Abstract: Systems and methods for performing localization and mapping with a mobile device are disclosed. In one embodiment, a method for performing localization and mapping with a mobile device includes identifying geometric constraints associated with a current area at which the mobile device is located, obtaining at least one image of the current area captured by at least a first camera of the mobile device, obtaining data associated with the current area via at least one of a second camera of the mobile device or a sensor of the mobile device, and performing localization and mapping for the current area by applying the geometric constraints and the data associated with the current area to the at least one image.

Abstract: A display recording information and generation method thereof are disclosed. The display recording information is used to record the corresponding relationship between the display information received by a driving IC of a display and pixels of the display. The display recording information is formed by one byte (8 bits). Its first bit through six bit record a counting result that a number counter or a column counter performs a six-bit counting on a number of pixels or a number of columns of pixels starting from 0; its seventh bit uses 0 or 1 to record that the counting result belongs to the number of pixels or a number of columns of pixels; its eighth bit uses 1 to record that a most significant bit of the display information including red, green, or blue is 1, otherwise uses 0 to record.

Abstract: Techniques are described for determining a region to be updated in a frame based on positional changes of one layer from frame-to-frame. The positional changes may be displacement of a layer or removal of a layer from one frame to the next. In addition to the information of the positional changes, the techniques also utilize all areas for which the image content changed, but the position did not, for determining the region to be updated.

Abstract: A method for shortening image delay includes, but is not limited to refreshing a current frame image from a frame buffer area to the display screen from top to bottom, and notifying an application to draw next frame image when the current frame image is refreshed to a predetermined row. The method further includes updating content in predetermined rows from top of next frame image drawn by the application to the frame buffer area of the system, and replacing content in the predetermined rows of the current frame image that have already been displayed The method further includes updating the content in the remaining rows of next frame image drawn by the application to the frame buffer area, and replacing content in the remaining rows of the current frame image that have already been displayed.

Abstract: A capo (10) suitable for a twelve string guitar, where string pairs of different gauges are used. The capo (10) includes a clamp arm (11) with a contact surface (12) for contacting the strings that includes a plurality of inclined portions (18) relative to a lateral extent of the clamp arm (11). The nature of the inclined portions (18) is such that adjacent strings (1st to 6th) of different gauges can be contacted with relatively even pressure upon the fingerboard (21).

Abstract: [Problem] To provide a marching drum which ensures forwards and downwards visibility and ensures the field of view during marching. [Solution] [Effect] By eliminating all or some members of the body of the drum, or by adopting transparent members, this marching drum which enables forwards and downwards visibility ensures the performer's field of view during marching.

Abstract: In some implementations, a computing device can be configured to present a graphical user interface that enables the dynamic authoring of music by a user of the computing device. The computing device can present a grid of cells, where each cell represents a music segment. The cells can be configured to playback the music segment once or playback the music segment in a repeating loop. The user can select (e.g., touch) one or more cells in the grid to cause the corresponding music segment to play. While playing selected cells, the user can provide input selecting various musical effects to apply to the playing music. The user can record a dynamically selected sequence of cells and musical effects to create an original musical product.

Abstract: An electrostatic capacitance transducer includes: multiple elements each having a cell including a first electrode, and a vibrating film including a second electrode, formed across a gap from the first electrode; a first flexible printed circuit having multiple first lines; and a second flexible printed circuit having multiple second lines. Part of the multiple elements are grouped into a first element group, each one thereof being electrically connected to a different one of the first lines. Part of the multiple elements other than the first element group are grouped into a second element group, each one thereof being electrically connected to a different one of the second lines. The intervals between adjacent lines in at least part of the plurality of first and second lines are wider at an opposite side from a connection side where the lines have been connected to the multiple elements, than at the connection side.

Abstract: In an active noise reducing headphone, a signal processor applies filters and control gains of both the feed-forward and feedback active noise cancellation signal paths. The signal processor is configured to apply first feed-forward filters to the feed-forward signal path and apply first feedback filters to the feedback signal path during a first operating mode providing effective cancellation of ambient sound, and to apply second feed-forward filters to the feed-forward signal path during a second operating mode providing active hear-through of ambient sounds with ambient naturalness.

