Abstract: An artificial intelligence system that conducts dialogs with one or more participants to achieve an educational outcome, such as teaching material with a Socratic question-and-answer method, reviewing material to reinforce ideas or to prepare a participant for future tests or events, or evaluating a participant's knowledge or communication skills. The system may use an artificial intelligence engine that can understand and generate natural language, such as a large-language model like ChatGPT. Text-to-speech and speech-to-text converters may be coupled to the AI engine to enable the system to communicate directly with participants using spoken language. The system may provide an interface for entry of contextual information for a dialog, such as background information on topics for discussion. It may provide an interface for moderation of a dialog, for example by a teacher, lawyer, thesis advisor, etc. System may evaluate the performance of the participants at the end of a dialog.

Abstract: A method performed by an encoder. The method comprises determining envelope representation residual coefficients as first compressed envelope representation coefficients subtracted from the input envelope representation coefficients. The method comprises transforming the envelope representation residual coefficients into a warped domain so as to obtain transformed envelope representation residual coefficients. The method comprises applying, at least one of a plurality of gain-shape coding schemes on the transformed envelope representation residual coefficients in order to achieve gain-shape coded envelope representation residual coefficients, where the plurality of gain-shape coding schemes have mutually different trade-offs in one or more of gain resolution and shape resolution for one or more of the transformed envelope representation residual coefficients.

Abstract: Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

Abstract: It is intended to acquire a highly accurate speech recognition result for a subject of a conversation, while inhibiting an increase in the amount of calculation. A speech recognition device (10) according to the present invention includes a first speech recognition unit (11) that performs speech recognition processing using a first method on speech data of a conversation made by a plurality of speakers and outputs a speech recognition result for each of respective uttered speech segments of the plurality of speakers, a determination unit (13) that determines a subject segment based on a result of the speech recognition processing by the first speech recognition unit 11, and a second speech recognition unit (14) that performs speech recognition processing using a second method higher in accuracy than the first method on the speech data in the segment determined to be the subject segment and outputs a speech recognition result as a subject text.

Abstract: A method and apparatus for improving the quality of an attention-based sequence-to-sequence model. The method includes determining an output sequence corresponding to an input sequence based on an attention-based sequence-to-sequence model, selecting at least one target attention head from among a plurality of attention heads, detecting at least one error output token among output tokens constituting the output sequence based on the target attention head, and correcting the output sequence based on the error output token.

Abstract: A dialogue complexity assessment method, system, and computer program product including calculating a complexity utilizing domain-dependent terms and domain-independent terms of a dialogue, where the dialogue includes dialogue data from contact centers of service providers.

Abstract: The present subject matter at least describes a method and a system (300, 1200) of performing speech-recognition in an electronic device having an embedded speech recognizer. The method comprises receiving an input-audio comprising speech at a device. In real-time, at-least one speech-recognition module is selected within at least one of the device and a server for recognition of at least a portion of the received speech based on a criteria defined in terms of a) past-performance of speech-recognition modules within the device and server; b) an orator of speech; and c) a quality of service associated with at least one of the device and a networking environment thereof. Based upon the selection of the server, output of the selected speech-recognition modules within the device are selected for processing by corresponding speech-recognition modules of the server. An uttered-speech is determined within the input-audio based on output of the selected speech-recognition modules of the device or the server.

Abstract: Systems and methods are presented for efficient cross-fading of compressed domain information streams on a user/client device. Exemplary systems may provide cross-fade between AAC/Enhanced AAC Plus information streams, between MP3 information streams, or between information streams of unmatched formats. These systems are distinguished in that cross-fade is directly applied to compressed bitstreams so a single decode operation is performed on the resulting bitstream. Thus, a set of frames from each input stream associated with the time interval in which a cross fade is decoded, and combined and recoded with a cross fade or other effect now in the compressed bitstream. Once sent through the client device's decoder, the user hears the transitional effect. The only input data that is decoded and processed is that associated with the portion of each stream used the crossfade, blend or other interstitial, and thus the vast majority of input streams are left compressed.

Abstract: The present disclosure relates to systems and methods for providing subtitle for a video. The video's audio is transcribed to obtain caption text for the video. A first machine-trained model identifies sentences in the caption text. A second model identifies intra-sentence breaks with in the sentences identified using the first machine-trained model. Based on the identified sentences and intra-sentence breaks, one or more words in the caption text are grouped into a clip caption to be displayed for a corresponding clip of the video.

Abstract: Systems, methods, devices and non-transitory, computer-readable storage mediums are disclosed for a wearable multimedia device and cloud computing platform with an application ecosystem for processing multimedia data captured by the wearable multimedia device. In an embodiment, a wearable multimedia device receives a first speech input from a user, including a first command to generate a message, and first content for inclusion in the message. The device determines second content for inclusion in the message based on the first content, and generates the message such that the messages includes the first and second content. The device receives a second speech input from the user, including a second command to modify the message. In response, the device determines third content for inclusion in the message based on the first content and/or the second content, and modifies the message using the third content. The device transmits the modified message to a recipient.

