Abstract: An object of the present invention is to provide a soundproof material having a practically useful high-level sound absorption coefficient that while maintaining thinness, and further having an expanded sound-absorbable frequency region. A means for solving the problem is a soundproof material comprising: a surface cover layer composed of a fiber material; a back-surface layer laminated onto the surface cover layer, and composed of a porous material with voids interconnected with each other; and a joining layer laminated between the surface cover layer and the back-surface layer, and composed of a joining material, wherein the fiber material has an average fiber diameter of 1 to 10 ?m and an air-permeation volume of 5 to 200 cm3/cm2·sec, and wherein the joining layer has a joint area percentage of 50 to 95% with respect to the entire surface where the surface cover layer and the back-surface layer face each other.

Abstract: A wind turbine comprising: a vibration source; a component arranged to receive a vibration from the vibration source, the component having a first resonant frequency; and a resonator module arranged to vibrate with a first wavelength when excited at the first resonant frequency, the resonator module being operably coupled to the component at a first location, wherein the resonator module has a first length extending from the first location to a first free end of the resonator module, and wherein the first length of the resonator module is a quarter of the first wavelength.

Abstract: Disclosed embodiments may relate to systems and methods for monitoring and/or mapping noise data from a plurality of noise monitoring devices. In some embodiments, the plurality of noise monitoring devices may include hearing protection devices configured to detect noise, and typically may communicate such noise data (which may also include location) so that the noise data can be pooled. The pooled noise data from the plurality of noise monitoring devices may then be used to the benefit of one or more of such noise monitoring devices.

Abstract: A display apparatus includes a display panel configured to include first to eleventh regions, at least one first to third vibration devices respectively at the first to third regions, at least one fourth to eighth vibration devices respectively at the fourth to eighth regions, at least one ninth to eleventh vibration devices respectively at the ninth to eleventh regions, a first partition between the first and third regions, a second partition between the second and third regions, a third partition between the fourth and seventh regions, a fourth partition between the fourth and eighth regions, a fifth partition between the sixth and seventh regions, and a sixth partition between the sixth and eighth regions. A length of one or more among the first and second partitions may differ from a length of one or more among the third to sixth partitions.

Abstract: Novel methods and systems for adapting a voice cloning synthesizer for a new speaker using real speech data are disclosed. Utterances from one or more target speakers are parameterized and are used to initialize an embedding vector for use with a voice synthesizer, by means of clustering the utterance data and determining the centroid of the data, using a speaker identification neural network, and/or by finding the closest stored embedded vector to the utterance data.

Abstract: The present disclosure relates to a text-to-speech synthesis method using machine learning based on a sequential prosody feature. The text-to-speech synthesis method includes receiving input text, receiving a sequential prosody feature, and generating output speech data for the input text reflecting the received sequential prosody feature by inputting the input text and the received sequential prosody feature to an artificial neural network text-to-speech synthesis model.

Abstract: A method for training a speech recognition model includes receiving a set of training utterance pairs each including a non-synthetic speech representation and a synthetic speech representation of a same corresponding utterance. At each of a plurality of output steps for each training utterance pair in the set of training utterance pairs, the method also includes determining a consistent loss term for the corresponding training utterance pair based on a first probability distribution over possible non-synthetic speech recognition hypotheses generated for the corresponding non-synthetic speech representation and a second probability distribution over possible synthetic speech recognition hypotheses generated for the corresponding synthetic speech representation. The first and second probability distributions are generated for output by the speech recognition model.

Abstract: To provide a voice analysis system capable of performing voice recognition with higher accuracy. A voice analysis system including a first voice analysis terminal and a second voice analysis terminal, the first voice analysis terminal obtaining first conversation information, and the second voice analysis terminal obtaining second conversation information, wherein the voice analysis system comprises a conversation category selection unit which compares the number of related words included in the first conversation information and the number of related words included in the second conversation information, in each conversation category, and adopts the conversation category with the larger number of related words as a correct conversation category.