Abstract: An exemplary engine noise control includes directly picking up engine noise from an engine of a vehicle at a pick-up position to generate a sense signal representative of the engine noise, and active noise control filtering to generate a filtered sense signal from the sense signal. The control further includes converting the filtered sense signal from the active noise control filtering into anti-noise and radiating the anti-noise to a listening position in an interior of the vehicle. The filtered sense signal is configured so that the anti-noise reduces the engine noise at the listening position.

Abstract: A microphone device including a first sound receiving module and a second sound receiving module is provided. The first sound receiving module includes a first output terminal and receives a sound signal to output a first electronic signal through the first output terminal. The second sound receiving module, which disposed adjacent to the first sound receiving module to receive the sound signal, includes a second output terminal and outputs a second electronic signal through the second output terminal accordingly. The first output terminal of the first sound receiving module is coupled to the second output terminal of the second sound receiving module, and the phase of the first electronic signal and the phase of the second electronic signal are inverse to each other.

Abstract: A flexible waveguide band is provided for that may be worn by a user around their neck, for example. The flexible waveguide band includes a spine, such as a pliable rod; a plurality of vertebrae mounted on the spine, with each vertebra including at least one waveguide channel guide; and an encapsulating potting material. The flexible waveguide band may also be attached to an acoustic pod, including an acoustic driver that may radiate sound waves into said waveguide channels and exit via a sound outlet opening in the flexible band.

Abstract: A computing device reduces the complexity of setting a preferred language on the computing device based on verbal communications with a user. The device may detect when a user is having difficulty navigating a device in a current language and detects the language spoken by a user to cause a language setting to change. The computing device may cross reference other information associated with user, such as other applications or content, when selecting a preferred language.

Abstract: Computer-implemented techniques can include obtaining languages for automatic speech recognition, the languages being associated with a plurality of users and receiving an input indicative of a request to provide speech input. In response to receiving the input, a first indication that automatic speech recognition (ASR) is being performed in each of the plurality of languages can be displayed. A speech input from one of the plurality of users can be received and ASR can identify one of the languages associated with the speech input to obtain a detected language. In response to obtaining the detected language, a second indication that ASR is being performed in the detected language can be displayed. The speech input can be transcribed and translated to another one of the plurality of languages to obtain a translated text that can be displayed.

Abstract: According to an aspect of the present disclosure, a method for generating a keyword model of a user-defined keyword in an electronic device is disclosed. The method includes receiving at least one input indicative of the user-defined keyword, determining a sequence of subwords from the at least one input, generating the keyword model associated with the user-defined keyword based on the sequence of subwords and a subword model of the subwords, wherein the subword model is configured to model a plurality of acoustic features of the subwords based on a speech database, and providing the keyword model associated with the user-defined keyword to a voice activation unit configured with a keyword model associated with a predetermined keyword.

Abstract: Various implementations disclosed herein include a training module configured to produce a set of segment templates from a concurrent segmentation of a plurality of vocalization instances of a VSP vocalized by a particular speaker, who is identifiable by a corresponding set of vocal characteristics. Each segment template provides a stochastic characterization of how each of one or more portions of a VSP is vocalized by the particular speaker in accordance with the corresponding set of vocal characteristics. Additionally, in various implementations, the training module includes systems, methods and/or devices configured to produce a set of VSP segment maps that each provide a quantitative characterization of how respective segments of the plurality of vocalization instances vary in relation to a corresponding one of a set of segment templates.

Abstract: Provided are methods and systems for passive training for automatic speech recognition. An example method includes utilizing a first, speaker-independent model to detect a spoken keyword or a key phrase in spoken utterances. While utilizing the first model, a second model is passively trained to detect the spoken keyword or the key phrase in the spoken utterances using at least partially the spoken utterances. The second, speaker dependent model may utilize deep neural network (DNN) or convolutional neural network (CNN) techniques. In response to completion of the training, a switch is made from utilizing the first model to utilizing the second model to detect the spoken keyword or the key phrase in spoken utterances. While utilizing the second model, parameters associated therewith are updated using the spoken utterances in response to detecting the keyword or the key phrase in the spoken utterances. User authentication functionality may be provided.

