Abstract: A server controlling an external device is provided. The server includes a communicator; a processor; a memory which stores at least one natural language understanding (NLU) engine for generating a command corresponding to a user's utterance. The server receives, from a pairing device paired to the external device, the user's utterance controlling the external device and information about at least one external device registered with the pairing device, via the communicator, determines an NLU engine corresponding to the external device, from among the at least one NLU engine, based on the user's utterance controlling the external device and the information about the at least one external device, and generates the command controlling the external device based on the user's utterance, by using the determined NLU engine.

Abstract: A method of providing real-time translation for video chat is provided. The method includes: continuously receiving first-language voice data and at least one second-language word from a first terminal; continuously displaying the at least one second-language word at the same time as reproduction of the voice data; acquiring a second-language translation of an ended sentence included in a voice recognition result for the voice data; and substituting at least one word, which corresponds to the ended sentence in the displayed at least one second-language word, with the acquired translation. The at least one second-language word corresponds to respective words included in the voice recognition result for the voice data.

Abstract: A speaker identification system (“system”) automatically assigns a speaker to voiced segments in a conversation, without requiring any previously recorded voice sample or any other action by the speaker. The system enables unsupervised learning of speakers' fingerprints and using such fingerprints for identifying a speaker in a recording of a conversation. The system identifies one or more speakers, e.g., representatives of an organization, who are in conversation with other speakers, e.g., customers of the organization. The system processes recordings of conversations between a representative and one or more customers to generate multiple voice segments having a human voice, identifies the voice segments that have the same or a similar feature, and determines the voice in the identified voice segments as the voice of the representative.

Abstract: In some embodiments, a system may process a user interface to identify textual or graphical items in the interface, and may prepare a plurality of audio files containing spoken representations of the items. As the user navigates through the interface, different ones of the audio files may be selected and played, to announce text associated with items selected by the user. A computing device may periodically determine whether a cache offering the interface to users stores audio files for all of the interface's textual items, and if the cache is missing any audio files for any of the textual items, the computing device may take steps to have a corresponding audio file created.

Abstract: A system for improved natural language understanding (NLU) provides pre-feature input to a named entity recognition (NER) component. Pre-features may include no-textually derived information associated with the circumstances describing a user command (such as time, location, etc.). A domain and/or intent may also be determined prior to NER processing and may be passed to the NER component as an input. The pre-features and/or domain or intent information may assist the NER processing by providing context to a textual input, thereby improving NER processing such as semantic tagging, which in turn may improve overall NLU processing quality.

Abstract: A translation apparatus that can perform translation based on a correct syntax, a syntax evaluation apparatus employed in the translation apparatus, a syntax evaluation method, and a syntax evaluation program are provided. A syntax evaluation unit 13 includes a grammatical element guessing part 131 that guesses a grammatical element that should be connected before and after or after a word string indicated by first fragment data, and a grammatical element complementing part 132 that complements, based on the guessing result of the grammatical element guessing part 131, the first fragment data as necessary to generate second fragment data. When the grammatical element guessing part 131 guesses a grammatical element, the grammatical element complementing part 132 complements, at a location to which the grammatical element of the word string indicated by the first fragment data should be connected, a tag indicating the grammatical element in order to generate the second fragment data.

Abstract: There is provided a storage control device including: a filter detecting unit configured to detect a voice signal estimation filter for estimating a first voice signal heard by a specific user himself/herself; an estimation unit configured to estimate the first voice signal heard by the specific user himself/herself, on the basis of a voice signal including a second voice signal of the specific user collected by an air conduction sound collecting unit in accordance with the voice signal estimation filter detected by the filter detecting unit; and a storage control unit configured to cause a storage unit to store the first voice signal estimated by the estimation unit.

Abstract: Disclosed are apparatuses and methods for processing a control command for an electronic device based on a voice agent. The apparatus includes a command tagger configured to receive at least one control command for the electronic device from at least one voice agent and to tag additional information to the at least one control command, and a command executor configured to, in response to the command tagger receiving a plurality of control commands, integrate the plurality of control commands based on additional information tagged to each of the plurality of control commands and to control the electronic device based on a result of the integration.

Abstract: An apparatus and method for evaluating quality of an automatic translation is disclosed. An apparatus for evaluating quality of automatic translation includes a converter which converts an automatic translation and a reference translation of an original text to a first distributed representation and a second distributed representation, respectively, using a distributed representation model and a quality evaluator which evaluates quality of automatic translation data based on similarity between the first distributed representation and the second distributed representation.

Abstract: A generation device includes a receiving unit and a generating unit. The receiving unit receives a model representing correspondence between one or more phonetic symbols and one or more words. The generating unit generates a first finite state transducer based on the model, the first finite state transducer at least including, as outgoing transitions from a first state representing transition destination of a first transition which has a first phonetic symbol of a predetermined type as input symbol, a second transition that has a second phonetic symbol, which is different than a particular symbol representing part or whole of input symbol of the first transition, as input symbol, and a third transition that has a third phonetic symbol, which represents the particular symbol or silence, as input symbol.

