Sas Institute Inc.

Xu Yang

Xiaolong Li

Xiaozhuo Cheng

Teresa S Jade

Fan Wang

Samuel Norris Henderson

Qin Yang

Wei-shan Chiang

Aaron Douglas Arthur

Seng Lee

Jared Peterson

Haipeng Liu

Biljana Belamaric Wilsey

Techniques described herein provide for generation of structured output for documents identified using automated near-duplicate detection. In one example, a system can receive a set of documents including at least one pair of similar documents determined to be similar to one another based on similarity scores generated using a predefined similarity scoring technique. The system can generate document groups by merging together pairs of documents that share at least one document. The system can, for each of the document groups, identify a representative document for the document group. The system can generate an output for display including a section for each document group, in which each section includes the representative document for the document group and, for each document in the document group, the similarity score relative to the representative document for the document group.

Structured output of duplicate or near-duplicate text documents identified using automated near-duplicate detection for text documents

Techniques described herein provide for automated near-duplicate detection for new text documents given text documents that were previously processed using automated near-duplicate detection for text documents. In one example, a system can receive new documents and documents that were previously processed using a predefined processing technique for automated near-duplicate detection. The system can process the new documents and cluster the new documents into multiple predefined clusters previously identified using the predefined processing technique. For each predefined cluster including at least one new document, the system can generate document groups by determining similarity scores using the predefined processing technique as applied to the documents in the predefined clusters. The system can identify a representative document for each document group and generate an output data structure including the document groups and the representative document for each group.

Expediting automated near-duplicate detection for new text documents

A system, method, and computer-program product includes receiving speech audio of a multi-turn conversation, generating, via a speech-to-text process, a transcript of the speech audio, wherein the transcript of the speech audio textually segments speech spoken during the multi-turn conversation into a plurality of utterances, generating a speaker diarization prompt that includes contextual information about a plurality of speakers participating in the multi-turn conversation, inputting, to a large language model, the speaker diarization prompt and the transcript of the speech audio, and obtaining, from the large language model, an output comprising an enhanced transcript of the speech audio, wherein the enhanced transcript of the speech audio textually segments the speech spoken during the multi-turn conversation into a plurality of refined utterances and associates a speaker identification value with each of the plurality of refined utterances.

Systems and methods for enhanced speaker diarization

Techniques described herein provide for automated detection of near-duplicate documents. In one example, a system can cluster documents into a set of clusters based on character frequencies associated with the documents. For a given cluster, the system can generate first similarity scores associated with every pair of documents in the cluster. The system can then select a filtered group of documents associated with first similarity scores that meet or exceed a first predefined similarity threshold. Next, the system can convert the filtered group of documents into matrix representations. The system can generate second similarity scores for every pair of matrix representations. The system can then identify documents, from among the filtered group of documents, associated with second similarity scores that meet or exceed a second predefined similarity threshold. The identified documents can be duplicate or near-duplicate text documents.

Automated near-duplicate detection for text documents

A system, method, and computer-program product includes constructing a transcript adaptation training data corpus that includes a plurality of transcript normalization training data samples, wherein each of the plurality of transcript normalization training data samples includes: a predicted audio transcript that includes at least one numerical expression, an adapted audio transcript that includes an alphabetic representation of the at least one numerical expression, and a transcript normalization identifier that, when applied to a model input comprising a target audio transcript, defines a text-to-text transformation objective causing a numeric-to-alphabetic expression machine learning model to predict an alphabetic-equivalent audio transcript that represents each numerical expression included in the target audio transcript in one or more alphabetic tokens; configuring the numeric-to-alphabetic expression machine learning model based on a training of a machine learning text-to-text transformer model using the transcript adaptation training data corpus; and executing the numeric-to-alphabetic expression machine learning model.

Method for configuring and using a numeric-to-alphabetic expression machine learning model

A system, method, and computer-program product includes constructing a transcript correction training data corpus that includes a plurality of labeled audio transcription training data samples, wherein each of the plurality of labeled audio transcription training data samples includes: an incorrect audio transcription of a target piece of audio data; a correct audio transcription of the target piece of audio data; and a transcript correction identifier that, when applied to a model input that includes a likely incorrect audio transcript, defines a text-to-text transformation objective causing an audio transcript correction machine learning model to predict a corrected audio transcript based on the likely incorrect audio transcript; configuring the audio transcript correction machine learning model based on a training of a machine learning text-to-text transformer model using the transcript correction training data corpus; and executing the audio transcript correction machine learning model within a speech-to-text post-processing sequence of a speech-to-text service.

