comprising sensors configured to acquire data sets related to physiological and environmental condition of a user and a computing device comprising a processor and a memory. The computing device is configured to read, by a data acquisition module, the data sets received from the sensors, to perform, by a data analysis module, a value range analysis of the data sets received to normalize the data sets, to map, with the help of the data analysis module, each of the normalized data sets to families of sounds stored in a data store, to create, by the data analysis module, individual music pieces on the basis of a time series analysis and a frequency analysis of the normalized data sets mapped to the families of sounds and to merge, by a music generation module, the individual music pieces to create a final piece of music.

Abstract: The hammer union pressure transducer engages with a cinch nut of a hammer union coupling to cinch a nose end toward an internal sealing surface of a male component of the hammer union coupling. The transducer includes a connection end removably threaded to the nose end. An anti-rotation device engages the connection end and the nose end, inhibiting inadvertent unthreading. The anti-rotation device is removable or shearable, allowing unthreading of the connection end from the nose end as desired. A recess may be formed on the external sealing surface of the nose end and an insert may be disposed in the recess. The insert, if used, may be formed of a material that is different from a material of the nose end. An upgrade kit may also be employed and includes an adapter plate to connect to the nose end.

Abstract: A particulate sound absorption board and its preparation method. The said particulate sound absorption board consists of binding agent and sound absorption particle; the external surface of sound absorption particle is covered with a layer of binding agent, and the angularity coefficient of particle covered with binding agent is less than 1.3; the said sound absorption particle consists of skeleton particle and filling particle, in which the former is used for sound absorption board skeleton, and the latter flows into the pore between skeleton particles to form sound absorption pore, and the average diameter of cross section of sound absorption pore is 0.07 mm. The two-stage manufacturing technology (i.e. coating, curing and then shaping) is adopted for the said preparation method to prevent the pore between particles from being blocked by excess binding agent, and further improve the angularity coefficient of particle.

Abstract: A sandwich panel including a core having a first major side and an opposed second major side, the core defining cavities, a first liner sheet connected to the first major side, the first liner sheet defining apertures, wherein each aperture provides fluid communication with an associated cavity, and a bulk absorber material and/or a thermal conductor material received in at least a portion of the cavities.

Abstract: A particulate sound absorption board used for sound absorption surface layer of sound absorption/insulation board is a micropore particle board formed by splicing skeleton particles and filling particles which are covered with binding agent on the surface and have small angularity coefficient. The particulate sound insulation board used for sound insulation surface layer of sound absorption/insulation board is a compressed board formed by closely splicing skeleton particles, filling particles, binding agent and coupling agent, and there is a resonance sound absorption cavity that functions together with sound absorption surface layer in the board body. The particulate sound barrier consists of column and more than two overlapped sound absorption/insulation boards fixed between adjacent columns. A convex-concave joint end face is set on the sound absorption/insulation board, and the sealing cushion is bound between adjacent end faces.

Abstract: An arrangement comprising a plurality of attenuators for attenuating acoustic waves, each attenuator of the plurality of attenuators comprising: a first body defining a cavity therein and at least one open aperture extending across a portion of the first body, the first body being configured to attenuate acoustic waves over a resonant frequency band.

Abstract: A system for reducing noise emissions in underwater environments is presented. The system can be extended to applications in any two-fluid environments where one fluid (gas) is contained in an enclosed resonator volume connected to the outside environment at an open end of the resonator body. The resonators act as gas-containing (e.g., air) Helmholtz resonators constructed into solid panels that are submerged in the fluid medium (e.g., sea water) in the vicinity of a noise generating source. The oscillations of the trapped air volume in the resonators causes reduction of certain noise energy and a general reduction in the transmitted noise in the environment of the system.

Abstract: An anti-noise signal is produced in accordance with an active noise cancellation process (ANC), at an input of a speaker so as to control how much background noise a user can hear. Strength of the anti-noise signal is adjusted gradually, rather than abruptly, in proportion to decreasing or increasing sound pressure level (SPL) of the background noise, during inactivation or activation of the ANC process. Other embodiments are also described and claimed.

