Rovi Guides, Inc.

Adeia Guides Inc.

Rovl Guides, Inc.

Jeffry Copps Robert Jose

Ankur Anil Aher

Ajay Kumar Mishra

Mithun Umesh

Reda Harb

Sindhuja Chonat Sri

Susanto Sen

Cato Yang

Sai Durga Venkat Reddy Pulikunta

R Balaji

Arun Kumar T V

Aashish Goyal

Sindhuja C S

Manik Malhotra

Sakura Saito

Systems and methods for processing audio streams are disclosed herein. An audio stream including speech content is received. The audio stream is compacted to generate a compacted audio stream and the compacted audio stream is transmitted to an automatic speech recognition (ASR) service for transcription of the speech content to text content. In response to transmitting the compacted audio stream for transcription, text content, a transcription of the audio stream, is received from the ASR service, and transcription charges are determined.

Methods to employ compaction in ASR service usage to reduce transcription charges

A frequency of occurrence for each term in a training data set is determined in relation to the entire training data set. A relational data structure is generated that associates each term in the training data with its respective frequency. Any term that has a frequency below a threshold frequency is then added to a list of relevant words. When a natural language search query is received, a plurality of terms in the natural language search query are identified and compared with the list of relevant words. If any term of the natural language search query is included in the relevant words list, that term is identified as a keyword. The natural language search query is then interpreted based on any identified keywords.

Systems and methods for interpreting natural language search queries using training data

Systems and methods are described for managing presentation of content. A determination may be made, based on user information related to the current media asset, whether the presentation of the current media asset is not likely to be of interest to the user. In response to determining that the presentation of the current media asset is not likely to be of interest to the user, a selectable option may be presented to skip current content (e.g., advertisement content, or another currently presented media asset) and start presentation of a next media asset (e.g., a selected media asset, or a media asset similar to the current media asset).

Systems and methods for providing improved skip and delay functionality in media assets

A plurality of video clips comprising audio of a song are identified from a pool of videos. A portion of the song corresponding to the audio in each video clip is then determined. Using the determined portion, each video clip is mapped to a timeline of the song. A subset of video clips comprising different sections of the song are then selected. Video clips comprising audio from different sections of the song are selected to be included in the personalized video, which is then generated from the selected subset of video clips. The personalized video is then generated for display to the user.

Systems and methods of generating personalized video clips for songs using a pool of short videos

Methods and systems are disclosed herein for training a network to detect mimicked voice input, so that it can be determined whether a voice input signal is a mimicked voice signal. First voice data is received. The first voice data comprises at least a voice signal of a first individual and another voice signal. The voice signal of the first individual and at least one other voice signal is combined to create a composite voice signal. Second voice data is received. The second voice data comprises at least a voice signal of the first individual. The network is trained using at least the composite voice signal and the second voice data to determine whether a voice input signal is a mimicked voice input signal.

Systems and methods for detecting a mimicked voice input signal

Systems and methods for determining to perform an action of a query using a trained natural language model of a natural language understanding (NLU) system are disclosed herein. A text string corresponding to a prescribed action includes at least a content entity is received. A determination is made as to whether the text string corresponds to an audio input of a first group. In response to determining the text string corresponds to an audio input of a first group, a determination is made as to whether the text string includes an obsequious expression. In response to determining the text string corresponds to an audio input of a first group and in response to determining the text string includes an obsequious expression, a determination is made to perform the prescribed action. In response to determining the text string corresponds to an audio input of a first group and in response to determining the text string does not include the obsequious expression, a determination is made to not perform the prescribed action.

Methods for natural language model training in natural language understanding (NLU) systems

Systems and methods are described for extended reality environment interaction. An extended reality environment including an object is generated for display, and a first sensor is used to detect that a gaze has shifted from a first portion of the extended reality environment to a second portion of the extended reality environment, where the object is excluded from the first portion of the extended reality environment and included in the second portion of the extended reality environment. An indicator of the shift in the gaze is generated for display within the extended reality environment in response to detecting the gaze shift, and a voice command is detected by a second sensor while the indicator is in a vicinity of the object. In response to detecting the voice command, an action corresponding to the voice command may be executed.

