Abstract: Generating, updating, and using a knowledge graph. Concepts in a knowledge graph can have relations to one another. These relations may be expressed as confidence values. A training data set may be split into two portions, with the first portion used to update confidence values for existing relations between concept pairs, using the knowledge graph. These confidence values can be used, together with the second portion used to update confidence values for known phrases that express known relations. These confidence values, in turn, can be used, together with the first portion, to increase the accuracy of the original confidence scores with respect to existing relations. The process may be iteratively employed, with each iteration increasing the accuracy of confidence scores.

Abstract: Embodiments relate to a system and a method for identifying, from contractual documents, (i) standard exact clauses matching clause examples and (ii) non-standard clauses semantically related to but not matching the clause examples. A standard feature data set comprising standard exact clauses matching clause examples is obtained. In addition, a mirror feature data set comprising semantically related clauses of the clause examples is obtained using semantic language analysis, where the mirror feature data set encompasses the standard feature data set. Non-standard clauses are obtained by extracting a difference between the mirror feature data set and the standard exact feature data set.

Abstract: A transliteration processing device according to one embodiment includes a character string acquisition unit that acquires a first alphabetic character string representing by alphabet a first word written in a first language having a specified script and a second alphabetic character string representing by alphabet a second word written in a second language having a different script from the first language, a determination unit that makes a determination whether a first consonant element included in the first alphabetic character string and a second consonant element included in the second alphabetic character string have a predetermined correspondence, and determines whether the first word and the second word have a transliteration relationship based on a result of the determination, and an output unit that outputs, as a transliteration pair, the first word and the second word determined to have a transliteration relationship by the determination unit.

Abstract: A voice synthesis method for generating a voice signal through connection of a phonetic piece extracted from a reference voice, includes selecting, by a piece selection unit, the phonetic piece sequentially; setting, by a pitch setting unit, a pitch transition in which a fluctuation of an observed pitch of the phonetic piece is reflected based on a degree corresponding to a difference value between a reference pitch being a reference of sound generation of the reference voice and the observed pitch of the phonetic piece selected by the piece selection unit; and generating, by a voice synthesis unit, the voice signal by adjusting a pitch of the phonetic piece selected by the piece selection unit based on the pitch transition generated by the pitch setting unit.

Abstract: Mechanisms for identifying hidden meaning in a portion of natural language content are provided. A primary portion of natural language content is received and a secondary portion of natural language content is identified that references the natural language content. The secondary portion of natural language content is analyzed to identify indications of meaning directed to elements of the primary portion of natural language content. A probabilistic model is generated based on the secondary portion of natural language content modeling a probability of hidden meaning in the primary portion of natural language content. A hidden meaning statement data structure is generated for the primary portion of natural language content based on the probabilistic model.

Abstract: An apparatus for decoding an encoded signal includes: an audio decoder for decoding an encoded representation of a first set of first spectral portions to obtain a decoded first set of first spectral portions; a parametric decoder for decoding an encoded parametric representation of a second set of second spectral portions to obtain a decoded representation of the parametric representation, wherein the parametric information includes, for each target frequency tile, a source region identification as a matching information; and a frequency regenerator for regenerating a target frequency tile using a source region from the first set of first spectral portions identified by the matching information.

Abstract: Apparatus and methods for generating an encoded audio bitstream, including by including substream structure metadata (SSM) and/or program information metadata (PIM) and audio data in the bitstream. Other aspects are apparatus and methods for decoding such a bitstream, and an audio processing unit (e.g., an encoder, decoder, or post-processor) configured (e.g., programmed) to perform any embodiment of the method or which includes a buffer memory which stores at least one frame of an audio bitstream generated in accordance with any embodiment of the method.

Abstract: A system that incorporates teachings of the present disclosure may include, for example, a controller configured to obtain information associated with media content, to generate a first group of tones representative of the information associated with the media content, and to generate a media stream comprising the media content and the first group of tones; and a communication interface configured to transmit the media stream to a media device whereby the media device presents the media content and a sequence of tones, where the sequence of tones is generated based at least in part on the first group of tones, where the first group of tones comprises high frequency tones and low frequency tones, and where one of the high and low frequency tones represents a binary one and the other of the high and low frequency tones represents a binary zero. Other embodiments are disclosed.

Abstract: The disclosure provides a method and an apparatus for detecting a voice activity in an input audio signal composed of frames. A noise characteristic of the input signal is determined based on a received frame of the input audio signal. A voice activity detection (VAD) parameter is derived based on the noise characteristic of the input audio signal using an adaptive function. The derived VAD parameter is compared with a threshold value to provide a voice activity detection decision. The input audio signal is processed according to the voice activity detection decision.