Abstract: A speech signal processing method is performed at a terminal device, including: obtaining a recorded signal and a to-be-output speech signal, the recorded signal including a noise signal and an echo signal; calculating a loop transfer function according to the recorded signal and the speech signal; calculating a power spectrum of the echo signal and a power spectrum of the noise signal according to the recorded signal, the speech signal, and the loop transfer function; calculating a frequency weighted coefficient according to the two power spectra of the echo signal and the noise signal; adjusting a frequency amplitude of the speech signal based on the frequency weighted coefficient; and outputting the adjusted speech signal to a speaker electrically coupled to the terminal device. As such, the frequency amplitude of the speech signal is automatically adjusted according to the relative frequency distribution of a noise signal and the speech signal.

Abstract: Systems, methods, and devices for outputting indications regarding voice-based interactions are described. A first speech-controlled device detects spoken audio corresponding to recipient information. The first device captures the audio and sends audio data corresponding to the captured audio to a server. The server determines a second speech-controlled device of the recipient and sends a signal to the recipient's second speech-controlled device representing a message is forthcoming. The recipient's second speech-controlled device outputs and indication representing a message is forthcoming.

Abstract: Methods and systems for a transportation vehicle are provided. One method includes receiving a user input for a valid communication session by a processor executable, digital assistant at a device on a transportation vehicle; tagging by the digital assistant, the user input words with a grammatical connotation; generating an action context, a filter context and a response context by a neural network, based on the tagged user input; storing by the digital assistant, a key-value pair for a parameter of the filter context at a short term memory, based on an output from the neural network; updating by the digital assistant, the key-value pair at the short term memory after receiving a reply to a follow-up request and another output from the trained neural network; and providing a response to the reply by the digital assistant.

Abstract: A method of forming parallel corpora comprises receiving sets of items in first language and second languages, each of the sets having one or more associated descriptions and metadata. The metadata is collected from the two sets of items and are aligned using the metadata. The aligned metadata are mapped from the first language to the second language for each of the sets. The descriptions of two items are fetched and the structural similarity of the descriptions is measured to assess whether two items are likely to be translations of each other. For mapped items with structurally similar descriptions, the mapped item descriptions are formed into respective sentences in first language and in the second language. The sentences are parallel corpora which may be used to translate an item from the first language to the second language, and also to train a machine translation system.

Abstract: An audio signal, having first and second regions of frequency spectrum, is coded. Spectral peaks in the first region are encoded by a first coding method. For a segment of the audio signal, a relation between energy of bands in the first and second regions is determined. A relation between the energy of the band in the second region and energy of neighboring bands in the second region is determined. A determination is made whether available bits are sufficient for encoding at least one non-peak segment of the first region and the band in the second region. Responsive to first and second relations fulfilling a respective predetermined criterion and a sufficient number of bits, encoding the band in the second region using a second coding method different from the first coding method, and otherwise, subjecting the band in the second region to BandWidth Extension (BWE) or noise fill.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech endpointing based on word comparisons are described. In one aspect, a method includes the actions of obtaining a transcription of an utterance. The actions further include determining, as a first value, a quantity of text samples in a collection of text samples that (i) include terms that match the transcription, and (ii) do not include any additional terms. The actions further include determining, as a second value, a quantity of text samples in the collection of text samples that (i) include terms that match the transcription, and (ii) include one or more additional terms. The actions further include classifying the utterance as a likely incomplete utterance or not a likely incomplete utterance based at least on comparing the first value and the second value.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for tagging during speech recognition. A word lattice that indicates probabilities for sequences of words in an utterance is obtained. A conditional probability transducer that indicates a frequency that sequences of both the words and semantic tags for the words appear is obtained. The word lattice and the conditional probability transducer are composed to construct a word lattice that indicates probabilities for sequences of both the words in the utterance and the semantic tags for the words. The word lattice that indicates probabilities for sequences of both the words in the utterance and the semantic tags for the words is used to generate a transcription that includes the words in the utterance and the semantic tags for the words.

Abstract: An encoding for data in an audio data stream may be indicated in the data stream using a footer stored in low-order bits of data frames in the audio data stream. When the audio data stream may include either Pulse Code Modulation (PCM) or Direct Stream Digital (DSD) data, PCM data may be marked with a footer to indicate the encoding as PCM. The footer may be a fixed value, an alternating fixed value, a predetermined sequence of values, or a value computed based on the PCM data. Examples of computed values for the footer marker may include an error code, an error correction code (ECC), and a scrambled code.

Abstract: An authentication application receives an audio input, detects whether the audio input matches a known passphrase, and processes the audio input to determine whether the audio input is consistent with a known voice signature. Upon determining that the audio input is consistent with the known voice signature, the application will identify a user who is associated with the voice signature. The device will output an audio prompt, receive a spoken answer, and analyze the spoken answer to determine whether it corresponds to an expected response. Outputting the prompt may responsive to determining that the user was not authenticated to the device or the application within a threshold time period, or if a security threat was posted to the user's profile, When the system determines that the spoken answer corresponds to the expected response, it will authenticate the user and provide the user with access to the device or application.

Abstract: An apparatus comprising at least one processor and at least one memory including computer program code. The at least one memory and the computer program code is configured to, with the at least one processor, cause the apparatus at least to determine a loudness estimate of a first audio signal, generate a parameter dependent on the loudness estimate; and control the first audio signal dependent on the parameter.