Abstract: A method and system of training a spoken language understanding (SLU) model includes receiving natural language training data comprising (i) one or more speech recording, and (ii) a set of semantic entities and/or intents for each corresponding speech recording. For each speech recording, one or more entity labels and corresponding values, and one or more intent labels are extracted from the corresponding semantic entities and/or overall intent. A spoken language understanding (SLU) model is trained based upon the one or more entity labels and corresponding values, and one or more intent labels of the corresponding speech recordings without a need for a transcript of the corresponding speech recording.

Abstract: A supervised discriminator for detecting bio-markers in an audio sample dataset is trained and a denoising autoencoder is trained to learn a latent space that is used to reconstruct an output audio sample with a same fidelity as an input audio sample of the audio sample dataset. A conditional auxiliary generative adversarial network (GAN) trained to generate the output audio sample with the same fidelity as the input audio sample, wherein the output audio sample is void of the bio-markers. The conditional auxiliary generative adversarial network (GAN), the corresponding supervised discriminator, and the corresponding denoising autoencoder are deployed in an audio processing system.

Abstract: A method for detecting a hotword includes receiving a sequence of input frames that characterize streaming audio captured by a user device and generating a probability score indicating a presence of a hotword in the streaming audio using a memorized neural network. The network includes sequentially-stacked single value decomposition filter (SVDF) layers and each SVDF layer includes at least one neuron. Each neuron includes a respective memory component, a first stage configured to perform filtering on audio features of each input frame individually and output to the memory component, and a second stage configured to perform filtering on all the filtered audio features residing in the respective memory component. The method also includes determining whether the probability score satisfies a hotword detection threshold and initiating a wake-up process on the user device for processing additional terms.

Abstract: A method includes receiving a representation of a spoken utterance, processing the representation of the spoken utterance to identify, from a number of candidate domains, a request and a serving domain, and routing the request to a personal assistant based on the request and the serving domain. Identification of the serving domain is based on one or more of a contextual state, a behavior profile of a speaker of the utterance, and a semantic content of the utterance.

Abstract: Described are systems, methods, apparatuses, and computer program product embodiments for automatically processing intent-based spoken language for SLU. The disclosed solution uses a scale-free network structured conversational knowledge graph that stores nodes representative of actions, objects, and intent names and edges representative of relationships between the nodes. For all phrases (including a sentence) from the same intent, the system calculates a mean feature vector using a Universal Sentence Embedding (USE) model as a feature element. The system also employs a multi-step intent detection strategy. A graph query technique may be used to match all potential intent nodes from the trained knowledge graph. The system may compute a covariance matrix between the feature element of an input phrase and feature elements of all potential intents. The major component of the covariance matrix along with the maximum covariance may be used to determine the final intent.

Abstract: A security panel for controlling home automation devices via a voice assistant device is provided, in which the security panel includes a processor, a memory, a microphone, and a speaker. In one example implementation, the security panel is configured to receive a text input from a user, convert the text input into an audio format via a text-to-speech engine to generate a first voice command for controlling one or more home automation devices via a voice assistant device, and to output the first voice command via the speaker of the security panel, in which the first voice command is received by the voice assistant device via a microphone of the voice assistant device, in which the voice assistant device is configured to control the one or more home automation devices based on the first voice command.

Abstract: Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, and/or computing entities for displaying content found in technical documentation via an IETM viewer. In accordance with one embodiment, a method is provided comprising: providing a window for display via the IETM viewer, the window displaying content found in the documentation; receiving a focus of a first portion of the content; and thereafter: determining whether the first portion is relevant to a user; and responsive to determining the first portion is relevant, causing the first portion to be displayed using a relevant format; receiving a focus of a second portion of the content; and thereafter: determining whether the second portion of the content is relevant to the user; and responsive to determining the second portion is not relevant, causing the second portion to be displayed on the window using an irrelevant format that is different than the relevant format.

Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

Abstract: Techniques for performing centralized unsuperivised learning in a multi-domain system are described. A user may request labeled data for an ML task, where the request includes a prompt for obtaining relevant explicit user feedback. The system may use the prompt to collect explicit user feedback for relevant runtime user inputs. After a duration of time (in the user's request for labeled data) has elapsed, the system determines whether collected user feedback indicates processing of the user input was defective and, if so, determines a cause of the defective processing. The system then uses one or more label generators to generate labeled data using the collected user feedback, whether the processing was defective, and the determined defect cause.

