Abstract: A method for foreign language learning between a learner and a terminal, based on video or audio containing foreign language, particularly, to a conversation-based foreign language learning method using a speech recognition function and a TTS function of a terminal, a learner learns a foreign language in a way that: the terminal reads a current learning target sentence to the learner to allow the learner to speak the current learning target sentence after the terminal, when speech input by the learner in a speech waiting state of the terminal is the same as the current learning target sentence or belongs to the same category as the current learning target sentence; and the terminal and the learner alternately speak sentences one-by-one when the speech input by the learner is the same as the next sentence of the current learning target sentence or belongs to the same category as the next sentence.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses a set of speech recognition hypothesis samples, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Abstract: A text-based virtual object animation generation includes acquiring text information, where the text information includes an original text of a virtual object animation to be generated; analyzing an emotional feature of the text information; performing speech synthesis according to the emotional feature, a rhyme boundary, and the text information to obtain audio information, where the audio information includes emotional speech obtained by conversion based on the original text; and generating a corresponding virtual object animation based on the text information and the audio information, where the virtual object animation is synchronized in time with the audio information.

Abstract: This application discloses an audio processing method and a terminal. The method may include: collecting, by a first terminal, an original speech of a first user, translating the original speech of the first user into a translated speech of the first user, receiving an original speech of a second user that is sent by a second terminal, and translating the original speech of the second user into a translated speech of the second user; sending at least one of the original speech of the first user, the translated speech of the first user, and the translated speech of the second user to the second terminal based on a first setting; and playing at least one of the original speech of the second user, the translated speech of the second user, and the translated speech of the first user based on a second setting.

Abstract: This disclosure describes techniques and architectures for evaluating conversations. In some instances, conversations with users, virtual assistants, and others may be analyzed to identify potential risks within a language model that is employed by the virtual assistants and other entities. The potential risks may be evaluated by administrators, users, systems, and others to identify potential issues with the language model that need to be addressed. This may allow the language model to be improved and enhance user experience with the virtual assistants and others that employ the language model.

Abstract: Technologies are provided for determining deficiencies in narrative textual data that may impact decision-making in a decisional context. A candidate text document and a reference corpus of text may be utilized to generate one or more topic models and document-term matrices, and then to determine a corresponding statistical perplexity and probabilistic coherence. Statistical determinations of a degree to which the candidate deviates from the reference normative corpus are determined, in terms of the statistical perplexity and probabilistic coherence of the candidate as compared to the reference. If the difference is statistically significant, a message may be reported to user, such as the author or an auditor of the candidate text document, so that the user has the opportunity to amend the candidate document so as to improve its adequacy for the decisional purposes in the context at hand.

Abstract: A vehicle device setting method including: capturing, by an image sensing unit, a first image frame; recognizing a user ID according to the first image frame; showing ID information of the recognized user ID on a screen or by a speaker; capturing a second image frame; generating a confirm signal when a first user expression is recognized by calculating an expression feature in the second image frame and comparing the recognized expression feature with stored expression data associated with a predetermined user expression to confirm whether the recognized user ID is correct or not according to the second image frame captured after the ID information is shown; controlling an electronic device according to the confirm signal; and entering a data update mode instructed by the user and updating setting information of the electronic device by current electronic device setting according to a saving signal generated by confirming a second user expression in a third image frame captured after the user ID is confirmed

Abstract: Devices and techniques are generally described for data-to-text generation. In various examples, a first machine learned model may receive first data including a structured representation of linguistic data. In various examples, the first machine learned model may generate first output data comprising a first natural language representation of the first data. In at least some examples, a second machine learning model may determine second data indicating that the first natural language representation is a semantically accurate representation of the first data. In some examples, the first output data may be selected for output based at least in part on the second data.

Abstract: A translation method includes: a first electronic device establishes a call connection to a second electronic device and then displays a call interface; after receiving a first operation of a first user, the first electronic device switches from displaying the call to displaying a translation interface; when receiving a first speech of the first user in a first language, the translation interface sequentially displays at least a first text and a second text, where the first text is obtained by recognizing the first speech, and the second text is obtained by translating the first speech into a target language; and the first electronic device sends a machine speech in the target language to the second electronic device.

