Abstract: Methods and computer systems for audio search on a social networking platform are disclosed. The method includes: while running a social networking application, receiving a first audio input from a user of the computer system, the first audio input including one or more search keywords; generating a first audio confusion network from the first audio input; determining whether the first audio confusion network matches at least one of one or more second audio confusion networks, wherein a respective second audio confusion network was generated from a corresponding second audio input associated with a chat session of which the user is a participant; and identifying a second audio input corresponding to the at least one second audio confusion network that matches the first audio confusion network, wherein the identified second audio input includes the one or more search keywords that are included in the first audio input.

Abstract: According to one general aspect a system includes an identification module, a translation module, and a display module. The identification module being configured to identify when an application running within the system attempts to display a work to a user of the application in a first language. The translation module being configured to translate the word from the first language to a second language different than the first language. The display module being configured to display the word in the second language to the user.

Abstract: A sound synthesis device that includes a processor configured to perform the following: extracting intonation information from prosodic information contained in sound data and digitally smoothing the extracted intonation information to obtain smoothed intonation information; obtaining a plurality of digital sound units based on text data and concatenating the plurality of digital sound units so as to construct a concatenated series of digital sound units that corresponds to the text data; and modifying the concatenated series of digital sound units in accordance with the smoothed intonation information with respect to at least one of parameters of the concatenated series of digital sound units to generate synthesized sound data corresponding to the text data.

Abstract: An apparatus for decoding an encoded audio signal including bandwidth extension control data indicating either a first harmonic bandwidth extension mode or a second non-harmonic bandwidth extension mode, includes: an input interface for receiving the encoded audio signal including the bandwidth extension control data indicating either the first harmonic bandwidth extension mode or the second non-harmonic bandwidth extension mode; a processor for decoding the audio signal using the second non-harmonic bandwidth extension mode; and a controller for controlling the processor to decode the audio signal using the second non-harmonic bandwidth extension mode, even when the bandwidth extension control data indicates the first harmonic bandwidth extension mode for the encoded signal.

Abstract: A content alignment service may generate content synchronization information to facilitate the synchronous presentation of audio content and textual content. In some embodiments, a region of the textual content whose correspondence to the audio content is uncertain may be analyzed to determine whether the region of textual content corresponds to one or more words that are audibly presented in the audio content, or whether the region of textual content is a mismatch with respect to the audio content. In some embodiments, words in the textual content that correspond to words in the audio content are synchronously presented, while mismatched words in the textual content may be skipped to maintain synchronous presentation. Accordingly, in one example application, an audiobook is synchronized with an electronic book, so that as the electronic book is displayed, corresponding words of the audiobook are audibly presented.

Abstract: Various implementations disclosed herein include an expert-assisted phoneme recognition neural network system configured to recognize phonemes within continuous large vocabulary speech sequences without using language specific models (“left-context”), look-ahead (“right-context”) information, or multi-pass sequence processing, and while operating within the resource constraints of low-power and real-time devices. To these ends, in various implementations, an expert-assisted phoneme recognition neural network system as described herein utilizes a-priori phonetic knowledge. Phonetics is concerned with the configuration of the human vocal tract while speaking and acoustic consequences on vocalizations. While similar sounding phonemes are difficult to detect and are frequently misidentified by previously known neural networks, phonetic knowledge gives insight into what aspects of sound acoustics contain the strongest contrast between similar sounding phonemes.

Abstract: Various implementations disclosed herein include an expert-assisted phoneme recognition neural network system configured to recognize phonemes within continuous large vocabulary speech sequences without using language specific models (“left-context”), look-ahead (“right-context”) information, or multi-pass sequence processing, and while operating within the resource constraints of low-power and real-time devices. To these ends, in various implementations, an expert-assisted phoneme recognition neural network system as described herein utilizes a-priori phonetic knowledge. Phonetics is concerned with the configuration of the human vocal tract while speaking and acoustic consequences on vocalizations. While similar sounding phonemes are difficult to detect and are frequently misidentified by previously known neural networks, phonetic knowledge gives insight into what aspects of sound acoustics contain the strongest contrast between similar sounding phonemes.

Abstract: A comfort noise controller for generating CN (Comfort Noise) control parameters is described. A buffer of a predetermined size is configured to store CN parameters for SID (Silence Insertion Descriptor) frames and active hangover frames. A subset selector is configured to determine a CN parameter subset relevant for SID frames based on the age of the stored CN parameters and on residual energies. A comfort noise control parameter extractor (50B) is configured to use the determined CN parameter subset to determine the CN control parameters for a first SID frame following an active signal frame.

Abstract: A voice wakeup detecting device for an electronic product includes a digital microphone and an application processor. The digital microphone has a function of judging whether a digital voice signal contains a subword according to subword model parameters. If the digital microphone confirms that the digital voice signal contains the subword, the digital microphone generates a first interrupt signal and outputs the digital voice signal. The application processor is enabled in response to the first interrupt signal. The application processor judges whether the digital voice signal contains a keyword according to keyword model parameters. If the application processor confirms that the digital voice signal contains the keyword, the electronic product is waked up from a sleep state to a normal working state under control of the application processor.