Abstract: An adaptive filter of an adaptive blocking matrix in an adaptive beam former or null former may be modified to track and maintain noise correlation between an input and a reference noise signal to the adaptive noise canceller module. That is, a noise correlation factor may be determined, and that noise correlation factor may be used in an inter-sensor signal model applied when generating the blocking matrix output signal. The output signal may then be further processed within the adaptive beamformer to generate a less-noisy representation of the speech signal received at the microphones. The inter-sensor signal model may be estimated using a gradient decent total least squares (GrTLS) algorithm. Further, spatial pre-whitening may be applied in the adaptive blocking matrix to further improve noise reduction.

Abstract: An active noise control apparatus for a vehicle including: a plurality of microphones each configured to receive noise generated in the vehicle and generate an electrical signal corresponding to the noise; an external amplifier configured to supply power required for operations of the plurality of microphones; and a head unit configured to control the external amplifier to output a signal for removing the noise, based on the electrical signals generated from the plurality of microphones.

Abstract: An ultrasonic sensor and method for using the same are arranged for capturing a value document transported through a capture region of the ultrasonic sensor. The ultrasonic sensor has an ultrasound transmitter arranged for emitting ultrasound into the capture region and an ultrasound receiver arranged for receiving ultrasound from the ultrasound transmitter from the capture region. A control and evaluation circuit is arranged for controlling the ultrasound transmitter and for capturing and evaluating the signals of the ultrasound receiver. A circuit carrier carries the control and evaluation circuit, the ultrasound transmitter, the ultrasound receiver, and conducting paths electrically connecting the control and evaluation circuit to the first and second ultrasonic transducers. The circuit carrier has a U-shaped configuration and two interconnected arm portions, and the ultrasound transmitter is held on one of the two arm portions and the ultrasound receiver on the other of the two arm portions.

Abstract: The present invention relates to a method of manufacturing a capacitive micro-machined transducer (100), in particular a CMUT, the method comprising depositing a first electrode layer (10) on a substrate (1), depositing a first dielectric film (20) on the first electrode layer (10), depositing a sacrificial layer (30) on the first dielectric film (20), the sacrificial layer (30) being removable for forming a cavity (35) of the transducer, depositing a second dielectric film (40) on the sacrificial layer (30), depositing a second electrode layer (50) on the second dielectric film (40), and patterning at least one of the deposited layers and films (10, 20, 30, 40, 50), wherein the depositing steps are performed by Atomic Layer Deposition. The present invention further relates to a capacitive micro-machined transducer (100), in particular a CMUT, manufactured by such method.

Abstract: An ultrasonic transmitter of an ultrasonic occupancy sensing device has adjustable ultrasonic signal output amplitude to prevent overload of an ultrasonic sensor associated with the ultrasonic occupancy sensing device. A circuit for controlling the operating voltage to a power driver of the ultrasonic transmitter allows field adjustment of the output thereof so that an optimal level (amplitude) for the transmitted ultrasonic signal may be found in an area of actual use (e.g., field adjustable).

Abstract: A method for voice based diagnostics can include receiving a voice command from a user at a computing device, performing, by the computing device, a number of diagnostic tests corresponding to a functionality of the computing device, and sending an audio message to the user, wherein the audio message corresponds to results of the number of diagnostic tests.

Abstract: Disclosed are embodiments for use in an articulatory-based text-to-speech conversion system configured to establish an articulatory speech synthesis model of a person's voice based on facial characteristics defining exteriorly visible articulatory speech synthesis model parameters of the person's voice and on a predefined articulatory speech synthesis model selected from among stores of predefined models.

Abstract: A device may receive an input indicative of acoustic feature parameters associated with speech. The device may determine a modulated noise representation for noise pertaining to one or more of an aspirate or a fricative in the speech based on the acoustic feature parameters. The aspirate may be associated with a characteristic of an exhalation of at least a threshold amount of breath. The fricative may be associated with a characteristic of airflow between two or more vocal tract articulators. The device may also provide an audio signal indicative of a synthetic audio pronunciation of the speech based on the modulated noise representation.

Abstract: According to the present invention there is provided a method for automatically converting text-based information and content to video form. In one embodiment of the invention the method creates a video which preserves the main idea of a given input text, and is adapted to convey the essence of the text. According to the invention data is extracted from the input text and from other sources of information relevant to it, so that the text can be analyzed as a whole and with respect to its main content. After extracting all the possible data, the text is semantically analyzed, summarized and converted to a video as a configuration file.