Abstract: A method operates a hearing device system which has a hearing aid and a peripheral device which provides a voice-controlled digital assistant. A microphone signal from the hearing aid is examined for own voice components of the wearer of the hearing aid. If own voice components are detected by the hearing aid the microphone signal is examined for a pre-defined activation command for the digital assistant. If the activation command is recognized, a portion of the microphone signal representing the activation command and a subsequent speech sequence is processed by the hearing aid for a speech recognizer of the digital assistant using an algorithm. The processed portion of the microphone signal is transmitted to the peripheral device.

Abstract: Methods, apparatus, and computer readable media related to receiving textual input of a user during a dialog between the user and an automated assistant (and optionally one or more additional users), and generating responsive reply content based on the textual input and based on user state information. The reply content is provided for inclusion in the dialog. In some implementations, the reply content is provided as a reply, by the automated assistant, to the user's textual input and may optionally be automatically incorporated in the dialog between the user and the automated assistant. In some implementations, the reply content is suggested by the automated assistant for inclusion in the dialog and is only included in the dialog in response to further user interface input.

Abstract: A method for selecting a speech recognition result on a computing device includes receiving a first speech recognition result determined by the computing device, receiving first features, at least some of the features being determined using the first speech recognition result, determining whether to select the first speech recognition result or to wait for a second speech recognition result determined by a cloud computing service based at least in part on the first speech recognition result and the first features.

Abstract: A method and apparatus for automatically generating a meeting summary is disclosed herein. Meeting audio is recorded and converted into a text-based transcript. Handwritten meeting notes are converted into notes text. The transcript and notes text are correlated to provide correlated meeting text. Meeting topics are determined from the correlated meeting text. A meeting summary is generated from the meeting topics.

Abstract: Methods, systems, and apparatus for receiving, by a voice action system, data specifying trigger terms that trigger an application to perform a voice action and a context that specifies a status of the application when the voice action can be triggered. The voice action system receives data defining a discoverability example for the voice action that comprises one or more of the trigger terms that trigger the application to perform the voice action when a status of the application satisfies the specified context. The voice action system receives a request for discoverability examples for the application from a user device having the application installed, and provides the data defining the discoverability examples to the user device in response to the request. The user device is configured to provide a notification of the one or more of the trigger terms when a status of the application satisfies the specified context.

Abstract: Disclosed speech recognition techniques improve user-perceived latency while maintaining accuracy by: receiving an audio stream, in parallel, by a primary (e.g., accurate) speech recognition engine (SRE) and a secondary (e.g., fast) SRE; generating, with the primary SRE, a primary result; generating, with the secondary SRE, a secondary result; appending the secondary result to a word list; and merging the primary result into the secondary result in the word list. Combining output from the primary and secondary SREs into a single decoder as described herein improves user-perceived latency while maintaining or improving accuracy, among other advantages.

Abstract: Embodiments of systems and methods for user enrollment in speaker authentication and speaker identification systems are disclosed. In some embodiments, the enrollment process includes collecting speech samples that are examples of multiple speech types spoken by a user, computing a speech representation for each speech sample, and aggregating the example speech representations to form a robust overall representation or user voiceprint of the user's speech.

Abstract: Certain embodiments of the present disclosure provide techniques training a user detection model to identify a user of a software application based on voice recognition. The method generally includes receiving a data set including a plurality of voice interactions with users of a software application. For each respective recording in the data set, a spectrogram representation is generated based on the respective recording. A plurality of voice recognition models are trained. Each of the plurality of voice recognition models is trained based on the spectrogram representation for each of the plurality of voice recordings in the data set. The plurality of voice recognition models are deployed to an interactive voice response system.

Abstract: Disclosed is an operating method of an electronic device, including receiving a first user model from another electronic device of a user registered in the electronic device, through a communication circuit of the electronic device, refining a user model of the electronic device based on the first user model, and identifying the user based on a first voice input of the user by using the refined user model, wherein the user model is trained by the electronic device based on a second user model of at least one another user other than the user before the user is registered, and wherein the first user model is trained by the another electronic device based on a second voice input of the user obtained by the another electronic device of the user.

