Abstract: A translation assistance system according to one embodiment includes an acquisition unit and a determination unit. The acquisition unit acquires a target translated text obtained by translating a target source text into a target language, and acquires, as a correct word set, a set containing a reference word n-gram forming a reference text written in the target language and independent of the target source text. The determination unit calculates a degree of matching between one or more translated word n-grams forming the target translated text and the correct word set, and determines adequacy of the target translated text based on the degree of matching.

Abstract: The present invention relates to a mobile terminal, an audio output device and an audio output system comprising the same. The mobile terminal according to an embodiment of the present invention comprises: a memory for storing audio data; a communication unit for receiving a repetitive radio signal from the audio output device; and a control unit controlling the audio data such that the audio data is transmitted to the audio output device in a wireless manner when the strength or the level of the repetitive radio signal is a first predetermined value or more, while reproducing the audio data, wherein the communication unit comprises a first communication module for receiving the repetitive radio signal and a second communication module for outputting the audio data to the audio output device. Therefore, the audio output device can output a sound of the audio data reproduced by the mobile terminal.

Abstract: Decoding of Ambisonics representations for a stereo loudspeaker setup is known for first-order Ambisonics audio signals. But such first-order Ambisonics approaches have either high negative side lobes or poor localization in the frontal region. The invention deals with the processing for stereo decoders for higher-order Ambisonics HOA. The desired panning functions can be derived from a panning law for placement of virtual sources between the loudspeakers. For each loudspeaker a desired panning function for all possible input directions at sampling points is defined. The panning functions are approximated by circular harmonic functions, and with increasing Ambisonics order the desired panning functions are matched with decreasing error. For the frontal region between the loudspeakers, a panning law like the tangent law or vector base amplitude panning (VBAP) are used. For the rear directions panning functions with a slight attenuation of sounds from these directions are defined.

Abstract: Audio content may be played back in synchrony with a member of a synchrony group based on playback timing information. While synchronously playing back the audio content, the playback timing information may be transmitted to the member of the synchrony group. The transmitted playback timing information may comprise a first timestamp. In response to a pause command, the synchronous playback may be paused prior to a time indicated by the first timestamp and a second timestamp. While the synchronous playback is paused and in response to a resume command, the member of the synchrony group may be instructed to update the first timestamp based on a new start time indicative of when the synchronous playback is to be resumed and update the second timestamp such that the updated second timestamp is synchronized with the updated first timestamp. The synchronous playback may be resumed based on the updated second timestamp.

Abstract: A method for spoken language understanding (SLU) includes generating a first encoded representation of words from a user based on an output of a recurrent neural network (RNN), generating an intent label corresponding to the words based on an output of a first RNN decoder based on the first encoded representation, generating a corrected plurality of words based on an output of a second RNN decoder based on the first encoded representation and the intent label, generating a second encoded representation corresponding to the plurality of corrected words using the RNN encoder based on the plurality of corrected words, and generating a machine-readable dialog phrase that includes at least one word in the plurality of corrected words assigned to at least one slot based on an output of a third RNN decoder based on the second encoded representation of the plurality of corrected words and the intent label.

Abstract: An example implementation involves a playback device receiving a request to add continuous automated streaming audio content to a playback queue, the request indicating a playback start time, and the playback queue indicating a plurality of audio content. The implementation further involves the playback device adding the continuous automated streaming audio content to the playback queue. The example implementation also involves the playback device determining that a duration until the playback start time is less than a duration of the given audio content before playing a given audio content in the playback queue. The example implementation involves the playback device responsively, playing the continuous automated streaming audio content.

Abstract: Example implementations involve cloud queue synchronization. An example implementation may involve while playing back a particular media item from a local queue of media items, a playback device sending, to a remote server over the network interface, (i) a request for a window of media items from a cloud queue of media items that is accessible to the playback device via a wide area network, and (ii) an indication of the particular media item that is being played by the playback device. The playback device receives, over the network interface in response to the request for the window of media items, an indication of two or more media items from the cloud queue of media items and incorporates an indication of at least one of the two or more media items into the local queue of media items.

Abstract: A method for processing an audio signal is performed at a computing device. The method includes the following steps: receiving a digital stereo audio input signal; extracting localization cues from the digital stereo audio input signal; generating a left-side component and a right-side component from the digital stereo audio input signal, at least partially, in accordance with the localization cues; performing crosstalk cancellation to the left-side component and the right-side component, respectively, to obtain a crosstalk-cancelled left-side component and a crosstalk-cancelled right-side component; and generating a digital stereo audio output signal including the crosstalk-cancelled left-side component and the crosstalk-cancelled right-side component.

Abstract: An approach is described for creating an audio file sample based upon user preferences. An associated method may include detecting selection of an audio file by a user, wherein the selection of the audio file occurs via a communications network and indexing the audio file to create a plurality of indexed segments based upon audio analysis. The method further may include selecting at least one segment among the plurality of indexed segments based upon a profile of the user and incorporating the at least one selected segment into an audio sample having a designated length. Indexing the audio file to create a plurality of indexed segments based upon audio analysis may include, for each audio characteristic among a plurality of designated audio characteristics, creating from the audio file at least one indexed segment corresponding to the audio characteristic.