Abstract: An eyewear device with camera-based compensation that improves the user experience for user's having partial blindness or complete blindness. The camera-based compensation determines features, such as objects, and then converts the determined objects to audio that is indicative of the objects and that is perceptible to the eyewear user. The camera-based compensation may use a region-based convolutional neural network (RCNN) to generate a feature map including text that is indicative of objects in images captured by a camera. The feature map is then processed through a speech to audio algorithm featuring a natural language processor to generate audio indicative of the objects in the processed images.

Abstract: A network-attached storage device (NAS) includes a non-volatile memory module storing a media stream, a network interface, and control circuitry coupled to the non-volatile memory module and to the network interface and configured to connect to a client over a network connection using the network interface, receive a request for the media stream from the client, determine subtitle preferences associated with the request for the media stream, access an audio stream associated with the media stream, generate subtitles based on the audio stream, and send a transport stream to the client over the network connection, the transport stream including the media stream and the subtitles.

Abstract: This disclosure relates to answer prediction in a speech processing system. The system may disambiguate entities spoken or implied in a request to initiate an action with respect to a target user. To initiate the action, the system may determine one or more parameters; for example, the target (e.g., a contact/recipient), a source (e.g., a caller/requesting user), and a network (voice over internet protocol (VOIP), cellular, video chat, etc.). Due to the privacy implications of initiating actions involving data transfers between parties, the system may apply a high threshold for a confidence associated with each parameter. Rather than ask multiple follow-up questions, which may frustrate the requesting user, the system may attempt to disambiguate or determine a parameter, and skip a question regarding the parameter if it can predict an answer with high confidence. The system can improve the customer experience while maintaining security for actions involving, for example, communications.

Abstract: An image forming system is configured to receive an input of natural language speech. Regardless of whether the natural language speech includes a combination of first words or second words, the image forming system can recognize the natural language speech as an instruction to select a specific print setting displayed on a screen.

Abstract: Methods, systems and computer program products for multi-style text transformation are provided herein. A computer-implemented method includes selecting at least one set of style specifications for transforming at least a portion of input text. The at least one set of style specifications include one or more target writing style domains selected from a plurality of writing style domains, weights for each of the target writing style domains representing relative impact of the target writing style domains for transformation of at least a portion of the input text, and weights for each of a set of linguistic aspects for transformation of at least a portion of the input text. The computer-implemented method also includes generating one or more style-transformed output texts based at least in part on the at least one set of style specifications utilizing at least one unsupervised neural network.

Abstract: In the present invention, a method for searching multilingual keywords in mixlingual speech corpus is proposed. This method is capable of searching audio as well as text keywords. The capability of audio search enables it to search out-of-vocabulary (OOV) words. The capability of searching text keywords enables it to perform semantic search. An advanced application of searching keyword translations in mixlingual speech corpus is also possible within posteriorgram framework with this system. Also, a technique for combining information from text and audio keywords is given which further enhances the search performance. This system is based on multiple posteriorgrams based on articulatory classes trained with multiple languages.

Abstract: The disclosure relates to an artificial intelligence (AI) system using a learned AI model according to at least one of machine learning, neural network, or a deep learning algorithm and applications thereof. In the disclosure, a control method of an electronic apparatus is provided. The control method comprises the steps of: displaying an image including at least one object receiving a voice; inputting the voice to an AI model learned by an AI algorithm to identify an object related to the voice among the at least one object included in the image and acquire tag information about the identified object; and providing the obtained tag information.

Abstract: According to one embodiment, the interface-providing apparatus comprises an identifying unit and a generating unit. The identifying unit identifies a keyword from dialogue data including a question text to request information, and a response text in reply thereto. The generating unit generates display information to display a user interface for receiving feedback input relating to a degree of usefulness of a keyword when searching for the requested information.