Abstract: According to an embodiment, an electronic device comprises a communication module, a memory, and a processor configured to, upon obtaining a first utterance related to a memory service, prepare to store first information for the memory service for the first utterance and store the first information including essential information, sensitivity information for the first information, and an authentication method for the first information, detected from the first utterance, in the memory, and obtain a second utterance for looking up information related to the memory service, upon identifying that the obtained second utterance is one for looking up the first information, complete authentication based on the authentication method, and provide the essential information by a providing method determined based on the sensitivity information. Various other embodiments may be provided.

Abstract: An electronic apparatus is provided. The electronic apparatus may include a microphone; a memory configured to store a wakeup word; and a processor configured to: identify, based on context information of the electronic apparatus, an occurrence of a pre-determined event; change, based on the occurrence of the pre-determined event, a first threshold value for recognizing the wakeup word; obtain, based on a first user voice input received via the microphone, a similarity value between first text information corresponding to the first user voice input and the wakeup word; and perform, based on the similarity value being greater than or equal to the first threshold value, a voice recognition function on second text information corresponding to a second user voice input received via the microphone after the first user voice input.

Abstract: The present disclosure relates to the field audio coding, an in particular to an audio decoder having at least two decoding modes, and associated decoding methods and decoding software for such audio decoder. In one of the decoding modes, at least one dynamic audio object is mapped to a set of static audio objects, the set of static audio objects corresponding to a predefined speaker configuration. The present disclosure further relates to a corresponding audio encoder, and associated encoding methods and encoding software for such audio encoder.

Abstract: A signal processing device includes: a processor; and a memory having instructions. The instructions, when executed by the processor, cause the signal processing device to perform operations. The operations include performing a modulation processing of modulating a sound signal by using a modulation parameter based on an interaural phase difference at a listening position of the sound signal.

Abstract: An audio encoder for encoding an audio signal has: a first encoding processor for encoding a first audio signal portion in a frequency domain, having: a time frequency converter for converting the first audio signal portion into a frequency domain representation; an analyzer for analyzing the frequency domain representation to determine first spectral portions to be encoded with a first spectral resolution and second regions to be encoded with a second resolution; and a spectral encoder for encoding the first spectral portions with the first spectral resolution and encoding the second portions with the second resolution; a second encoding processor for encoding a second different audio signal portion in the time domain; a controller for analyzing and determining, which portion of the audio signal is the first audio signal portion encoded in the frequency domain and which portion is the second audio signal portion encoded in the time domain; and an encoded signal former for forming an encoded audio signal havi

Abstract: Described herein is a method of low-bitrate coding of audio data and generating enhancement metadata for controlling audio enhancement of the low-bitrate coded audio data at a decoder side, including the steps of: (a) core encoding original audio data at a low bitrate to obtain encoded audio data; (b) generating enhancement metadata to be used for controlling a type and/or amount of audio enhancement at the decoder side after core decoding the encoded audio data; and (c) outputting the encoded audio data and the enhancement metadata. Described is further an encoder configured to perform said method. Described is moreover a method for generating enhanced audio data from low-bitrate coded audio data based on enhancement metadata and a decoder configured to perform said method.

Abstract: Various embodiments of a system and methods for audio source separation via multi-scale feature learning are disclosed.

Abstract: Systems and methods for amplifying and/or attenuating audio signals are disclosed. In one implementation, a system for selectively amplifying audio signals may include at least one microphone for capturing sounds from an environment of the user and a processor. The processor may be programmed to receive an audio signal representative of sounds captured by the at least one microphone; determine whether the audio signal comprises speech by a user of the system; subject to the audio signal comprising speech by the user, modify the audio signal by attenuating a first part of the audio signal comprising the speech by the user; subject to the audio signal comprising audio other than speech by the user, modify the audio signal by amplifying a second part of the audio signal comprising audio other than the speech by the user; and transmit the modified audio signal to a hearing interface device.

