Abstract: A system and method for homonym treatment in a speech recognition system and method are provided. The system and method for homonym treatment in a speech recognition system may be used in a mobile wireless communication devices that are voice operated after their initial activation. The system may use a voice command interpreter to identify a correct interpretation for a received word that has one or more homonyms based on the received word and the one or more pieces of grammar for the word includes the inserted information about the one or more homonyms.

Abstract: A system and method for hybrid machine translation approach is based on a statistical transfer approach using statistical and linguistic features. The system and method may be used to translate from one language into another. The system may include at least one database, a rule based translation module, a statistical translation module and a hybrid machine translation engine. The database(s) store source and target text and rule based language models and statistical language models. The rule based translation module translates source text based on the rule based language models. The statistical translation module translates source text based on the statistical language models. A hybrid machine translation engine, having a maximum entropy algorithm, is coupled to the rule based translation module and the statistical translation module and is capable of translating source text into target text based on the rule based and statistical language models.

Abstract: A computer-implemented method for presenting statistical analysis in a natural language textual output comprising: receiving data to be analyzed by the processor; processing the data according to at least one of a plurality of pre-established statistical analysis types, thereby providing processed data; interpreting the processed data by analyzing the processed data to provide a pre-determined natural language text, thereby providing interpreted data; and generating a natural language textual output for the interpreted data according to at least one pre-established rule for converting the interpreted data to a natural language textual output.

Abstract: A method, performed in an electronic device, for assigning a target keyword to a function is disclosed. In this method, a list of a plurality of target keywords is received at the electronic device via a communication network, and a particular target keyword is selected from the list of target keywords. Further, the method may include receiving a keyword model for the particular target keyword via the communication network. In this method, the particular target keyword is assigned to a function of the electronic device such that the function is performed in response to detecting the particular target keyword based on the keyword model in an input sound received at the electronic device.

Abstract: An audio processing system configured to generate, based at least in part on captured sound, an audio signal that includes a speech component corresponding to a user's speech utterance and an audio component corresponding to audio output of another device is described herein. The audio processing system is also configured to receive a reference signal that corresponds to the audio output of the other device. The reference signal may be received as ultrasonic audio output of the other device or from a remote server. The audio processing device then processes the generated audio signal to remove at least a part of the generated audio signal that corresponds to the reference signal.

Abstract: A method for supervising text includes receiving input text in a natural language, the input text including at least one source sentence. The input text is analyzed, which includes, for a source sentence in the input text, generating a syntacetic representation. A target sentence is generated in the same natural language, based on the syntacetic representation. The source sentence is compared with the target sentence to determine whether there is a match. A decision is output, based on the comparison.

Abstract: Disclosed are a method, a device and a system of generation of a modified digital media file based on encoding of a digital media file with decodable data such that the decodable data is indistinguishable through a human ear from a primary audio stream. In one embodiment, a method includes validating a user as a publisher, associating a response action to a message of the user, using a processor and a memory, generating a unique identifier through a hash function applied to the response action, encoding a digital media file with a decodable data using the unique identifier such that the decodable data is indistinguishable from a primary audio stream through a human ear, and generating a modified digital media file based on the encoding of the message with the decodable data such that the decodable data is indistinguishable from a primary audio stream through the human ear.

Abstract: A computer-implemented method, program product, and system, for extracting pieces of text from a plurality of pieces of text. The method includes: primarily evaluating a measure of positive expressions and a measure of negative expressions included in each of pieces of text; secondarily evaluating each of the pieces of text on the basis of a plurality of evaluation functions, where certain evaluation functions among the plurality of evaluation functions include, as variables, the measure of positive expressions and the measure of negative expressions; and extracting a piece of text having an evaluation result with a higher rating in preference to a piece of text having an evaluation result with a lower rating, where the individual evaluation results are based on the same evaluation function among the plurality of evaluation functions.

Abstract: A dictation device includes: an audio input device configured to receive a voice utterance including a plurality of words; a video input device configured to receive video of lip motion during the voice utterance; a memory portion; a controller configured according to instructions in the memory portion to generate first data packets including an audio stream representative of the voice utterance and a video stream representative of the lip motion; and a transceiver for sending the first data packets to a server end device and receiving second data packets including combined dictation based upon the audio stream and the video stream from the server end device. In the combined dictation, first dictation generated based upon the audio stream has been corrected by second dictation generated based upon the video stream.

Abstract: Embodiments relate to a method, apparatus and program product and for generating a natural language processing model for an information domain. The method derives a skeleton of a natural language lexicon from a source model and uses it to form a dictionary. It also applies a set of syntactical rules defining concepts and relationships to the dictionary and expands the skeleton of the natural language lexicon based on a plurality of reference documents from the information domain. Using the expanded skeleton of the natural language lexicon, it also provides a natural language processing model for the information domain.

