Abstract: Systems and processes for performing unit-selection text-to-speech synthesis are provided. In an example process, text to be converted to speech is received. The text is represented as a sequence of target units. A plurality of candidate speech segments corresponding to the sequence of target units are selected. Predicted statistical parameters of acoustic features associated with the sequence of target units are determined. The predicted statistical parameters of acoustic features are used to determine target costs and concatenation costs associated with the plurality of candidate speech segments. Based on a combined cost determined from the target costs and concatenation costs, a subset of candidate speech segments is selected from the plurality of candidate speech segments. Speech corresponding to the received text is generated using the subset of candidate speech segments.

Abstract: Embodiments of the invention include methods, systems and computer program products for generating at least one control parameter for controlling a signal processor that processes audio signals. A point set is defined, wherein the point set may assume a plurality of topological configurations. Each topological configuration comprises at least one region, each of the at least one region associated with at least one or more topological attributes. A mapping is defined from each of the plurality of topological configurations to a respective plurality of parameters, wherein the mapping is performed based upon the topological attributes of said topological configuration. A user input is received wherein the user input expresses a transformation of the point set from a first topological configuration a second topological configuration. An updated set of topological attributes is determined based upon the second topological configuration.

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 semantically equivalent variants of a natural language term. The mechanism receives an input term for variant analysis. The natural language processing engine executing on the data processing system identifies a semantic type of the input term based on a store of semantic types. The natural language processing engine performs a type-specific series of rule-based expansions of the input term based on the identified semantic type of the input term to form a set of semantically equivalent variants of the input term. The natural language processing engine performs a natural language processing operation using the input term and the set of semantically equivalent variants of the input term.

Abstract: The disclosure describe a system and method for detecting one or more segments of desired speech utterances from an audio stream using timings of events from other modes that are correlated to the timings of the desired segments of speech. The redundant information from other modes results in a highly accurate and robust utterance detection.

Abstract: An estimate of a fractional chirp rate of a signal may be computed by using multiple frequency representations of the signal. A first frequency representation may be computed using a first fractional chirp rate and a first score may be computed using the first frequency representation that indicates a match between the first fractional chirp rate and a fractional chirp rate of the signal. A second frequency representation may be computed using a second fractional chirp rate and a second score may be computed using the second frequency representation that indicates a match between the second fractional chirp rate and the fractional chirp rate of the signal. The fractional chirp rate of the signal may be estimated using the first score and the second score, for example, by selecting a fractional chirp rate corresponding to a highest score.

Abstract: The embodiments herein provide a system and method for translation of static and dynamic. content in digital applications. The embodiments provide a system and method for contextual translation of static and dynamic content on digital applications based on user-defined triggers. Currently available methods are pre-configured for content that is already part of the application, the applications do not localize or translate dynamically generated content. The present embodiments provide a system for contextual translation of static and dynamic content on digital applications. The system enables localization of multiple aspects of digital content, such as static and dynamic content, language, push notifications etc. based on multiple user-defined triggers such as history of user preferences, usage pattern of the user, input method, location of user etc. The system also provides a rank-based priority for localization of content based on analyses of usage pattern.

Abstract: This disclosure covers systems and methods that create references for locating a translation of a term expressed within a digital communication. In particular, in certain embodiments, the disclosed systems and methods create a hashkey to identify a translation (or multiple translations) of an initial term from a source language to a target language. By referring to this hashkey corresponding to the initial term, the disclosed systems and methods can identify a translation (or multiple translations) of the same or similar term within a digital communication to translate a digital communication from a source language to a target language.

Abstract: A mechanism is provided in a data processing system having a processor and a memory storing instructions for implementing a natural language processing engine, a store of semantic types, and a store of units, conversions among units, and variants of unit names, for generating semantically equivalent variants of a natural language term. The mechanism receives an input term for variant analysis. The natural language processing engine executing on the data processing system identifies a semantic type of the input term based on the store of semantic types. The natural language processing engine extracts a quantity and a unit from the input term based on the store of units, conversions among units, and variants of unit names. The natural language processing engine populates type-specific templates at a level of specificity based on the input term based on the identified semantic type of the input term and the extracted quantity and unit to form a set of semantically equivalent variants of the input term.

Abstract: It is disclosed inter alia a method comprising: estimating a value of entropy for a multi-channel audio signal; determining a channel configuration of the multi-channel audio signal from the value of entropy; and encoding the multi-channel audio signal, wherein the mode of encoding is dependent on the channel configuration.

Abstract: An audio signal transmission device for encoding an audio signal includes an audio encoding unit that encodes an audio signal and a side information encoding unit that calculates and encodes side information from a look-ahead signal. An audio signal receiving device for decoding an audio code and outputting an audio signal includes: an audio code buffer that detects packet loss based on a received state of an audio packet, an audio parameter decoding unit that decodes an audio code when an audio packet is correctly received, a side information decoding unit that decodes a side information code when an audio packet is correctly received, a side information accumulation unit that accumulates side information obtained by decoding a side information code, an audio parameter missing processing unit that outputs an audio parameter upon detection of audio packet loss, and an audio synthesis unit that synthesizes decoded audio from the audio parameter.