Abstract: Systems and methods provide input and output mode control for audio processing on a user device. Audio processing may be configured by monitoring audio activity on a device having at least one microphone and a digital audio processing unit, collecting information from the monitoring of the activity, including an identification of at least one application utilizing audio processing, and determining a context for the audio processing, the context including at least one of a hardware, software, audio signal and/or environmental context. An audio signal processing configuration is determined based on the application and determined context, an associated audio signal processing mode is selected, and an optimized audio signal generated.

Abstract: An apparatus for processing a multichannel audio signal has a plurality of channel signals. The apparatus performs a time scale modulation of the multichannel audio signal and has a phase adaptor and a separator. The phase adaptor provides a processed signal by modifying a phase of a signal based on a combination of the channel signals. The separator provides separated signals based on the processed signal. A corresponding method is provided.

Abstract: A method for matching audio clips includes: obtaining a first feature sequence corresponding to a first audio clip and a second feature sequence corresponding to a second audio clip; constructing a distance matrix, elements in the distance matrix representing respective distances between first positions in the first feature sequence and second positions in the second feature sequence; calculating a first accumulation distance between a start position and a target position in the distance matrix, and calculating a second accumulation distance between an end position and the target position in the distance matrix; and calculating a minimum distance between the first feature sequence and the second feature sequence based on the first accumulation distance and the second accumulation distance, and determining a degree of matching between the first audio clip and the second audio clip according to the minimum distance.

Abstract: An apparatus and method of blind detection of binauralized audio. If the input content is detected as binaural, a second binauralization may be avoided. In this manner, the user experience avoids audio artifacts introduced by multiple binauralizations.

Abstract: A tape drive (226) for use in a tape library (10) that retains at least one tape cartridge (220) that retains magnetic tape (250) includes a drive housing (226A) and a media conditioner (255). The drive housing (226A) is configured to receive the tape cartridge (220). The media conditioner (255) is coupled to the drive housing (226A). The media conditioner (255) is configured to condition the magnetic tape (250) when the tape cartridge (220) is received within the drive housing (226A). The media conditioner (255) can be configured to remove at least one of abrasives, contaminants and lubricants that are on the magnetic tape (250) when the tape cartridge (220) is received within the drive housing (226A). The magnetic tape (250) is configured to move along a predefined path (251) within the drive housing (226A), which is defined by one or more rollers (254).

Abstract: Example read channel circuits, data storage devices, and methods to provide overlapping processing of data tracks are described. The data storage device may include media configured with a plurality of tracks in a concentric or continuous pattern. The read signal for a data track may be processed using error correction codes (ECC) as it is read during a first track read operation period. Some portion of its data sectors may need additional ECC postprocessing after the first track is initially received and processed by the read channel circuit. While the read signal for a next data track is being read and processed, the read channel circuit may continue postprocessing of the portion of data sectors from the first track during the second track read operations. Various decision parameters for managing the data stream, additional postprocessing time, and rereading tracks for data recovery are also described.

Abstract: According to an embodiment, a track includes first sectors and a second sector. When write of a second data segment to a third sector that is one of the first sectors is requested from a host, a controller acquires the second data segment from the host and stores the second data segment in the memory, and reads a data set including all first data segments and all first information pieces from the track and stores the data set in the memory. The controller acquires a second information piece of the third sector, and updates a first data segment and a first information piece read from the third sector in the data set in the memory with the second data segment and the second information piece. The controller calculates a second parity while the updated data set to the track, and writes the second parity to the second sector.

Abstract: Setting a replay speed of a pre-recorded video presentation includes determining a mood of a presenter of the pre-recorded video presentation, determining complexity of material that is presented in the pre-recorded video presentation, and setting a replay speed based on the mood of the presenter and the complexity of the material that is presented. Setting a replay speed of a pre-recorded video presentation may also include adjusting the replay speed based on determining a desired speech tempo for a listener. The desired speech tempo of the listener may be based on time of day, age of the listener, and/or comprehension level of the listener. Measuring the comprehension level of the listener may be based facial expressions of the listener, eye-tracking of the listener, and/or listener comprehension quizzes. Measuring the mood of the presenter may be based on facial recognition, sentiment recognition, and/or gesture recognition.