Abstract: A system, method and computer-readable storage device which balance latency and accuracy of machine translations by segmenting the speech upon locating a conjunction. The system, upon receiving speech, will buffer speech until a conjunction is detected. Upon detecting a conjunction, the speech received until that point is segmented. The system then continues performing speech recognition on the segment, searching for the next conjunction, while simultaneously initiating translation of the segment. Upon translating the segment, the system converts the translation to a speech output, allowing a user to hear an audible translation of the speech originally heard.

Abstract: A processing buffer unit stores an audio signal. A pitch calculation unit and a pitch cycle correction unit calculate a multiple of N as the number of samples in a pitch cycle of the audio signal, in which N is an integer equal to or more than 1. A processing control unit and a start-position movement amount correction unit sequentially determine, as a sample in a start position of a compression process in a time axis domain of the audio signal, a (multiple of N)-th sample from a start position immediately before the start position. An operation unit compresses samples in a predetermined number times the pitch cycle from the sample in the start position in a time axis domain, and sets the number of samples after the compression to be the multiple of N. The present technology, for example, may be applied to an audio signal processing apparatus.

Abstract: A speech recognition system uses, in one embodiment, an extended phonetic dictionary that is obtained by processing words in a user's set of databases, such as a user's contacts database, with a set of pronunciation guessers. The speech recognition system can use a conventional phonetic dictionary and the extended phonetic dictionary to recognize speech inputs that are user requests to use the contacts database, for example, to make a phone call, etc. The extended phonetic dictionary can be updated in response to changes in the contacts database, and the set of pronunciation guessers can include pronunciation guessers for a plurality of locales, each locale having its own pronunciation guesser.

Abstract: A processing system receives an audio signal encoding an utterance and determines that a first portion of the audio signal corresponds to a predefined phrase. The processing system accesses one or more text-dependent models associated with the predefined phrase and determines a first confidence based on the one or more text-dependent models associated with the predefined phrase, the first confidence corresponding to a first likelihood that a particular speaker spoke the utterance. The processing system determines a second confidence for a second portion of the audio signal using one or more text-independent models, the second confidence corresponding to a second likelihood that the particular speaker spoke the utterance. The processing system then determines that the particular speaker spoke the utterance based at least in part on the first confidence and the second confidence.

Abstract: Power consumption for a computing device may be managed by one or more keywords. For example, if an audio input obtained by the computing device includes a keyword, a network interface module and/or an application processing module of the computing device may be activated. The audio input may then be transmitted via the network interface module to a remote computing device, such as a speech recognition server. Alternately, the computing device may be provided with a speech recognition engine configured to process the audio input for on-device speech recognition.

Abstract: Features are disclosed for reducing errors in speech recognition processing. Methods for reducing errors can include receiving multiple speech recognition hypotheses based on an utterance indicative of a command or query of a user and determining a command or query within a grammar having a least amount of difference from one of the speech recognition hypotheses. The determination of the least amount of difference may be based at least in part on a comparison of individual subword units along at least some of the sequence paths of the speech recognition hypotheses and the grammar. For example, the comparison may be performed on the phoneme level instead of the word level.

Abstract: Determining a subject type for an entity in a text segment. A text segment is selected, which includes one or more single-word or multi-word entities. Natural language processing is performed on the selected text segment to identify entities that constitute subjects of the selected text segment. One entity is selected. A variant annotation is associated with the selected entity. The variant annotation reflects multiple subject types for the selected entity and a value for each subject type. The most probable subject type is determined for the selected entity, based on a combination of natural language processing rules and dictionary listings. The value of the annotation is incremented for the subject type corresponding to the most probable subject type for the selected entity, so that the highest value of the annotation indicates the most probable subject type for the selected entity within the selected text segment.

Abstract: A graphical user interface is described for human guided audio source separation in a multi-speaker automated transcription system receiving audio signals representing speakers participating together in a speech session. A speaker avatar for each speaker is distributed about a user interface display to suggest speaker positions relative to each other during the speech session. There also is a speaker highlight element on the interface display for visually highlighting a specific speaker avatar corresponding to an active speaker in the speech session to aid a human transcriptionist listening to the speech session to identify the active speaker. A speech signal processor performs signal processing of the audio signals to isolate an audio signal corresponding to the highlighted speaker avatar.

Abstract: Methods and apparatus to audio watermarking and watermark detection and extracted are described herein. According to an example method, an identifier is encoded in media content when a different identifier has been previously encoded. According to another example method, messages decoded from media content are validated to provide improved decoding accuracy. In another example method, decoded symbols are stored in memory and synchronization symbols are located to detect a message encoded in media content.

Abstract: Embodiments of the present invention provide a voice identification method, which includes: obtaining voice data; obtaining a confidence value according to the voice data; obtaining a noise scenario according to the voice data; obtaining a confidence threshold corresponding to the noise scenario; and if the confidence value is greater than or equal to the confidence threshold, processing the voice data. An apparatus is also provided. The method and apparatus that flexibly adjust the confidence threshold according to the noise scenario greatly improve a voice identification rate under a noise environment.