Methods and systems of extended reality environment interaction based on eye motions

Systems and methods for processing audio streams are disclosed herein. In a disclosed method, N number of audio streams is received from an independent source, each audio stream includes speech content. A set of the N audio streams is concatenated to generate a concatenated audio stream. Based on the N received audio streams or the set of audio streams, N−1 or one less that the total number of audio streams in the set of audio stream separators, respectively, are generated. An audio stream separator is inserted between every two adjacent audio streams of the concatenated audio stream to generate a single audio stream payload. The single audio stream payload is transmitted for transcription of the audio stream speech content to text content and in response to transmitting the payload, a text file is received including text content corresponding to the audio streams delineated by the audio stream separators.

Methods to employ concatenation in ASR service usage based on speech-to-text cost

The system receives a voice query at an audio interface and converts the voice query to text. The system identifies entities included in the query based on comparison to an information graph, as well as dynamic types based on the structure and format of the query. The system can determine dynamic types by analyzing parts of speech, articles, parts of speech combinations, parts of speech order, influential features, and comparisons of these aspects to references. The system combines tags associated with the identified entities and tags associated with the dynamic types to generate query interpretations. The system compares the interpretations to reference templates, and selects among the query interpretations using predetermined criteria. A search query is generated based on the selected interpretation. The system retrieves content or associated identifiers, updates metadata, updates reference information, or a combination thereof. Accordingly, the system responds to queries that include non-static types.

Systems and methods for identifying dynamic types in voice queries

Systems and methods are described for extended reality environment interaction. An extended reality environment including an object is generated for display, and a table of eyelid motion identifiers and corresponding actions performable on the object in the extended reality environment is stored in memory. An eyelid motion is detected by using a sensor, and the detected eyelid motion is matched to one of the stored eyelid motion identifiers. An updated version of the extended reality environment, based on the action that corresponds to the matched eyelid motion, is generated for display, in response to matching the detected eyelid motion to one of the stored eyelid motion identifiers.

Systems and methods for determining hint words that improve the accuracy of automated speech recognition (ASR) systems. Hint words are determined in the context of a user issuing voice commands in connection with a voice interface system. Terms are initially taken from most frequently occurring terms in operation of a voice interface system. For example, most frequently occurring terms that arise in electronic search queries or received commands are selected. Certain of these terms are selected as hint words, and the selected hint words are then transmitted to an ASR system to assist in translation of speech to text.

Method and apparatus for generating hint words for automated speech recognition

Systems and methods are provided for determining hint words that improve the accuracy of automated speech recognition (ASR) systems. Hint words are typically determined in the context of a user issuing voice commands in connection with a voice interface system, however, a voice interface system may capture terms from overheard content and/or conversations. A system may determine a sliding window of hint words using set of qualifier rules. The system may capture audio, e.g., from a conversation or played back content, as a first input and decipher a plurality of words including a qualifying first term added to the hint words. The voice interface system may capture more audio as a second input and decipher a second plurality of words including a qualifying second term. The first term may be removed from the set of hint words, e.g., when the second term is added or after an expiration time.

Systems and methods for generating a dynamic list of hint words for automated speech recognition

Systems and methods for handling multilingual queries are provided. One example method includes receiving, at a computing device, an input, wherein the input comprises a multi-lingual query comprising at least a first source language and a second source language. The multi-lingual query is translated, word for word, into a destination language to produce a monolingual query, with the word order of the multilingual query and the word order of the monolingual query being the same. The monolingual query is processed using natural language processing to map the mono-lingual query to a natural language query in the destination language.

Systems and methods for handling multilingual queries

The system provides a voice command recommendation to a user to avoid a non-voice command. The system determines a command that is expected to be received, and generates a voice command recommendation that corresponds to the predicted command. The predicted command can be based on the user's behavior, a plurality of users' behavior, environmental circumstances such as a phone call ring, or a combination thereof. The system may access one or more databases to determine the predicted command. The voice command recommendation may include a displayed notification that describes the recommended voice command, and exemplary voice inputs that are recognized. The system also activates an audio interface, such as a microphone, that is configured to receive a voice input. If the system receives a recognizable voice input at the audio interface that corresponds to the recommendation, the system performs the predicted command in response to receiving the voice input.

Systems and methods for providing voice command recommendations

Systems and methods are presented for adaptive biometric authentication. According to one example method, a failure of a first type of biometric authentication is detected. In response to detecting the failure of the first type of biometric authentication, an alternative type of authentication is completed. In response to completing the alternative type of authentication, a biometric characteristic of a biometric signature is selectively modified in a stored user profile for processing a subsequent attempt of the first type of biometric authentication.

Growing community of inventors

Tamil Nadu, India

Jeffry Copps Robert Jose