Abstract: The present document relates to audio signal processing in general, and to the concealment of artifacts that results from loss of audio packets during audio transmission over a packet-switched network, in particular. A method (200) for concealing one or more consecutive lost packets (412, 413) is described. A lost packet (412) is a packet which is deemed to be lost by a transform-based audio decoder. Each of the one or more lost packets (412, 413) comprises a set of transform coefficients (313). A set of transform coefficients (313) is used by the transform-based audio decoder to generate a corresponding frame (412, 413) of a time domain audio signal. The method (200) comprises determining (205) for a current lost packet (412) of the one or more lost packets (412, 413) a number of preceding lost packets from the one or more lost packets (313); wherein the determined number is referred to as a loss position.

Abstract: Features that may be computed from a harmonic signal include a fractional chirp rate, a pitch, and amplitudes of the harmonics. A fractional chirp rate may be estimated, for example, by computing scores corresponding to different fractional chirp rates and selecting a highest score. A first pitch may be computed from a frequency representation that is computed using the estimated fractional chirp rate, for example, by using peak-to-peak distances in the frequency distribution. A second pitch may be computed using the first pitch, and a frequency representation of the signal, for example, by using correlations of portions of the frequency representation. Amplitudes of harmonics of the signal may be determined using the estimated fractional chirp rate and second pitch. Any of the estimated fractional chirp rate, second pitch, and harmonic amplitudes may be used for further processing, such as speech recognition, speaker verification, speaker identification, or signal reconstruction.

Abstract: A speech recognition apparatus that controls one or more devices by using speech recognition, including: a speech obtainer that obtains speech information representing speech spoken by a user; a speech recognition processor that recognizes the speech information, obtained by the speech obtainer, as character information; and a recognition result determiner that determines, based on the character information recognized by the speech recognition processor, whether the speech is spoken to the device(s).

Abstract: A high quality speech is reproduced with a small data amount in speech coding and decoding for performing compression coding and decoding of a speech signal to a digital signal. In speech coding method according to a code-excited linear prediction (CELP) speech coding, a noise level of a speech in a concerning coding period is evaluated by using a code or coding result of at least one of spectrum information, power information, and pitch information, and various excitation codebooks are used based on an evaluation result.

Abstract: Technologies are described herein that allow a user to wake up a computing device operating in a low-power state and for the user to be verified by speaking a single wake phrase. Wake phrase recognition is performed by a low-power engine. In some embodiments, the low-power engine may also perform speaker verification. In other embodiments, the mobile device wakes up after a wake phrase is recognized and a component other than the low-power engine performs speaker verification on a portion of the audio input comprising the wake phrase. More than one wake phrases may be associated with a particular user, and separate users may be associated with different wake phrases. Different wake phrases may cause the device transition from a low-power state to various active states.

Abstract: Provided are a method and apparatus for encoding and decoding an audio signal. According to the present application, a signal of a high frequency band above a preset frequency band is adaptively encoded or decoded in the time domain or in the frequency domain by using a signal of a low frequency band below the preset frequency band. As such, the sound quality of a high frequency signal is not deteriorate even when an audio signal is encoded or decoded by using a small number of bits and thus coding efficiency may be maximized.

Abstract: An estimate of a pitch of a signal may be computed by using peak-to-peak distances in a frequency representation of the signal. A frequency representation of the signal may be computed, peaks in the frequency representation may be identified, for example, by identifying peaks larger than a threshold value. Peak-to-peak distances may be determined using the locations in frequency of the peaks. The pitch of the signal may be estimated by, for example, estimating cumulative distribution function of the peak-to-peak distances or computing a histogram of the peak-to-peak distances.

Abstract: According to an embodiment, a text-to-speech device includes a context acquirer, an acoustic model parameter acquirer, a conversion parameter acquirer, a converter, and a waveform generator. The context acquirer is configured to acquire a context sequence affecting fluctuations in voice. The acoustic model parameter acquirer is configured to acquire an acoustic model parameter sequence that corresponds to the context sequence and represents an acoustic model in a standard speaking style of a target speaker. The conversion parameter acquirer is configured to acquire a conversion parameter sequence corresponding to the context sequence to convert an acoustic model parameter in the standard speaking style into one in a different speaking style. The converter is configured to convert the acoustic model parameter sequence using the conversion parameter sequence. The waveform generator is configured to generate a voice signal based on the acoustic model parameter sequence acquired after conversion.

Abstract: Some examples include generating a personal language model based on linguistic characteristics of one or more files stored at one or more locations in a file system. Further, some implementations include predicting and presenting a non-Latin character string based at least in part on the personal language model, such as in response to receiving a Latin character string via an input method editor interface.

Abstract: A crossover protection system including a product transport vehicle having a tank compartment for containing a liquid product, a fluid property sensor positioned to contact liquid product stored in the tank compartment, a system controller, and a valve coupled to the tank compartment. The valve regulates a flow of liquid product from the tank compartment and has a normally locked state. The system controller may compare a received transported liquid type signal from the fuel property sensor indicative of the type of liquid product in the tank compartment and compare the type of liquid product to a stored liquid product type. If the two types match, the crossover protection controller transitions the valve to an unlocked state to allow the liquid product to unload from the tank compartment. If the two types do not match, the crossover protection controller will disable the valve from transitioning to the unlocked state.