Abstract: Embodiments for text segmentation for topic modelling by a processor. A machine learning mechanism is implemented to enhance one or more topic modelling operations of collected real-time conversation data, the real-time conversation data classified into burst segments or reflection segments; wherein the burst segments comprise successive messages received into the conversation data within a first time interval and the reflection segments comprise multiple messages each received into the conversation data having an inter-arrival time outside the first time interval. A summary of the one or more topic modelling operations is presented on a display to a user according to an output of a text mining analysis implementing the one or more topic modelling operations enhanced by the machine learning mechanism.

Abstract: An audio fingerprint extraction method and device are provided. The method includes: converting an audio signal to a spectrogram; determining one or more characteristic points in the spectrogram; in the spectrogram, determining one or more masks for the characteristic points; determining mean energy of each of the spectrum regions; determining one or more audio fingerprint bits according to mean energy of the plurality of spectrum regions in the one or more masks; judging credibility of the audio fingerprint bits to determine one or more weight bits; and combining the audio fingerprint bits and the weight bits to obtain an audio fingerprint. Each of the one or more masks includes a plurality of spectrum regions.

Abstract: An interpreting assistant system which provides to a user captions of auditory communications in the user's vicinity. The interpreting assistant system includes a smart microphone transmitter that defines an input device which converts auditory communications into audio signals and transmit the signals a translation device, with a smart phone defining the translation device which generates a text transcript from the audio signals and send the transcript file to a display device, with the display device being defined by a wearable display interface which displays the transcript for a user to see. When in use, the interpreting assistant system provides for the display of a real time transcription and display of auditory communications such as spoken words for a user that may have hearing difficulties.

Abstract: A topic based conversation retrieval system and method may include receiving a first conversation between a first plurality of users a second conversation between the first plurality of users or a second plurality of users, the second conversation being conducted on a second communication mode different than the first communication mode, analyzing the first conversation and the second conversation, determining one or more topics of discussion in the first conversation and the second conversation, and retrieving a portion of each of the first conversation and the second conversation, where the portion is related to a topic chosen to be retrieved.

Abstract: Various implementations include approaches for demonstrating device capabilities in a wearable audio device. In certain cases, these approaches include initiating a demonstration using the wearable audio device to provide the user with an example of the device capabilities. In particular aspects, the wearable audio device is configured to apply acoustic demonstration settings at the wearable audio device based upon the demonstration mode, and output an acoustic signal for playback at the wearable audio device.

Abstract: A voice command identification method for an electronic device having a microphone matrix is provided. The method includes: obtaining a plurality of sound signals from the microphone matrix; executing a voice purify operation on the sound signals to obtain a purified sound signal and identifying a target voice signal from the purified sound signal; calculating a compound speech feature data corresponding to the target voice signal through a compound speech recognition model; comparing the compound speech feature data with a plurality of reference speech feature data in the speech feature database, so as to determine a target command mapped to the target voice signal; and executing the target command.

Abstract: Embodiments described herein provide for acoustic signatures in a playback system. As example implementation involves receiving from a microphone of the controller device, an audio signal played by a playback device, the audio signal indicating network information corresponding to the playback device. The example implementation further involves identifying the playback device based on the network information and responsively, modifying a user interface on the controller device based on the identification of the playback device.

Abstract: Disclosed embodiments provide methods and systems to capture, persist, and access a real-time audio stream and metadata associated with a radio broadcast. The real-time audio stream is captured on an audio capture device comprising a real-time clock. The audio is associated with the points in time it is captured with time markers. In embodiments, the audio is encoded for transmission with the time markers to a remote server. After being captured, encoded, and associated with time markers, the audio is transmitted to a remote server for archiving. Client devices are used to provide access to archived content. Clients request portions of the real-time audio stream from the remote server, and identify the portions they are requesting by including in their request either real-time bounds, or other information which is associated on the remote server with real-time bounds, such as content descriptor types.

Abstract: Techniques for reducing the time used to output audio or video include increasing the output rate for portions of the content to reduce the time needed for a user to consume the content. Audio data is analyzed to determine portions that are silent and portions that include speech, such as by determining amplitude and other signal characteristics. Portions that include speech are analyzed to determine an initial rate of speech associated with each portion. Speech characteristics of the portions, such as language, volume, and pitch are used to determine a target maximum comprehensible rate of speech for a user. When audio output is generated, the portions that represent speech are each output at a rate that results in the speech being presented within a threshold of the target rate. The portions that represent silence may be removed, shortened, or output at a faster rate than the portions that represent speech.

Abstract: A dialogue system for a vehicle may include: a storage configured to store vehicle state information and driving environment information; an input processor configured to acquire an utterance from a user and to extract an action corresponding to the utterance when it is identified that the utterance includes user state information; a dialogue manger configured to acquire a parameter value of a condition determination parameter used to determine whether the action corresponding to the utterance is executable from the storage, to determine an action to be executed based on the parameter value of the condition determination parameter, and to acquire a parameter value of an action parameter used to execute the determined action from the storage; and a result processor configured to generate a response to execute the determined action using the acquired parameter value of the action parameter.