Abstract: Technologies for natural language interactions with virtual personal assistant systems include a computing device configured to capture audio input, distort the audio input to produce a number of distorted audio variations, and perform speech recognition on the audio input and the distorted audio variants. The computing device selects a result from a large number of potential speech recognition results based on contextual information. The computing device may measure a user's engagement level by using an eye tracking sensor to determine whether the user is visually focused on an avatar rendered by the virtual personal assistant. The avatar may be rendered in a disengaged state, a ready state, or an engaged state based on the user engagement level. The avatar may be rendered as semitransparent in the disengaged state, and the transparency may be reduced in the ready state or the engaged state. Other embodiments are described and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Abstract: The present invention provides a terminal, comprising: a voice recognition unit for recognizing a voice during a call and generating recognition data; a first acquisition unit connected to the voice recognition unit and used for acquiring information correlated with the recognition data; and a display unit connected to the first acquisition unit and used for displaying the correlated information. The present invention also provides a server and an information pushing method. Through the technical schemes of the present invention, information correlated with the call content can be automatically and rapidly acquired according to the call content and presented to a user, thus facilitating timely referring of the user.

Abstract: A method and an apparatus for classifying spoken content in a teleconference for a follower of the teleconference is disclosed. The method comprises: detecting a topic to which the spoken content belongs; determining a (overall) correlation degree between the follower and the spoken content at least according to a correlation degree between the follower and the topic; and classifying the spoken content according to the (overall) correlation degree between the follower and the spoken content. With the method and the apparatus, the correlation degree between the spoken content in the teleconference and the follower of the teleconference can be determined automatically, and the spoken content can be classified according to the correlation degree, so that the follower can selectively pay attention to some spoken contents during the teleconference, which reduces a burden of the follower and improves conference efficiency.

Abstract: A spoken language understanding (SLU) system receives a sequence of words corresponding to one or more spoken utterances of a user, which is passed through a spoken language understanding module to produce a sequence of intentions. The sequence of words are passed through a first subnetwork of a multi-scale recurrent neural network (MSRNN), and the sequence of intentions are passed through a second subnetwork of the multi-scale recurrent neural network (MSRNN). Then, the outputs of the first subnetwork and the second subnetwork are combined to predict a goal of the user.

Abstract: An automated arrangement is described for conducting natural language interactions with a human user. A user interface is provided for user communication in a given active natural language interaction with a natural language application during an automated dialog session. An automatic speech recognition (ASR) engine processes unknown user speech inputs from the user interface to produce corresponding speech recognition results. A natural language concept module processes the speech recognition results to develop corresponding natural language concept items. A concept item storage holds selected concept items for reuse in a subsequent natural language interaction with the user during the automated dialog session.

Abstract: A method for adapting a speech recognition system for out-of-vocabulary, comprising, decoding by a hybrid speech recognition a speech including out-of-vocabulary terms, thereby generating graphemic transcriptions of the speech with a mixture of recognized in-vocabulary words and unrecognized sub-words, while keeping a track of the decoded segments of the speech, determining in the transcription sequences of sub-words as candidate out-of-vocabulary words based on a first condition with respect to lengths of the sequences of sub-words and a second condition with respect to the number of repetitions of the sequences, audibly presenting to a user the candidate out-of-vocabulary words from the corresponding segments of the speech according to the track, and receiving from the user indications of valid words corresponding to audible presentations of the sequences of sub-words in the candidate out-of-vocabulary words, and training a speech recognition to additionally recognize the candidate out-of-vocabulary words,

Abstract: Embodiments of the present invention provide a voice identification method, including: obtaining voice data; obtaining a first confidence value according to the voice data; obtaining a noise scenario according to the voice data; obtaining a second confidence value corresponding to the noise scenario according to the first confidence value; and if the second confidence value is greater than or equal to a pre-stored confidence threshold, processing the voice data. An apparatus is also provided. The method and apparatus that flexibly adjust the confidence value according to the noise scenario greatly improve a voice identification rate under a noise environment.

Abstract: Embodiments of techniques or systems for fraud detection are provided herein. A communication may be received where the communication includes one or more voice signals from an individual. Frequency responses associated with these voice signals may be determined and analyzed and utilized to determine whether or not potential fraudulent activity is occurring. For example, if a frequency response is greater than a frequency threshold, potential fraudulent activity may be determined. Further, frequency responses may be cross referenced with voice biometrics, voice printing, or fraud pathway detection results. In this way, voice stress or frequency responses may be utilized to build other databases related to other types of fraud detection, thereby enhancing one or more aspects of fraud detection. For example, a database may include a voice library, a pathway library, or a frequency library which include characteristics associated with fraudulent activity, thereby facilitating identification of such activity.

