A computer implemented method includes receiving a natural language utterance, generating multiple alternative N-gram contexts for a evaluating a next word in the natural language utterance, selecting N-gram context candidates from the multiple alternative N-gram contexts comprising different sets of N-1 words in the natural language utterance for selecting a next word in the natural language utterance, and providing the N-gram context candidates for creating a transcript of the natural language utterance.

An audio stream is detected during a communication session with a user. Natural language processing on the audio stream is performed to update a set of attributes by supplementing the set of attributes based on attributes derived from the audio stream. A set of filter values is updated based on the updated set of attributes. The updated set of filter values is used to query a set of databases to obtain datasets. A probabilistic program is executed during the communication session by determining a set of probability parameters characterizing a probability of an anomaly occurring based on the datasets and the set of attributes. A determination is made if whether the probability satisfies a threshold. In response to a determination that the probability satisfies the threshold, a record is updated to identify the communication session to indicate that the threshold is satisfied.

An audio stream is detected during a communication session with a user. Natural language processing on the audio stream is performed to update a set of attributes by supplementing the set of attributes based on attributes derived from the audio stream. A set of filter values is updated based on the updated set of attributes. The updated set of filter values is used to query a set of databases to obtain datasets. A probabilistic program is executed during the communication session by determining a set of probability parameters characterizing a probability of an anomaly occurring based on the datasets and the set of attributes. A determination is made if whether the probability satisfies a threshold. In response to a determination that the probability satisfies the threshold, a record is updated to identify the communication session to indicate that the threshold is satisfied.

Systems and methods are described for interpreting machine learning model predictions. An example method includes: providing a machine learning model configured to receive a plurality of features as input and provide a prediction as output, wherein the plurality of features includes an engineered feature including a combination of two or more parent features; calculating a Shapley value for each feature in the plurality of features; and allocating a respective portion of the Shapley value for the engineered feature to each of the two or more parent features.

A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

A conversation augmentation system can automatically augment a conversation with content items based on natural language from the conversation. The conversation augmentation system can select content items to add to the conversation based on determined user “intents” generated using machine learning models. The conversation augmentation system can generate intents for natural language from various sources, such as video chats, audio conversations, textual conversations, virtual reality environments, etc. The conversation augmentation system can identify constraints for mapping the intents to content items or context signals for selecting appropriate content items. In various implementations, the conversation augmentation system can add selected content items to a storyline the conversation describes or can augment a platform in which an unstructured conversation is occurring.

Systems for performing intelligent interactive voice recognition functions are provided. In some aspects, natural language data may be received from a plurality of users. The natural language data may be used to train a machine learning model. After training the machine learning model, additional or subsequent natural language input data may be received. The natural language data may include a user query, such as a request to obtain information from the system, to process a transaction, or the like. The natural language data may be processed to remove noise associated with the audio data. The data may then be further processed using the machine learning model to interpret the query of the user and generate an output. The output may be transmitted to the user and feedback data may be received from the user. The user-specific machine learning dataset may then be validated and/or updated based on the feedback data.

Systems for performing intelligent interactive voice recognition functions are provided. In some aspects, natural language data may be received from a plurality of users. The natural language data may be used to train a machine learning model. After training the machine learning model, additional or subsequent natural language input data may be received. The natural language data may include a user query, such as a request to obtain information from the system, to process a transaction, or the like. The natural language data may be processed to remove noise associated with the audio data. The data may then be further processed using the machine learning model to interpret the query of the user and generate an output. The output may be transmitted to the user and feedback data may be received from the user. The user-specific machine learning dataset may then be validated and/or updated based on the feedback data.

A speech recognition method includes adding a preset special sequence to a front end of an input sequence that corresponds to an input utterance of a speaker, recognizing the preset special sequence and the input sequence, and recognizing the input sequence based on the preset special sequence and a speech recognition result obtained by recognizing the preset special sequence and the input sequence.

A speech recognition method includes adding a preset special sequence to a front end of an input sequence that corresponds to an input utterance of a speaker, recognizing the preset special sequence and the input sequence, and recognizing the input sequence based on the preset special sequence and a speech recognition result obtained by recognizing the preset special sequence and the input sequence.