Abstract: Relative Excitation Features, in all conditions, are far superior to conventional acoustic features like Mel-Frequency Cepstrum (MFC) and Perceptual Linear Prediction (PLP), and provide much more speaker-independence, channel-independence, and noise-immunity. Relative Excitation features are radically different than conventional acoustic features. Relative Excitation method doesn't try to model the speech-production or vocal tract shape, doesn't try to do deconvolution, and doesn't utilize LP (Linear Prediction) and Cepstrum techniques. This new feature set is completely related to human hearing. The present invention is inspired by the fact that human auditory perception analyzes and tracks the relations between spectral frequency component amplitudes and the “Relative Excitation” name implies relative excitation levels of human auditory neurons. Described herein is a major breakthrough for explaining and simulating the human auditory perception and its robustness.

Abstract: A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.

Abstract: Features are disclosed for processing user utterances and applying user-supplied corrections to future user utterances. If a user utterance is determined to relate to a speech processing error that occurred when processing a previous utterance, information about the error or a correction thereto may be stored. Such information may be referred to as correction information. Illustratively, the correction information may be stored in a skip list. Subsequent utterances may be processed based at least partly on the correction information. For example, speech processing results generated from processing subsequent utterances that include a term associated with the error may be removed or re-scored in order to reduce or prevent the chance that an error will be repeated.

Abstract: A computer-implemented method is described for front end speech processing for automatic speech recognition. A sequence of speech features which characterize an unknown speech input provided on an audio input channel and associated meta-data which characterize the audio input channel are received. The speech features are transformed with a computer process that uses a trained mapping function controlled by the meta-data, and automatic speech recognition is performed of the transformed speech features.

Abstract: Disclosed are a voice recognition system and a construction method for the voice recognition system. By way of layering the system, a general semantic recognition operation for the system is separated from a specific semantic recognition operation for an application program; and by way of classifying the application programs and abstracting out a common performance function, the system can find the application program matching the voice content semantics very efficiently and a third-party program is easily added into the existing voice recognition system. The present invention maps the performance function to a regular expression with semantic variables, so that the system can recognize more semantic expression manners with optimization of the semantic recognition. Therefore, the system can show more humanized characteristics.

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 includes a first microphone disposed near a first seat in a car cabin, the first seat configured to seat a first occupant, a second microphone disposed near a second seat in the car cabin, the second seat configured to seat a second occupant, a processor, and a memory storing a computer program. The computer program, when executed, causes the processor to execute operations including: estimating a first mixed speech using a second signal acquired by the second microphone, the first mixed speech including a first speech that has been uttered by the second occupant and has entered the first microphone, and removing the first mixed speech from a first signal acquired by the first microphone.

Abstract: A robot apparatus including an input unit to receive a voice command from a user, a determination unit to determine whether a voice command is repeated a predetermined number of times, and a control unit to register a shortcut command to shorten a voice command if it is determined a voice command is repeated a predetermined number of times. A shortcut command to shorten a voice command of a user is generated, and thus user convenience is enhanced.

Abstract: Systems and methods that provide for voice command devices that receive sound but do not transfer the voice data beyond the system unless certain voice-filtering criteria have been met are described herein. In addition, embodiments provide devices that support voice command operation while external voice data transmission is in mute operation mode. As such, devices according to embodiments may process voice data locally responsive to the voice data matching voice-filtering criteria. Furthermore, systems and methods are described herein involving voice command devices that capture sound and analyze it in real-time on a word-by-word basis and decide whether to handle the voice data locally, transmit it externally, or both.

Abstract: A system, method and computer-readable storage devices are disclosed for using targeted clarification (TC) questions in dialog systems in a multimodal virtual agent system (MVA) providing access to information about movies, restaurants, and musical events. In contrast with open-domain spoken systems, the MVA application covers a domain with a fixed set of concepts and uses a natural language understanding (NLU) component to mark concepts in automatically recognized speech. Instead of identifying an error segment, localized error detection (LED) identifies which of the concepts are likely to be present and correct using domain knowledge, automatic speech recognition (ASR), and NLU tags and scores. If at least concept is identified to be present but not correct, the TC component uses this information to generate a targeted clarification question.