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to improve media identification. An example apparatus includes a hash handler to generate a first set of reference matches by performing hash functions on a subset of media data associated with media to generate hashed media data based on a first bucket size, a candidate determiner to identify a second set of reference matches that include ones of the first set, the second set including ones having first quantities of hits that did not satisfy a threshold, determine second quantities of hits for ones of the second set by matching ones to the hash tables based on a second bucket size, and identify one or more candidate matches based on at least one of (1) ones of the first set or (2) ones of the second set, and a report generator to generate a report including a media identification.

Abstract: Disclosed are a scenario-based sound effect control method and an electronic device. The method comprises: after being turned on, an electronic device enables a service having an interception function; the electronic device intercepts, by using the service having the interception function, whether there is a newly created audio decoder and/or video decoder in the electronic device; if determining that there is the newly created audio decoder and the video decoder in the electronic device, the electronic device determines that a current scenario is a video playing application scenario; the electronic device obtains a scenario-based sound effect corresponding to the video playing application scenario, and sets a current sound effect of the electronic device as the scenario-based sound effect.

Abstract: A method and device for sound effect processing, and a non-transitory storage medium. The method includes the following actions. A task manager is traversed to determine whether a sound effect service process for a sound effect service exists. Responsive to determining that the sound effect service process exists, whether the sound effect service process is a system process of a system, is determined. When the sound effect service process is not a system process of the system, the sound effect service process is set to be a system process of the system.

Abstract: Embodiments are provided for utilizing communication routes based operation mode. In an example implementation, while operating in a normal power mode, a playback device maintains information in a network table, the information includes first information associated with a second playback device of the networked media system and second information associated with a third playback device of the networked media system. The playback device determines that the first playback device is to enter a low power mode to draw less power from a battery of the first playback device relative to the normal power mode, and responsive to the determination, foregoing maintaining of the second information in the network table. Thereafter, the playback device determines that the first playback device is to return to normal power mode; and, and in response, synchronizes with the second playback device based at least in part on the first information for playback of audio content.

Abstract: There is provided a method of computing an ingredient substitute(s), comprising: receiving a target food-recipe data structure, receiving a selection of ingredient(s) for substitution, accessing ingredient substitution data structure(s) each storing substitutes for one of the selected ingredient(s), computing adjusted food-recipe data structure(s) that include a predefined textual code that replaces one of the selected ingredients for substitution, computing for each of the adjusted food-recipe data structures, by a trained neural network, coordinates of a respective adjusted point within a multi-dimensional space, determining, for each of the adjusted food-recipe data structures, the value of the respective coordinates corresponding to each one of the substitute ingredient(s) corresponding to the selected ingredient for substitution, selecting, for each of the selected ingredients for substitution, substitute ingredient indication(s) from the corresponding ingredient substitution data structure according to

Abstract: A system, method, and apparatus for media content marking and tracking are disclosed.

Abstract: A microphone and its manufacturing method, relating the semiconductor techniques, are presented. The microphone comprises: a substrate comprising an opening, a first electrode layer at the bottom of the opening, and at least one groove adjacent to the first electrode layer, with the groove and the opening on two opposing sides of a bottom surface of the first electrode layer; a separation material layer filling the groove; and a second electrode layer on the separation material layer, wherein the first electrode layer, the separation material layer, and the second electrode layer form a cavity. In this inventive concept, the separation material layer on the groove works as an anchor node embedding in the substrate to increases the effective contact area and the bonding power, and to improve the bonding quality between the second electrode layer and the substrate, which results in a strengthened second electrode layer.

Abstract: A system includes an analog-to-digital converter receiving input signals. One particular input signal has a particular analog value, and the analog-to-digital converter uses a fixed reference to convert the particular analog value to a particular digital value. The analog-to-digital converter uses the particular analog value as a reference for converting the analog values of the remaining input signals.

Abstract: A system uses a voice energy detection (VED) circuit along with a capture buffer for improved performance and lower power dissipation. With a VED assigned to each microphone in the system, combing the output of more than one VED to improve the detection probability or reduce the false alarm rate improves the post detection signal-to-noise ratio. One or more VED circuits are dynamically selected based on background energy and detection performance. Further, a digital VED algorithm dynamically changes the oversampling ratio (OSR) values and passband bandwidth as a function of the loudness of the background noise and desired signal levels. If the desired signal or noise is strong, then the OSR is reduced to save power. If desired speech is detected, then the OSR value increases to get the target SNR for the remaining audio processing needs.

Abstract: An example playback device includes programming to perform functions including storing an active volume state variable in memory, where the active volume state variable corresponds to a current playback volume. The functions also include storing a volume limit state variable in memory, where the volume limit state variable corresponds to a playback volume limit of the playback device. The functions also include receiving, from a control device, a command to begin playback of media, and determining whether the control device is located in a second zone of the media playback system different from the first zone. Based on whether the control device is located in the second zone of the media playback system different from the first zone, the functions include selecting a startup playback volume to be one of the current playback volume or the playback volume limit, and then playing back media at the startup playback volume.