Abstract: According to one embodiment, the data generation apparatus includes a speech synthesis unit, a speech recognition unit, a matching processing unit, and a dataset generation unit. The speech synthesis unit generates speech data from an original text. The speech recognition unit generates a recognition text by speech recognition from the speech data. The matching processing unit performs matching between the original text and the recognition text. The dataset generation unit generates a dataset in such a manner where the speech data, from which the recognition text satisfying a certain condition for a matching degree relative to the original text is generated, is associated with the original text, based on a matching result.

Abstract: In various embodiments, a voice command is associated with a plurality of processing steps to be performed. The plurality of processing steps may include analysis of audio data using automatic speech recognition, generating and selecting a search query from the utterance text, and conducting a search of database of items using a search query. The plurality of processing steps may include additional or different steps, depending on the type of the request. In performing one or more of these processing steps, an error or ambiguity may be detected. An error or ambiguity may either halt the processing step or create more than one path of actions. A model may be used to determine if and how to request additional user input to attempt to resolve the error or ambiguity. The voice-enabled device or a second client device is then causing to output a request for the additional user input.

Abstract: A method for identifying errors associated with named entity recognition includes recognizing a candidate named entity within a text and extracting a chunk from the text containing the candidate named entity. The method further includes creating a feature vector associated with the chunk and analyzing the feature vector for an indication of an error associated with the candidate named entity. The method also includes correcting the error associated with the candidate named entity.

Abstract: An AI apparatus includes a microphone to acquire speech data including multiple languages, and a processor to acquire text data corresponding to the speech data, determine a main language from languages included in the text data, acquire a translated text data obtained by translating a text data portion, which has a language other than the main language, in the main language, acquire a morpheme analysis result for the translated text data, extract a keyword for intention analysis from the morpheme analysis result, acquire an intention pattern matched to the keyword, and perform an operation corresponding to the intention pattern.

Abstract: A translation method, implemented by a computer, includes: converting a text written in a first language into a replacement text in which a named entity in the text is replaced with a predetermined character string; translating the replacement text into a second language by using a text translation model which is a neural network; and translating a named entity corresponding to the predetermined character string in the replacement text into the second language by using a named entity translation model which is a neural network.

Abstract: A guidance system S includes a plurality of autonomous mobile robots (1) which guide a user to a destination, and a reception apparatus (2) which is provided separately from the robots (1) and recognizes the destination. Availability of each of the plurality of robots (1) is managed based on a state of the robot and the destination.

Abstract: An information processing system includes: a first device configured to acquire a user's uttered voice, transfer the user's uttered voice to at least one of a second and a third devices each actualizing a voice interaction agent, when a control command is acquired, convert a control signal based on the acquired control command to a control signal that matches the second device, and transmit the converted control signal to the second device; a second device configured to recognize the uttered voice transferred from the first device, and output, to the first device, a control command regarding a recognition result obtained by recognizing the uttered voice and response data based on the control signal; and a third device configured to recognize the uttered voice transferred from the first device, and output, to the first device, a control command regarding a recognition result obtained by recognizing the uttered voice.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer-readable storage media, for speech recognition using attention-based sequence-to-sequence models. In some implementations, audio data indicating acoustic characteristics of an utterance is received. A sequence of feature vectors indicative of the acoustic characteristics of the utterance is generated. The sequence of feature vectors is processed using a speech recognition model that has been trained using a loss function that uses N-best lists of decoded hypotheses, the speech recognition model including an encoder, an attention module, and a decoder. The encoder and decoder each include one or more recurrent neural network layers. A sequence of output vectors representing distributions over a predetermined set of linguistic units is obtained. A transcription for the utterance is obtained based on the sequence of output vectors. Data indicating the transcription of the utterance is provided.

Abstract: A system enhances existing audio-visual content with audio describing the setting of the visual content. A scene annotation module classifies scene elements from an image frame received from a host system and generates a caption describing the scene elements.