Abstract: A voice recognition device includes an extractor configured to extract at least one of a first utterance element indicating an execution command and a second utterance element indicating a subject, from a user's voice utterance, a domain determiner configured to determine a current domain to provide response information regarding the voice utterance based on the first and the second utterance elements, and a controller configured to determine a candidate conversation frame to provide the response information regarding the voice utterance on at least one of the current domain and a previous domain based on a conversation state of the current domain, wherein the previous domain is determined from a previous voice utterance of the user.

Abstract: A computer-implemented method for dynamically presenting a prewritten text in a graphical user interface is disclosed. The method comprises receiving a text artifact, storing the text artifact in a memory device of a computer, retrieving the text artifact, displaying the text artifact on the display screen of the computer, receiving a vocal input, generating a text file representing the words spoken in the vocal input, comparing a predetermined number of the hypothesis words to a predetermined number of the artifact words, determining a match location in the text artifact where a specific number of the predetermined number of hypothesis words match a specific number of the predetermined number of artifact words, and altering the display on the display screen to display the match location on the display screen of the computer.

Abstract: A method and apparatus for speech recognition are provided. The method and the apparatus calculate signal to noise ratios (SNRs) of speech signals from a user received at speech recognition apparatuses. The method and the apparatus recognize a reference speech signal having a maximum SNR among the SNRs.

Abstract: An electronic device and a method for controlling the same are provided. The electronic device includes a storage configured to store domain information that is categorized for dialog subjects, a speaker configured to output a system response based on a user utterance sound, and a processor configured to detect a domain, among the domain information, based on the user utterance sound, determine one among the detected domain and a previous domain as a domain to be used to process the user utterance sound, based on a confidence between the user utterance sound and the detected domain, and process the user utterance sound to generate the system response, based on the determined domain.

Abstract: A system and method for processing multi-modal device interactions in a natural language voice services environment may be provided. In particular, one or more multi-modal device interactions may be received in a natural language voice services environment that includes one or more electronic devices. The multi-modal device interactions may include a non-voice interaction with at least one of the electronic devices or an application associated therewith, and may further include a natural language utterance relating to the non-voice interaction. Context relating to the non-voice interaction and the natural language utterance may be extracted and combined to determine an intent of the multi-modal device interaction, and a request may then be routed to one or more of the electronic devices based on the determined intent of the multi-modal device interaction.

Abstract: Biofeedback is used to alter subsequent speech of one or more participants engaged in a discussion. Biofeedback signals can range from simplistic (beeps, flashes, vibrations, etc.) to more complicated images, videos, and music. In one aspect, feedback signals can be rendered to the participant(s) based on the extent to which the discussion relates to one or more goals. Signals can be rendered in any suitable manner, including a visual image rendered by a virtual reality headset or other device, an electronically generated auditory sound, other tactilely perceptible vibrations or other movements, preferably in substantially near real-time.

Abstract: Embodiments of the present invention address deficiencies of the art in respect to podcasting and provide a method, system and computer program product for speed podcasting. In an embodiment of the invention, a speed podcasting method can include speech recognizing an audio portion of a podcast, parsing the speech recognized audio portion to identify essential words, and playing back only audio segments and corresponding video segments of the podcast including the essential words while excluding from playback audio segments and corresponding video segments of the podcast including non-essential words.

Abstract: Features are disclosed for processing user queries into a form that can produce relevant results. Spoken user queries can be transcribed into textual queries. Textual queries can be processed using a statistical model to identify entities within the queries. Running searches using the entities rather than the original search query can produce relevant results even when no result would have been obtained by running the original search query. In some embodiments, attributes may be identified and used during the search to narrow the results and potentially produce results that are more relevant.

