Abstract: A method, apparatus, and system are provided for resolving conflicts between training data conflicts by retrieving independent training data sets, each comprising a plurality of intents and end-user utterances for use in training one or more classifiers to recognize a corresponding intent from one or more of the end-user utterances, providing a first test end-user utterance associated with a first intent from the first independent training data set to the one or more classifiers to select an output intent generated by the one or more classifiers; identifying a first conflict when the first intent does not match the output intent, and automatically generating, by the system, one or more conflict resolution recommendations for display and selection by an end user to resolve the first conflict.

Abstract: The present disclosure relates to a method, device and computer readable storage medium for presenting an emotion. The method for presenting the emotion includes obtaining a first emotion presentation instruction, wherein the first emotion presentation instruction includes at least one first emotion presentation modality and at least one emotional style, and the at least one first emotion presentation modality includes a text emotion presentation modality; and presenting an emotion corresponding to one or more of the at least one emotional style according to each of the at least one first emotion presentation modality. The present disclosure can realize text-based multi-modal emotion presentation modes, and thus user experience can be improved.

Abstract: The present teaching relates to method, system, medium, and implementations for managing a user machine dialogue. Sensor data is received at a device, including an utterance representing a speech of a user engaged in a dialogue with the device. The speech of the user is determined based on the utterance and a response to the user is searched by a local dialogue manager residing on the device against a sub-dialogue tree stored on the device. The response, if identified from the sub-dialogue tree, is rendered to the user in response to the speech. A request is sent to a server for the response, if the response is not available in the sub-dialogue tree.

Abstract: A computer-implemented method includes obtaining, using a hardware processor, training data including utterances of speakers and performing tasks to train a machine learning model that converts an utterance into a feature vector, each task using one subset of multiple subsets of training data. The subsets of training data include a first subset of training data including utterances of a first number of speakers and at least one second subset of training data. Each second subset of training data includes utterances of a number of speakers that is less than the first number of speakers.

Abstract: A text search query including one or more words may be received. An ASR index created for an audio recording may be searched over using the query to produce ASR search results including words, each word associated with a confidence score. For each of the words in the ASR search results associated with a confidence score below a threshold (and in some cases having one or more preceding words in the ASR index and one or more subsequent words in the ASR index), a phonetic representation of the audio recording may be searched for the word having the confidence score below the threshold, where it occurs in the audio recording, possibly after the one or more preceding words and in the audio recording before the one or more subsequent words, to produce phonetic search results. Search results may be returned include ASR and phonetic results.

Abstract: A speech conversion system is described that includes a hierarchical encoder and a decoder. The system may comprise a processor and memory storing instructions executable by the processor. The instructions may comprise to: using a second recurrent neural network (RNN) (GRU1) and a first set of encoder vectors derived from a spectrogram as input to the second RNN, determine a second concatenated sequence; determine a second set of encoder vectors by doubling a stack height and halving a length of the second concatenated sequence; using the second set of encoder vectors, determine a third set of encoder vectors; and decode the third set of encoder vectors using an attention block.

Abstract: A system and method for creating an embedded phoneme map from a corpus of speech in accordance with a multiplicity of acoustic features of the speech. The embedded phoneme map is used to determine how to pronounce borrowed words from a lending language in the borrowing language, using the phonemes of the borrowing language that are closest to the phonemes of the lending language. The embedded phoneme map is also used to help linguists visualize the phonemes being pronounced by a speaker in real-time and to help non-native speakers practice pronunciation by displaying the differences between proper pronunciation and actual pronunciation for open-ended speech by the speaker.

Abstract: A voice synthesis method according to an embodiment includes altering a series of synthesis spectra in a partial period of a synthesis voice based on a series of amplitude spectrum envelope contours of a voice expression to obtain a series of altered spectra to which the voice expression has been imparted, and synthesizing a series of voice samples to which the voice expression has been imparted, based on the series of altered spectra.

Abstract: The present disclosure relates to a dynamic catalog translation system (DCTS) for internationalization of an application in a cloud environment. The DCTS may comprise receiving a catalog, associated with the application, in a first language from a developer device. The DCTS may further comprise receiving a request for the catalog in a second language from a user device running the application. Further, the DCTS may comprise dynamically generating the catalog in the second language in response to the received request from the user. The catalog is generated in a real-time or a near real-time of running the application at the user device. Furthermore, the DCTS may comprise communicating the generated catalog in the second language to the user device so that the application is configured to execute at the user device in the second language.