Abstract: An audio packet error concealment system includes an encoding unit for encoding an audio signal consisting of a plurality of frames, and an auxiliary information encoding unit for estimating and encoding auxiliary information about a temporal change of power of the audio signal. The auxiliary information is used in packet loss concealment in decoding of the audio signal. The auxiliary information about the temporal change of power may contain a parameter that functionally approximates a plurality of powers of subframes shorter than one frame, or may contain information about a vector obtained by vector quantization of a plurality of powers of subframes shorter than one frame.

Abstract: An apparatus for generating at least one audio output signal based on an audio data stream having audio data relating to one or more sound sources is provided. The apparatus has a receiver for receiving the audio data stream having the audio data. The audio data has one or more pressure values for each one of the sound sources. Furthermore, the audio data has one or more position values indicating a position of one of the sound sources for each one of the sound sources. Moreover, the apparatus has a synthesis module for generating the at least one audio output signal based on at least one of the one or more pressure values of the audio data of the audio data stream and based on at least one of the one or more position values of the audio data of the audio data stream.

Abstract: An objective of the present invention is to correct a temporal envelope shape of a decoded signal with a small information volume and to reduce perceptible distortions.

Abstract: A speech-based system includes a local device in a user premises and a remote service that uses the local device to conduct speech dialogs with a user. The local device may also be directed to play audio such as music, audio books, etc. When designating audio for playing by the local device, the remote service may specify that the audio is either background audio or foreground audio. For background audio, the service indicates whether the background audio is mixable. For foreground audio, the service indicates an interrupt behavior. When the local device is playing background audio and receives foreground audio, the background audio is paused, attenuated, or not changed based on the indicated interrupt behavior of the foreground audio and whether the background audio has been designated as being mixable.

Abstract: Apparatus and methods for generating an encoded audio bitstream, including by including substream structure metadata (SSM) and/or program information metadata (PIM) and audio data in the bitstream. Other aspects are apparatus and methods for decoding such a bitstream, and an audio processing unit (e.g., an encoder, decoder, or post-processor) configured (e.g., programmed) to perform any embodiment of the method or which includes a buffer memory which stores at least one frame of an audio bitstream generated in accordance with any embodiment of the method.

Abstract: A system and method for dynamically selecting speech recognition functionality on a client device for recognizing user speech inputs are disclosed. Such selection may be made based on speech recognition functionalities actually available on the client devices. The speech functionalities that may be dynamically selected may include, without limitation, speech recognition software and/or services, speech libraries, kernel drivers, speech recognition hardware, audio hardware, and/or any other speech functionality available on a client device. User speech inputs may be processed via the selected speech functionality for generating control commands in a virtual space. In some implementations, remote speech recognition support may be evoked when a client device does not have any speech recognition functionality on the client device.

Abstract: A method and an apparatus for signal extraction of audio signal are provided. An audio signal is converted into a plurality of frames, and the frames are arranged in a chronological order. Spectral data of each of the frames is obtained. The spectral data of each of N frames is extracted in the chronological order, and a spectral connectivity operation is executed for the N frames. Finally, the signal including the frames having the spectral connectivity between adjacent frames in each of the frames is determined as an ideal signal.

Abstract: This disclosure includes, for example, methods and computer systems for providing audio-activated resource access for user devices. The computer systems may store instructions to cause the processor to perform operations, comprising capturing audio at a user device. The operations may also comprise using a speaker recognition system to identify a speaker in the transmitted audio and/or using a speech-to-text converter to identify text in the captured audio. The speaker identity or a condensed version of the speaker identity or other metadata along with the speaker identity may be transmitted to a server system to determine a corresponding speaker identity entry. The operations may also comprise receiving a resource corresponding to the identified speaker entry in the server system.

Abstract: An audio processing unit (APU) is disclosed. The APU includes a buffer memory configured to store at least one frame of an encoded audio bitstream, where the encoded audio bitstream includes audio data and a metadata container. The metadata container includes a header and one or more metadata payloads after the header. The one or more metadata payloads include dynamic range compression (DRC) metadata, and the DRC metadata is or includes profile metadata indicative of whether the DRC metadata includes dynamic range compression (DRC) control values for use in performing dynamic range compression in accordance with at least one compression profile on audio content indicated by at least one block of the audio data.

Abstract: A computer-implemented system and method for correlating activity within a user interface with special information is provided. A user interface with data entry fields is provided. One or more of the data entry fields is designated for special information. A first screen shot of the user interface is captured, and a second screen shot of the user interface is captured at a later time. The first and second screen shots are compared. A change comprising at least a portion of an entry within one of the data entry fields for special information in the second screen shot is identified between the first and second screen shots. The entry is rendered unintelligible.

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.