Abstract: A computer-implemented method of processing language, includes: calculating a value indicating a degree of easiness of association between words with regard to one or more combinations of words in a first word group included in first text data and a second word group included in second text data; associating a first word and a second word based on the value indicating the degree of easiness of association; calculating a value indicating a degree of easiness of association between word groups with regard to a word group in the first text data including the first word and a word group in the second text data including the second word, using a result of the associating and the value indicating the degree of easiness of association between the words; and updating the value indicating the degree of easiness of association between the words by using the value indicating the degree of easiness of association between the word groups.

Abstract: An audio decoder for providing a decoded audio information on the basis of an encoded audio information includes a linear-prediction-domain decoder configured to provide a first decoded audio information on the basis of an audio frame encoded in a linear prediction domain, a frequency domain decoder configured to provide a second decoded audio information on the basis of an audio frame encoded in a frequency domain, and a transition processor. The transition processor is configured to obtain a zero-input-response of a linear predictive filtering, wherein an initial state of the linear predictive filtering is defined depending on the first decoded audio information and the second decoded audio information, and modify the second decoded audio information depending on the zero-input-response, to obtain a smooth transition between the first and the modified second decoded audio information.

Abstract: Methods, apparatuses, systems, computing devices, computing entities, and/or the like are provided. An example method may include retrieving one or more record data elements associated with a client identifier; generating one or more encounter vectors based at least in part on the one or more record data elements; generating a client vector based at least in part on the one or more encounter vectors and a first natural language processing model; generating a prediction data element based at least in part on the client vector and a machine learning model; and perform at least one data operation based at least in part on the prediction data element.

Abstract: Described herein are systems, methods, and computer readable media for dynamically determining a language variant to use for vehicle output to a vehicle occupant based on the vehicle's location. A geographic region may include multiple sub-regions, each of which may be associated with a respective one or more language variants. As an example, a geographic region may be a state or province, and each sub-region may have one or more dialects that are spoken by individuals in that sub-region. In some cases, a particular dialect may be predominant in a given sub-region. As a vehicle traverses a travel path, it may determine its current location, which geographic sub-region includes that location, and which language variant (e.g., dialect) is predominant there. That language variant may then be selected for in-vehicle communication with a vehicle occupant. The vehicle location determination may be made at or near where the occupant entered the vehicle.

Abstract: A method includes detecting whether there is a very short pitch lag in a speech or audio signal that is shorter than a conventional minimum pitch limitation using a combination of time domain and frequency domain pitch detection techniques. The pitch detection techniques include using pitch correlations in a time domain and detecting a lack of low frequency energy in the speech or audio signal in a frequency domain. The detected very short pitch lag is coded using a pitch range from a predetermined minimum very short pitch limitation that is smaller than the conventional minimum pitch limitation.

Abstract: This disclosure describes, in part, context-driven device arbitration techniques to select a speech interface device from multiple speech interface devices to provide a response to a command included in a speech utterance of a user. In some examples, the context-driven arbitration techniques may include executing multiple pipeline instances to analyze audio signals and device metadata received from each of the multiple speech interface devices which detected the speech utterance. A remote speech processing service may execute the multiple pipeline instances and analyze the audio signals and/or metadata, at various stages of the pipeline instances, to determine which speech interface device is to respond to the speech utterance.

Abstract: Methods and systems for processing of voice input to identify intents and mapped standard terminologies are provided. Using natural language processing, an intent of a voice input is identified. The intent is utilized to identify a standard terminology that maps to the intent. The standard terminology is utilized to identify information relevant to the standard terminology in a patient's electronic health record.

Abstract: An intelligence-driven virtual assistant for automated documentation of new ideas is provided. During a brainstorming session, one or more user participants may discuss and identify one or more ideas. Such ideas may be tracked, catalogued, analyzed, developed, and further expanded upon through use of an intelligence-driven virtual assistant. Such virtual assistant may capture user input data embodying one or more new ideas and intelligently process the same in accordance with creativity tool workflows. Such workflows may further stimulate creativity for capturing ideas, while continuing to document, analyze, and identify further aspects to develop and expand.

Abstract: In some examples, a software agent executing on a server receives a communication comprising a first utterance from a customer and predicts, using an intent classifier, a first intent of the first utterance. Based on determining that the first intent is order-related, the software agent predicts, using a dish classifier, a cart delta vector based at least in part on the first utterance and modifies a cart associated with the customer based on the cart delta vector. The software agent predicts, using a dialog model, a first dialog response based at least in part on the first utterance and provides the first dialog response to the customer using a text-to-speech converter.

Abstract: As noted above, example techniques relate to toggling a cloud-based VAS between enabled and disabled modes. An example implementation involves a NMD detecting that the housing is in a first orientation and enabling a first mode. Enabling the first mode includes disabling voice input processing via a cloud-based VAS and enabling local voice input processing. In the first mode, the NMD captures sound data associated with a first voice input and detects, via a local natural language unit, that the first voice input comprises sound data matching one or more keywords. The NMD determines an intent of the first voice input and performs a first command according to the determined intent. The NMD may detect that the housing is in a second orientation and enables the second mode. Enabling the second mode includes enabling voice input processing via the cloud-based VAS.