Abstract: The application discloses a semantic recognition method, an electronic device and a computer-readable medium, belongs to a field of intention recognition. The semantic recognition method includes the following steps: S1, constructing a morpheme database; S2, constructing a synonym database; S3, receiving a service session request of a customer, and creating a customer service session; S4, analyzing contents of the customer service session to obtain a word sequence which only contains the standard words for expressing the customer service session; S5, determining a missing morpheme in the word sequence which only contains the standard words, and asking the customer a question to obtain a completely expressed word sequence which only contains the standard words; S6, according to the completely expressed word sequence which only contains the standard words, finding out a matched answer from the morpheme database and sending the matched answer to the customer.

Abstract: Systems and methods are described herein for replaying content dialogue in an alternate language in response to a user command. While the content is playing on a media device, a first language in which the content dialogue is spoken is identified. Upon receiving a voice command to repeat a portion of the dialogue, the language in which the command was spoken is identified. The portion of the content dialogue to repeat is identified and translated from the first language to the second language. The translated portion of the content dialogue is then output. In this way, the user can simply ask in their native language for the dialogue to be repeated and the repeated portion of the dialogue is presented in the user's native language.

Abstract: The object of the present invention is to provide a voice recognition technique that can handle wording in other languages. The voice recognition dictionary data construction apparatus includes an attribute setting unit that sets attributes to first words that constitute a first character string representing a place name in the first language, a language conversion unit that creates a second character string by replacing the first words in the first character string with the second words without changing the attributes thereof, an order changing unit that creates a third character string by changing the word order of the second character string based on the attributes of the words of the second character string and the word order rule of place names of the second language, a phoneme data construction unit that constructs the phoneme data of the third character string.

Abstract: Techniques are described herein for multi-modal interaction between users, automated assistants, and other computing services. In various implementations, a user may engage with the automated assistant in order to further engage with a third party computing service. In some implementations, the user may advance through dialog state machines associated with third party computing service using both verbal input modalities and input modalities other than verbal modalities, such as visual/tactile modalities.

Abstract: Embodiments of the present disclosure disclose a terminal holder and a far-field voice interaction system. A specific implementation of the terminal holder includes: a far-field voice pickup device and a voice analysis device. The far-field voice pickup device receives voice sent by a user, and sends the voice to the voice analysis device. The voice analysis device analyzes the voice, determines whether the voice contains a preset wake-up word, and sends the voice to a terminal in communication connection with the terminal holder when the preset wake-up word is contained. This embodiment receives voice sent by a user through the terminal holder supporting a far-field voice pickup function, thereby facilitating the far-field voice control over the terminal.

Abstract: A system and method enable one to set a target duration of a desired synthesized utterance without removing or adding spoken content. Without changing the spoken text, the voice characteristics may be kept the same or substantially the same. Silence adjustment and interpolation may be used to alter the duration while preserving speech characteristics. Speech may be translated prior to a vocoder step, pursuant to which the translated speech is constrained by the original audio duration, while mimicking the speech characteristics of the original speech.

Abstract: Embodiments of the present invention relate to computer-implemented methods, systems, and computer program products for managing a conversational system. In one embodiment, a computer-implemented method comprises: obtaining, by a device operatively coupled to one or more processors, a first message sequence comprising messages involved in a conversation between a user and a conversation server; obtaining, by the device, a conversation graph indicating an association relationship between messages involved in a conversation; and in response to determining that the first message sequence is not matched in the conversation graph, updating, by the device, the conversation graph with a second message sequence, the second message sequence being generated based on a knowledge library including expert knowledge that is associated with a topic of the conversation.

Abstract: Methods and systems for generating voices based on characteristics of an avatar. One or more characteristics of an avatar are obtained and one or more parameters of a voice synthesizer for generating a voice corresponding to the one or more avatar characteristics are determined. The voice synthesizer is configured based on the one or more parameters and a voice is generated using the parameterized voice synthesizer.

Abstract: The technology disclosed herein summarizes a document using a dictionary derived from tokens within the document itself. In a particular implementation, a method provides identifying a first document for summarization and inputting the first document into a natural language model. The natural language model is configured to summarize the first document using words from a first dictionary compiled based on tokens from the first document. The method further provides receiving a first summary output by the natural language model after the natural language model summarizes the first document.

Abstract: The disclosed technology relates to a process for automatically training a machine learning algorithm to recognize a custom wake word. By using different text-to-speech services, input providing a custom wake word to a text to speech service can be used in order to generate different speech samples covering different variations in how the custom wake word can be pronounced. These samples are automatically generated and are subsequently used to train the wake word detection algorithm that will be used by the computing device to recognize and detect when the custom wake word is uttered by any user nearby a computing device for the purposes of initiating a virtual assistant. In a further embodiment, “white-listed” words (e.g different words that are pronounced similar to the custom wake word) are also identified and trained in order to minimize the occurrence of erroneously initiating the virtual assistant.

Abstract: Embodiments of a computer-implemented system for improving classification of data associated with the deep web or dark net are disclosed.