Abstract: A device includes a memory adapted to store a list in a file or database comprising a plurality of vocabulary words in a first language and, for each vocabulary word, a corresponding word in a second language, a display device, and a processor. The processor is adapted to receive a plurality of words in the first language, select one or more words among the plurality of words, based on one or more predetermined criteria, translate, match or equate the one or more selected words from the first language to words of the second language, and cause the display device to display the plurality of words, wherein one or more first words that are in the plurality of words and are not among the one or more selected words which are displayed in the first language and one or more second words that are in the plurality of words and are among the one or more selected words are displayed in the second language.

Abstract: A co-user list may be configured based on user interaction in a virtual world environment. A first user may be enabled to navigate the virtual world environment using an instant messenger application that includes the co-user list. A second user that is located proximate to the first user in the virtual world environment may be detected. An attribute associated with the second user may be determined. The co-user list may be configured based on the attribute associated with the second user.

Abstract: Systems and methods are described for processing and interpreting audible commands spoken in one or more languages. Speech recognition systems disclosed herein may be used as a stand-alone speech recognition system or comprise a portion of another content consumption system. A requesting user may provide audio input (e.g., command data) to the speech recognition system via a computing device to request an entertainment system to perform one or more operational commands. The speech recognition system may analyze the audio input across a variety of linguistic models, and may parse the audio input to identify a plurality of phrases and corresponding action classifiers. In some embodiments, the speech recognition system may utilize the action classifiers and other information to determine the one or more identified phrases that appropriately match the desired intent and operational command associated with the user's spoken command.

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating contextually relevant transcripts of voice recordings based on social networking data. For instance, the disclosed systems receive a voice recording from a user corresponding to a message thread including the user and one or more co-users. The disclosed systems analyze acoustic features of the voice recording to generate transcription-text probabilities. The disclosed systems generate term weights for terms corresponding to objects associated with the user within a social networking system by analyzing user social networking data. Using the contextually aware term weights, the disclosed systems adjust the transcription-text probabilities. Based on the adjusted transcription-text probabilities, the disclosed systems generate a transcript of the voice recording for display within the message thread.

Abstract: An embodiment includes converting an original audio signal to an original text string, the original audio signal being from a recording of the original text string spoken by a specific person in a source language. The embodiment generates a translated text string by translating the original text string from the source language to a target language, including translation of a word from the source language to a target language. The embodiment assembles a standard phoneme sequence from a set of standard phonemes, where the standard phoneme sequence includes a standard pronunciation of the translated word. The embodiment also associates a custom phoneme with a standard phoneme of the standard phoneme sequence, where the custom phoneme includes the specific person's pronunciation of a sound in the translated word. The embodiment synthesizes the translated text string to a translated audio signal including the translated word pronounced using the custom phoneme.

Abstract: Provided are a speech translation method and apparatus, an electronic device and a storage medium. The method includes: acquiring a source speech corresponding to a to-be-translated language; acquiring a specified target language; inputting the source speech and indication information matched with the target language into a pre-trained speech translation model, where the speech translation model is configured to translate a language in a first language set into a language in a second language set, the first language set includes a plurality of languages, the first language set includes the to-be-translated language, the second language set includes a plurality of languages, and the second language set includes the target language; and acquiring a translated speech corresponding to the target language and output by the speech translation model; where the to-be-translated language is different from the target language.

Abstract: Enhanced graphical user interfaces for transcription of audio and video messages is disclosed. Audio data may be transcribed, and the transcription may include emphasized words and/or punctuation corresponding to emphasis of user speech. Additionally, the transcription may be translated into a second language. A message spoken by a user depicted in one or more images of video data may also be transcribed and provided to one or more devices.

Abstract: A computer-implemented method of building a multilingual acoustic model for automatic speech recognition in a low resource setting includes training a multilingual network on a set of training languages with an original transcribed training data to create a baseline multilingual acoustic model. Transliteration of transcribed training data is performed by processing through the multilingual network a plurality of multilingual data types from the set of languages, and outputting a pool of transliterated data. A filtering metric is applied to the pool of transliterated data output to select one or more portions of the transliterated data for retraining of the acoustic model. Data augmentation is performed by adding one or more selected portions of the output transliterated data back to the original transcribed training data to update training data. The training of a new multilingual acoustic model through the multilingual network is performed using the updated training data.