Abstract: Techniques for combining the results of multiple recognizers in a distributed speech recognition architecture. Speech data input to a client device is encoded and processed both locally and remotely by different recognizers configured to be proficient at different speech recognition tasks. The client/server architecture is configurable to enable network providers to specify a policy directed to a trade-off between reducing recognition latency perceived by a user and usage of network resources. The results of the local and remote speech recognition engines are combined based, at least in part, on logic stored by one or more components of the client/server architecture.

Abstract: A voice command recognition apparatus and method thereof are described. The voice command recognition apparatus includes audio sensors placed at different locations; a context determiner configured to determine user context based on a voice received at the audio sensors, wherein the context comprises a vocalization from a user. A command recognizer in the voice command recognition apparatus is configured to activate to recognize a voice command or remain inactive according to the recognized context.

Abstract: A method includes: receiving a first speech frame; identifying a first codec mode based at least in part on a Codec Mode Command (CMC) comprising the first speech frame; identifying a second codec mode based at least in part on a downlink (DL) Codec Mode Indication (DCMI) comprising the first speech frame; determining, based at least in part on a current uplink (UL) codec mode, to apply one of the first codec mode, the second codec mode, and a third codec mode having a higher bit rate than the first codec mode; and applying one of the first codec mode, the second codec mode, and the third codec mode. Apply the first codec mode when the RxLev and RXQual are determined not to exceed a predetermined threshold, and applying second or third codec modes otherwise.

Abstract: An audio decoder for providing at least four audio channel signals on the basis of an encoded representation is configured to provide a first residual signal and a second residual signal on the basis of a jointly encoded representation of the first residual signal and of the second residual signal using a multi-channel decoding. The audio decoder is configured to provide a first audio channel signal and a second audio channel signal on the basis of a first downmix signal and the first residual signal using a residual-signal-assisted multi-channel decoding. The audio decoder is configured to provide a third audio channel signal and a fourth audio channel signal on the basis of a second downmix signal and the second residual signal using a residual-signal-assisted multi-channel decoding. An audio encoder is based on corresponding considerations.

Abstract: Systems and methods are disclosed for detecting and removing traceable identifying audio content from electronic media content. One method includes: receiving, over a network, media content to be broadcast or distributed, the media content including audio data; determining whether the audio data of the media content includes traceable identifying audio content defined by an audio identifier; generating new audio data based on the audio data of the media content when an audio identifier is determined to be include in the audio data; removing audio data from the media content when the audio identifier is determined to be include in the audio data; adding the new audio data to the media content when the audio data is removed from the media content; and broadcasting or distributing the media content having the new audio data to one or more user devices.

Abstract: A data decoding method and device as well as an intelligent cipher key token are provided. The data decoding method includes: receiving a sinusoidal wave via an audio interface, wherein the sinusoidal wave has a waveform with at least one period, and different periods represent different bit values; processing the sinusoidal wave so as to obtain a first square wave, wherein the first square wave carries data to be decoded; determining whether there is a glitch waveform in the first square wave, based on a preset threshold or based on an adaptive threshold, wherein the adaptive threshold is calculated according to synchronization head data carried in the sinusoidal wave; if there is a glitch waveform in the first square wave, eliminating the glitch waveform from the first square wave so as to obtain a second square wave; and decoding the second square wave so as to obtain decoded data.

Abstract: An apparatus for generating an audio signal envelope from one or more coding values is provided. The apparatus includes an input interface for receiving the one or more coding values, and an envelope generator for generating the audio signal envelope depending on the one or more coding values. The envelope generator is configured to generate an aggregation function depending on the one or more coding values, wherein the aggregation function includes a plurality of aggregation points. Furthermore, the envelope generator is configured to generate the audio signal envelope such that the envelope value of each of the envelope points of the audio signal envelope depends on the aggregation value of at least one aggregation point of the aggregation function.

Abstract: The present disclosure is directed towards a system and method for reducing tandeming effects in a communications system. The method may include receiving, at a speech decoder, an input bitstream associated with an incoming initial speech signal from a speech encoder. The method may further include determining whether or not coding is required and if coding is required, modifying an excitation signal associated with the bitstream. The method may also include providing the modified excitation signal to an adaptive encoder.