Abstract: Systems and methods for determining an identity of an individual are provided. Audio may be received that includes a key phrase spoken by the individual, and the key phrase may include an identifier spoken by the individual. A key phrase voice print and key phrase text corresponding to the audio may be obtained. The key phrase text may include text corresponding to the identifier spoken by the individual. Voice prints may be retrieved based on the text corresponding to the identifier, and the voice prints may be provided to a voice biometric engine for comparison to the key phrase voice print. The individual may be authenticated based on a comparison of the key phrase voice print to the voice prints. The identifier may include a first name and a last name of the individual.

Abstract: An audio-signal processing device includes a decoding unit that decodes a compressed audio stream to obtain audio signals for a predetermined number of channels; a signal processing unit that generates 2-channel audio signals including left-channel audio signals and right-channel audio signals, on the basis of the predetermined-number-of-channels audio signals; and a coefficient setting unit that sets filter coefficients corresponding to the impulse responses for the digital filters, on the basis of format information of the compressed audio stream. The signal processing unit uses digital filters to convolve impulse responses for paths from sound-source positions of the channels to the left and right ears of a listener with the corresponding predetermined-number-of-channels audio signals and adds corresponding results of the convolutions for the channels to generate the left-channel audio signals and the right-channel audio signals.

Abstract: Following transmission of a watermarked audio signal over an acoustic path causing echoes, reverberation and/or noise, watermark detection correlation result peak values are concentrated within a limited temporal range around main correlation result peaks, which limited temporal range is much smaller than the total correlation length. The watermark detection is based on the following: given np correlation result peak values v=(v1, v2, . . . , vnp) in an average or expected probability distribution for correlation result values for unmarked content, the probability is calculated that within windows covering the limited temporal range there are np or more values from a correlation result value set greater than or equal to these peaks v.

Abstract: A system for encoding and applying Dynamic Range Control/Compression (DRC) gain values to a piece of sound program content is described. In particular, a set of DRC gain values representing a DRC gain curve for the piece of content may be divided into frames corresponding to frames of the piece of content. A set of fields may be included with an audio signal representing the piece of content. The additional fields may represent the DRC gain values using linear or spline interpolation. The additional fields may include 1) an initial gain value for each DRC frame, 2) a set of slope values at particular points in the DRC curve, 3) a set of time delta values for each consecutive pair of slope values, and/or 4) one or more gain delta values representing changes of DRC gain values in the DRC gain curve between points of the slope values.

Abstract: Systems and methods are provided for audio encoding. For example, first quantization encoding is performed on audio data associated with a current frame of an audio data stream to obtain first quantization-encoded data; second quantization encoding is performed on the audio data to obtain second quantization-encoded data; the first quantization-encoded data is coupled to the current frame of the audio data stream; and the second quantization-encoded data is coupled to a next frame of the audio data stream.

Abstract: A reconfigurable filter bank system that has an asymmetrical tree structure with multiple stages to generate multiband outputs. Each stage may include cascaded low-pass filters (LPFs), cascaded high-pass filters (HPFs) and/or all-pass filter(s) (APF(s)) having identical phase responses. As the cascaded LPFs, cascaded HPFs and APF(s) have identical phase responses, each frequency band of the multiband output may have an identical phase shift such that the frequency bands are in-phase and can be added together. The multiband outputs of the reconfigurable filter bank may have near-perfect reconstruction (e.g., small number of cross-band ripples) and therefore only minor distortion. In addition, the number of frequency bands and corresponding non-uniform bandwidths (e.g., frequency ranges) may be user-adjustable and/or reconfigurable during device operation. Further, the reconfigurable filter bank may have reduced computational complexity and/or latency.

Abstract: Sound enhancement techniques through dereverberation are described. In one or more implementations, a method is described of enhancing sound data through removal of reverberation from the sound data by one or more computing devices. The method includes obtaining a model that describes primary sound data that is to be utilized as a prior that assumes no prior knowledge about specifics of the sound data from which the reverberation is to be removed. A reverberation kernel is computed having parameters that, when applied to the model that describes the primary sound data, corresponds to the sound data from which the reverberation is to be removed. The reverberation is removed from the sound data using the reverberation kernel.