Abstract: In one aspect, a server that receives, from a client terminal via a network, a request to initiate a verbal conversation using natural language that is in a spoken or textual format, extracts information during the verbal conversation, determines a context of the verbal conversation, receives an inquiry during the verbal conversation, processes the inquiry, acquires response information based on the determined appropriate response, and transmits to the client terminal the response information.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. In accordance with one example, a method includes, at an electronic device with one or more processors, memory, and a plurality of microphones, sampling, at each of the plurality of microphones of the electronic device, an audio signal to obtain a plurality of audio signals; processing the plurality of audio signals to obtain a plurality of audio streams; and determining, based on the plurality of audio streams, whether any of the plurality of audio signals corresponds to a spoken trigger. The method further includes, in accordance with a determination that the plurality of audio signals corresponds to the spoken trigger, initiating a session of the digital assistant; and in accordance with a determination that the plurality of audio signals does not correspond to the spoken trigger, foregoing initiating a session of the digital assistant.

Abstract: In one embodiment, an eyeglass frame includes a lens holder, a first temple with a first end close to the lens holder and a second end, a second temple, an electrical connector and a printed circuit board. The printed circuit board with at least one electrical component can be in the first temple. The connector can be close to the first end of the first temple, facing downward, and electrically connected to the at least one electrical component. In another embodiment, an eyeglass frame includes a first printed circuit board, with at least one electrical component. The first printed circuit board can be connected to an electrical component at the frame via a second printed circuit board.

Abstract: A method and apparatus for correcting a wrongly-translated word in a device employing speech recognition is provided herein. During operation, a device will use a second language to correct a wrongly-translated word that was wrongly translated using a first language. More particularly, after speech recognition is performed using the first language, when a user selects text to be corrected, the user will utter the speech again using the second language that differs from the first language. Both the first and the second language can be used by the device to determine a best translation of the speech.

Abstract: An artificial intelligence (AI) system is provided. The AI system simulates functions of human brain such as recognition and judgment by utilizing a machine learning algorithm such as deep learning, etc. and an application of the AI system. A method, performed by an electronic device, of outputting a response to a speech input by using an application, includes receiving the speech input, obtaining text corresponding to the speech input by performing speech recognition on the speech input, obtaining metadata for the speech input based on the obtained text, selecting at least one application from among a plurality of applications for outputting the response to the speech input based on the metadata, and outputting the response to the speech input by using the selected at least one application.

Abstract: A semantic processing method includes the following steps of: segmenting an input sentence into a plurality of lexicons according to a lexicon database, wherein the lexicon table includes a plurality of table blocks, and the table blocks are respectively located at a plurality of levels of the lexicon table; referring one part of speech or a plurality of parts of speech, corresponding to one of the lexicons of the table blocks, in the lexicon database; performing at least one grammar rule for each of the table blocks of the levels according to the part of speech, the plurality of parts of speech, the part of speech sequence or the plurality of part of speech sequences corresponding to the table blocks of the lexicon table; and outputting a parse tree according to the table blocks in the lexicon table that conform to the at least one grammar rule.

Abstract: A device includes a memory adapted to store a list in a file or database comprising a plurality of vocabulary words in a first language and, for each vocabulary word, a corresponding word in a second language, a display device, and a processor. The processor is adapted to receive a plurality of words in the first language, select one or more words among the plurality of words, based on one or more predetermined criteria, translate, match or equate the one or more selected words from the first language to words of the second language, and cause the display device to display the plurality of words, wherein one or more first words that are in the plurality of words and are not among the one or more selected words which are displayed in the first language and one or more second words that are in the plurality of words and are among the one or more selected words are displayed in the second language.