Abstract: A “running range normalization” method includes computing running estimates of the range of values of features useful for voice activity detection (VAD) and normalizing the features by mapping them to a desired range. Running range normalization includes computation of running estimates of the minimum and maximum values of VAD features and normalizing the feature values by mapping the original range to a desired range. Smoothing coefficients are optionally selected to directionally bias a rate of change of at least one of the running estimates of the minimum and maximum values. The normalized VAD feature parameters are used to train a machine learning algorithm to detect voice activity and to use the trained machine learning algorithm to isolate or enhance the speech component of the audio data.

Abstract: A low-power sound wave reception method in a computer which includes a microphone, a memory which stores at least one reference pattern, and a computer processor is provided. The low-power sound wave reception method includes: when a sound wave signal having an intensity greater than or equal to a threshold value is detected by the microphone, comparing the sound wave signal and the at least one reference pattern stored in the memory; and when there is a reference pattern matching the sound wave signal, turning on the computer processor, and deactivating the reference pattern matching the sound wave signal (excluding the deactivated reference pattern from the comparing step).

Abstract: The present invention relates to a method of evaluating quality of a degraded speech signal received from an audio transmission system conveying a reference speech signal. The method comprises sampling said signals into reference and degraded signal frames, and forming frame pairs by associating reference and degraded signal frames with each other. For each frame pair a difference function representing disturbance is provided, which is then compensated for specific disturbance types for providing a disturbance density function. Based on the density function of a plurality of frame pairs, an overall quality parameter is determined. The method provides for compensating the overall quality parameter for the effect that the impact of noise in frequency bands where there is only marginal speech activity when compared to natural speech is not correctly modelled in the current measurement standards.

Abstract: A novel automatic record player for playing a phonograph record includes a base, a turntable, an upper hub, a lower hub, a tonearm, a drive unit, a pinion, a control cam, a main arm, an auxiliary arm, first and second micro-switches, a clutch member, a first clutch actuating member, a switch activating member, an actuating pin, a synchronizing unit, a position guide, an angular position setting unit, and an elongated member. With the provision of the angular position setting unit, when the clutch member is actuated by the first clutch actuating member, a forward free end of the tonearm can be more precisely positioned on an outermost groove of the phonograph record.

Abstract: Systems and methods for applying electric fields during ultraviolet exposure of lubricant layers for hard disk media. One such method involves inserting a magnetic medium into a chamber, the magnetic medium including a lubricant on an outer surface thereof, and applying an electric field and an ultraviolet radiation to the lubricant within the chamber. Another such method involves inserting a magnetic medium into a chamber, depositing a lubricant on the medium within the chamber, and applying an electric field and an ultraviolet radiation to the lubricant within the chamber.

Abstract: A method for assembling a head-gimbal assembly of a hard disk drive, the method including the steps of dispensing adhesive onto a top surface of a gimbal tongue, wherein the gimbal tongue is positioned adjacent to a load beam with a dimple extending from its top surface, and wherein the gimbal tongue is configured with at least one support feature that inhibits its deformation toward the dimple when subjected to downward pressure with respect to the dimple; positioning a slider on which a magnetic head is mounted adjacent to the top surface of the gimbal tongue; and pressing the slider onto the adhesive and toward the dimple of the load beam.

Abstract: A head gimbal assembly has a laminate flexure that includes a metallic conductive layer that includes a plurality of electrically conductive traces that are elongated and narrow and electrically connected to the read head, and a metallic structural layer that is stiffer than the conductive layer. A first dielectric layer is disposed between the structural layer and the conductive layer. A second dielectric layer substantially covers the conductive layer in a flexure tail bonding region that overlaps a flexible printed circuit (FPC). The structural layer includes a plurality of flexure bond pads that are aligned with, facing, and bonded to corresponding FPC bond pads. The flexure bond pads in the structural layer are electrically connected to the electrically conductive traces in the conductive layer by vias through the first dielectric layer. In certain embodiments, the flexure tail is folded upon itself in the flexure tail bonding region.