Abstract: A mechanism is provided in a data processing system having a processor and a memory storing a store of semantic types and instructions for implementing a natural language processing engine for generating a question/answer pair list with semantically equivalent variants. The mechanism generates a user interface for generating a question/answer pair list. The mechanism receives user input in the user interface specifying a question and an answer term and specifying an answer type from a list of previously created answer types. The input term comprises the answer term. The natural language processing engine executing on the data processing system identifies a semantic type of the answer term based on the store of semantic types. The natural language processing engine performs a type-specific series of rule-based expansions of the answer term based on the identified semantic type of the answer term of the answer term.

Abstract: An apparatus determining a weighting function for line prediction coding coefficients quantization converts a linear prediction coding (LPC) coefficient of an input signal into one of a line spectral frequency (LSF) coefficient and an immitance spectral frequency (ISF) coefficient and determines a weighting function associated with one of an importance of the ISF coefficient and importance of the LSF coefficient using one of the converted ISF coefficient and the converted LSF coefficient.

Abstract: Methods, systems, computer-readable media, and apparatuses for utilizing voice biometrics to prevent unauthorized access are presented. In some embodiments, a computing device may receive a voice sample. Subsequently, the computing device may determine a voice biometric confidence score based on the voice sample. The computing device then may evaluate the voice biometric confidence score in combination with one or more other factors to identify an attempt to access an account without authorization.

Abstract: Separation of speech and background from an audio mixture by using a speech example, generated from a source associated with a speech component in the audio mixture, to guide the separation process.

Abstract: Systems and methods for spoken term detection are provided. A method for spoken term detection, comprises receiving phone level out-of-vocabulary (OOV) keyword queries, converting the phone level OOV keyword queries to words, generating a confusion network (CN) based keyword searching (KWS) index, and using the CN based KWS index for both in-vocabulary (IV) keyword queries and the OOV keyword queries.

Abstract: A method and a device for encoding a high frequency signal, and a method and a device for decoding a high frequency signal are provided, which relate to encoding and decoding technology. The method for encoding a high frequency signal includes: determining a signal type of a high frequency signal of a current frame; smoothing and scaling time envelopes of the high frequency signal of the current frame and obtaining time envelopes of the high frequency signal of the current frame that require to be encoded, if the high frequency signal of the current frame is a non-transient signal and a high frequency signal of the previous frame is a transient signal; and quantizing and encoding the time envelopes of the high frequency signal of the current frame that require to be encoded, and frequency information and signal type information of the high frequency signal of the current frame.

Abstract: A social media monitoring and text analysis method for automated classification of user posts on the web, using a facet based relevance assessment model, comprise a semantic indexing server, which builds a faceted classification index of text objects, and a query server, which receives and analyzes the user's query. A query thus processed is then sent from the query server to the semantic indexing server through an interface in order to perform a search in the faceted classification index. The search system and method further comprise a result handler, which provides the user with a search result set comprising a list of unexpected links and a list of result elements. The list of unexpected links corresponds to filters which allow the user to narrow down or refine the original query.

Abstract: Systems and processes for performing unit-selection text-to-speech synthesis are provided. In one example process, a sequence of target units can represent a spoken pronunciation of text. A set of predicted acoustic model parameters of a second target unit can be determined using a set of acoustic features of a first candidate speech segment of a first target unit and a set of linguistic features of the second target unit. A likelihood score of the second candidate speech segment with respect to the first candidate speech segment can be determined using the set of predicted acoustic model parameters of the second target unit and a set of acoustic features of the second candidate speech segment of the second target unit. The second candidate speech segment can be selected for speech synthesis based on the determined likelihood score. Speech corresponding to the received text can be generated using the selected second candidate speech segment.

Abstract: A communication system and a method can be configured to facilitate the performance of a conference. The system can include a conference organizer terminal and at least two participants' terminals each assigned to respective conference participants who each log in to start a conference on the communication system. The communication system can be configured to calculate a decision situation at a particular point in time of the ongoing conference by analyzing the views expressed by the conference participants during the conference and send data relating to the decision situation for that point in time to the conference organizer's terminal and/or other conference participant terminals for use in facilitating the conference. IN some embodiments, such data can be used to assist the conference participants' in recognizing when there is a consensus made on at least one decision to be made during the conference.

Abstract: A method for automatically extracting claim candidates from complex sentences includes providing a parse tree of a text sample to be analyzed, disassembling the parse tree into a set of basic meaning-bearing clauses, assembling clauses of the set of basic clauses into a set of complex coherent statements based on permissible syntactic structures, testing the complex statements and discarding those statements that are not coherent when considered alone, discarding those complex statements that either do not provide additional information about a subject, or are too complex, removing information from a complex statement that provides supportive details about the subject, and discarding statements that restrict their subject, so that the subject cannot be generalized encompass a broader subject.

Abstract: Method and device of processing audio signals are disclosed. The method includes: obtaining a set of data, the set of data comprising LSP parameters for an audio signal; determining a set of sampling data points from the set of LSP parameters using a predetermined sampling rule, the set of sampling data points including spectrum amplitude values for a plurality of sampled frequency values; identifying one or more local maxima among the set of sampling data points, and a respective preceding local minimum and a respective succeeding local minimum for each of the identified local maxima; for each of the identified local maxima, shifting one or more of the set of data comprising LSP parameters located between the respective preceding local minimum and the respective succeeding local minimum of an identified local maximum towards the identified local maximum; and adjusting the set of data comprising LSP parameters using an energy coefficient.