Abstract: Methods and systems for improving a music experience are described. Multiple users can provide their musical preferences (e.g., favorite artist, group, genre, era, etc.). When the users come within the vicinity of a jukebox, the users' musical preferences are retrieved or determined. Using the combined or shared preferences of the users in the vicinity of the jukebox, the system is able to create or adjust the current playlist of songs, tailoring the music played based on the users listening nearby.

Abstract: A method for performing an active profiling of the sound emitted by a vehicle engine including the steps of injecting second acoustic waves (MW), which are able to combine with the first acoustic waves (EW) in a merge point in said primary propagation path and to generate third resulting acoustic waves (RW); and generating a driving signal for the diffuser by regulating the amplitude of harmonics of the driving signal (SP) as a function of reference acoustic waves and of a workpoint of the engine, calculating equalization coefficients (?1, . . . , ?M) to be applied to the amplitudes of said harmonics of the driving signal (SP) via a self-tuning procedure, and comparing the reference acoustic waves (TW) with a simulation (SRW) of the resulting waves. The simulation (SRW) is obtained by applying to a simulation of the second acoustic waves a model of the secondary propagation path.

Abstract: A method to watermark an audio signal may include receiving watermark data payload information, converting the watermark data payload information into a watermark audio signal including one or more watermark messages corresponding to the watermark data payload information, and inserting the one or more watermark messages into multiple spectral channels of the audio signal, wherein each of the multiple spectral channels occupies a different frequency range, wherein, once an audio segment has been inserted into a spectral channel of the audio signal, amplitude of the audio segment is held constant for the time duration of the audio segment such that a first portion of the audio segment is masked by the audio signal and a second portion of the audio segment is not masked by the audio signal.

Abstract: A state memory can store states of a plurality of users who are sleeping or awake. At least one processor can set priorities among the plurality of users. The at least one processor can select one user as a target user from among the plurality of users based on the states of the plurality of users and the priorities among the plurality of users. The at least one processor can reproduce a content in accordance with the target user.

Abstract: Example implementations involve cloud queue synchronization. An example implementation may involve a cloud server system receiving a request for a window of media items from a cloud queue of media items that is maintained by the cloud server system and sending, to a playback device, the requested window of media items from the cloud queue of media items. The playback device receives the requested window of media items from the cloud queue of media items and populates a local queue with the media items from the window. The playback device also receives, from a mobile device, a request to modify the local queue, and in response to the request to modify the local queue, modifies the local queue according to the request to modify the local queue.

Abstract: An example implementation may involve a computing system receiving, from a media playback system over the network interface, a request to initiate playback of the particular cloud queue at a first media item. The computing system assigns a playhead pointer to a position within the particular cloud queue that corresponds to the first media item and transmits, to the media playback system over the network interface, an instruction that causes one or more playback devices of the media playback system to initiate playback of the particular cloud queue at the first media item. While the one or more playback devices play back the particular cloud queue, the computing system updates the assigned position of the playhead pointer to indicate the currently playing media item of the particular cloud queue.

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: An example non-transitory computer-readable medium stores instructions that, when executed by a control device, cause the control device to perform functions. The functions comprise configuring a first playback device associated with a first user-account to (i) play media content from a playback queue comprising one or more audio tracks stored at a network location and (ii) enable one or more other user-accounts associated with other playback devices to subscribe to the playback queue. The functions further comprise receiving an indication that a second user-account associated with a second playback device has subscribed to the playback queue. The functions further comprise in response to receiving the indication, displaying a subscriber indicator on the control device showing that the second user-account has subscribed to the playback queue. An example control device and an example method, both related to the example non-transitory computer-readable medium, are also disclosed herein.

Abstract: A method for processing an audio signal is performed at a computing device. The method includes the following steps: receiving a digital stereo audio input signal; extracting localization cues from the digital stereo audio input signal; generating a left-side component and a right-side component from the digital stereo audio input signal, at least partially, in accordance with the localization cues; performing crosstalk cancellation to the left-side component and the right-side component, respectively, to obtain a crosstalk-cancelled left-side component and a crosstalk-cancelled right-side component; and generating a digital stereo audio output signal including the crosstalk-cancelled left-side component and the crosstalk-cancelled right-side component.

Abstract: The present invention relates to a new method and apparatus for improvement of High Frequency Reconstruction (HFR) techniques using frequency translation or folding or a combination thereof. The proposed invention is applicable to audio source coding systems, and offers significantly reduced computational complexity. This is accomplished by means of frequency translation or folding in the subband domain, preferably integrated with spectral envelope adjustment in the same domain. The concept of dissonance guard-band filtering is further presented. The proposed invention offers a low-complexity, intermediate quality HFR method useful in speech and natural audio coding applications.

Abstract: A method for processing an audio signal is performed at a computing device. The method includes the following steps: receiving a digital stereo audio input signal; extracting localization cues from the digital stereo audio input signal; generating a left-side component and a right-side component from the digital stereo audio input signal, at least partially, in accordance with the localization cues; performing crosstalk cancellation to the left-side component and the right-side component, respectively, to obtain a crosstalk-cancelled left-side component and a crosstalk-cancelled right-side component; and generating a digital stereo audio output signal including the crosstalk-cancelled left-side component and the crosstalk-cancelled right-side component.