Abstract: Techniques are described for automatically adaptive playback speed for media playback. In an embodiment, media data is received, which is associated with multimedia to be rendered at an original capture speed on a multimedia player on a computing device. A content density index value for a particular portion of the multimedia is determined, the content density index value representing a rate of content within the particular portion that a user of the multimedia player has to comprehend. Based on the content density index value for the particular portion, a new speed is determined for rendering the portion of the multimedia. The new speed may be stored associated with the portion of the multimedia for rendering the portion of the multimedia at the new speed that is different from the original speed.

Abstract: The present disclosure provides a method and apparatus of editing a multimedia file, an electronic device, and a storage medium. The method includes: acquiring a multimedia file and an operation information contained in each editing track of a plurality of editing tracks, wherein the operation information is acquired to edit the multimedia file; detecting a multimedia file frame contained in the each editing track at a current time in a case of editing the multimedia file in a chronological order; editing the multimedia file frame contained in the each editing track at the current time by using the operation information associated with the multimedia file frame, so as to obtain an edited file frame contained in the each editing track at the current time; and performing an encoding synthesis on the edited file frame contained in the each editing track at the current time.

Abstract: An automated artificial intelligence (AI) and template-based audio record mixing system and process are disclosed. The automated AI and template-based audio record mixing system and process use provided templates and AI to mix records. The artist maintains full control of how they want to record sound when utilizing the automated AI and template-based audio record mixing system and process.

Abstract: The disclosed technology is a system and computer-implemented method for assembling and editing a video program from spoken words or soundbites. The disclosed technology imports source audio/video clips and any of multiple formats. Spoken audio is transcribed into searchable text. The text transcript is synchronized to the video track by timecode markers. Each spoken word corresponds to a timecode marker, which in turn corresponds to a video frame or frames. Using word processing operations and text editing functions, a user selects video segments by selecting corresponding transcribed text segments. By selecting text and arranging that text, a corresponding video program is assembled. The selected video segments are assembled on a timeline display in any chosen order by the user. The sequence of video segments may be reordered and edited, as desired, to produce a finished video program for export.

Abstract: This disclosure provides a video generation method, a video generation apparatus, an electronic device, a storage medium and a program product, and relates to the field of artificial intelligence technology, and in particular to the field of computer vision technology and deep learning technology. A specific implementation includes: obtaining document content information of a document; extracting, from the document content information, populating information for multiple scenes in a preset video template; populating the populating information for the multiple scenes into corresponding scenes in the preset video template, respectively, to obtain image information of the multiple scenes; generating audio information of the multiple scenes according to the populating information for the multiple scenes; generating a video of the document based on the image information and audio information of the multiple scenes.

Abstract: In order to provide a recording and reproducing device that allows a user to select and manage arbitrary play lists, a unit of management for managing all registered play list information and an upper management hierarchical level are added. The unit of management is adapted to be handled on the same level with unified information that indicates a reproduction range of all AV data. User-defined unified information is adapted to be handled on the added management hierarchical level. The user-defined unified information is formed to allow arbitrary reproduction ranges contained on a lower hierarchical level to be registered.

Abstract: A decoding system decodes a video stream, which is encoded video information. The decoding system includes a decoder that acquires the video steam and generates decoded video information, a maximum luminance information acquirer that acquires maximum luminance information indicating the maximum luminance of the video stream from the video stream, and an outputter that outputs the decoded video information along with the maximum luminance information. In in a case where the video stream includes a base video stream and an enhanced video stream, the decoder generates base video information by decoding the base video stream, an enhanced video information by decoding the enhanced video stream, and generates the decoded video information based on the base video information and the enhanced video information, and the outputter outputs the decoded video information, along with the maximum luminance information.

Abstract: A disk device includes a magnetic disk, a magnetic head, a flexible printed circuit board, an electronic component, and a wall. The flexible printed circuit board is electrically connected to the magnetic head. The electronic component is mounted on the flexible printed circuit board. The wall has rigidity higher than the flexible printed circuit board and is attached to the flexible printed circuit board. The flexible printed circuit board with a first through hole includes a first surface facing the electronic component with a gap, and a second surface opposite the first surface and facing the wall, the first through hole being open to the first surface and the second surface to communicate with the gap. The wall is provided with a second through hole penetrating the wall to communicate with the first through hole.