Abstract: A system receives, at a translation device, a first domain name service request. The first domain name service request is from a voice-based communication device receives an audible request. The translation device translates the first domain name service request into a format recognizable by a service provider and then subsequently transmits the translated first domain name service request to the service provider. The service provider may perform a first domain name service in response to the translated first domain name service request to produce first domain name service information. The system may transmit the first domain name service information from the service provider to the translation device, which translates the first domain name service information into a format recognizable by the voice-based communication device and then subsequently transmits the translated first domain name service information to the voice-based communication device.

Abstract: In a general aspect, a head-mounted device (HMD) can be configured to receive a selection of a mode of operation of a content reader of the HMD from a plurality of modes of operation, and initiate, in response to the selection, a content capture process to capture content within a field of view (FOV) of a camera of the HMD. The HMD can be further configured to identify, in the captured content, a plurality of content items, receive a navigation command to select a content item from the plurality of content items, and provide, in response to the navigation command, readback of the selected content item.

Abstract: A dialog generator receives data corresponding to desired dialog, such as application programming interface (API) information and sample dialog. A first model corresponding to an agent simulator and a second model corresponding to a user simulator take turns creating a plurality of dialog outlines of the desired dialog. The dialog generator may determine that one or more additional APIs are relevant to the dialog and may create further dialog outlines related thereto. The dialog outlines are converted to natural dialog to generate the dialog.

Abstract: An exemplary speech presentation system receives a simulated binaural audio signal merging together a plurality of concurrent speech instances originating from a plurality of different speakers speaking concurrently. The speech presentation system also receives acoustic propagation data representative of respective propagation effects applied, within the simulated binaural audio signal, to each of the concurrent speech instances to simulate propagation of the concurrent speech instances. Based on the acoustic propagation data, the speech presentation system extracts, from the simulated binaural audio signal, a different auto-transcribable speech signal for each of the plurality of concurrent speech instances. Additionally, based on the extracted auto-transcribable speech signals, the speech presentation system generates a different closed captioning dataset for each of the plurality of concurrent speech instances. Corresponding methods and systems are also disclosed.

Abstract: In an embodiment, a method includes matching terms of a received query to a database of provider capabilities. The method further includes determining, for each portion of the received query, a respective provider to execute the portion of the received query. The method further includes sending each portion of the received query to its respective provider. The method further includes combining results from each respective provider to a returned query result.

Abstract: Methods and systems for generating search results are disclosed. In some examples, one or more keywords are extracted from one or more stored reviews associated with a merchant offering. A first extracted keyword is associated with a stored listing of the merchant offering. The first extracted keyword may be absent from the stored listing. In response to a search query that includes the first keyword, a set of search results is provided, where the set of search results includes the listing associated with the first keyword.

Abstract: In a voice output apparatus, an acquisition unit acquires a speech of an occupant of a vehicle. A determination unit determines whether or not the acquired speech is asking for repetition or rephrasing. A classification unit classifies, when it is determined that the speech is the asking, the speech according to a type of asking. An output unit outputs a voice sound in accordance with the classified type of the asking based on a content of a voice sound that is a target of the asking.

Abstract: This disclosure describes techniques that include modifying text associated with a sequence of images or a video sequence to thereby generate new text and overlaying the new text as captions in the video sequence. In one example, this disclosure describes a method that includes receiving a sequence of images associated with a scene occurring over a time period; receiving audio data of speech uttered during the time period; transcribing into text the audio data of the speech, wherein the text includes a sequence of original words; associating a timestamp with each of the original words during the time period; generating, responsive to input, a sequence of new words; and generating a new sequence of images by overlaying each of the new words on one or more of the images.

Abstract: Techniques are disclosed for data valuation using language-neutral content addressing techniques in an information processing system. For example, a method comprises the following steps. The method obtains original content in an original language. The method generates a language-neutral representation of the original content. The method then generates an object comprising the language-neutral representation of the original content and at least one valuation algorithm, wherein the at least one valuation algorithm is configured to perform content valuation. The method generates a cryptographic hash value of the object, and stores the object for access using the cryptographic hash value.