Systems and methods for configuring and using an audio transcript correction machine learning model

An apparatus includes a processor to: receive, from a requesting device, a request to perform speech-to-text conversion of a speech data set; within a first thread of a thread pool, perform a first pause detection technique to identify a first set of likely sentence pauses; within a second thread of the thread pool, perform a second pause detection technique to identify a second set of likely sentence pauses; perform a speaker diarization technique to identify a set of likely speaker changes; divide the speech data set into data segments representing speech segments based on a combination of at least the first set of likely sentence pauses, the second set of likely sentence pauses, and the set of likely speaker changes; use at least an acoustic model with each data segment to identify likely speech sounds; and generate a transcript based, at least in part, on the identified likely speech sounds.

Multithreaded speech data preprocessing

A system, method, and computer-program product includes distributing a plurality of audio data files of a speech data corpus to a plurality of computing nodes that each implement a plurality of audio processing threads, executing the plurality of audio processing threads associated with each of the plurality of computing nodes to detect a plurality of tentative speakers participating in each of the plurality of audio data files, generating, via a clustering algorithm, a plurality of clusters of embedding signatures based on a plurality of embedding signatures associated with the plurality of tentative speakers in each of the plurality of audio data files, and detecting a plurality of global speakers associated with the speech data corpus based on the plurality of clusters of embedding signatures.

Multi-threaded speaker identification

An apparatus includes a processor to: receive a request to perform speech-to-text conversion of a speech data set; perform pause detection to identify a set of likely sentence pauses and/or speaker diarization technique to identify a set of likely speaker changes; based the set of likely sentence pauses and/or the set of likely speaker changes, divide the speech data set into data segments representing speech segments; use an acoustic model with the data segments to derive sets of probabilities of speech sounds uttered; store the sets of probabilities in temporal order within a buffer queue; distribute the sets of probabilities from the buffer queue in temporal order among threads of a thread pool; and within each thread, and based on set(s) of probabilities, derive one candidate word and select either the candidate word or an alternate candidate word derived from a language model as the next word most likely spoken.

Multithreaded speech-to-text processing

An apparatus includes at least one processor to, in response to a request to perform speech-to-text conversion: perform a pause detection technique including analyzing speech audio to identify pauses, and analyzing lengths of the pauses to identify likely sentence pauses; perform a speaker diarization technique including dividing the speech audio into fragments, analyzing vocal characteristics of speech sounds of each fragment to identify a speaker of a set of speakers, and identifying instances of a change in speakers between each temporally consecutive pair of fragments to identify likely speaker changes; and perform speech-to-text operations including dividing the speech audio into segments based on at least the likely sentence pauses and likely speaker changes, using at least an acoustic model with each segment to identify likely speech sounds in the speech audio, and generating a transcript of the speech audio based at least on the likely speech sounds.

Speech segmentation based on combination of pause detection and speaker diarization

An apparatus includes processor(s) to: generate a set of candidate n-grams based on probability distributions from an acoustic model for candidate graphemes of a next word most likely spoken following at least one preceding word spoken within speech audio; provide the set of candidate n-grams to multiple devices; provide, to each node device, an indication of which candidate n-grams are to be searched for within the n-gram corpus by each node device to enable searches for multiple candidate n-grams to be performed, independently and at least partially in parallel, across the node devices; receive, from each node device, an indication of a probability of occurrence of at least one candidate n-gram within the speech audio; based on the received probabilities of occurrence, identify the next word most likely spoken within the speech audio; and add the next word most likely spoken to a transcript of the speech audio.

Speech-to-analytics framework with support for large n-gram corpora

An apparatus includes processor(s) to: perform preprocessing operations of a segmentation technique including divide speech data set into data chunks representing chunks of speech audio, use an acoustic model with each data chunk to identify pauses in the speech audio, and analyze a length of time of each identified pause to identify a candidate set of likely sentence pauses in the speech audio; and perform speech-to-text operations including divide the speech data set into data segments that each representing segments of the speech audio based on the candidate set of likely sentence pauses, use the acoustic model with each data segment to identify likely speech sounds in the speech audio, analyze the identified likely speech sounds to identify candidate sets of words likely spoken in the speech audio, and generate a transcript of the speech data set based at least on the candidate sets of words likely spoken.

Dual use of acoustic model in speech-to-text framework

An apparatus includes processor(s) to: perform pre-processing operations including derive an audio noise level of speech audio of a speech data set, derive a first relative weighting for first and second segmentation techniques for identifying likely sentence pauses in the speech audio based on the audio noise level, and select likely sentence pauses for a converged set of likely sentence pauses from likely sentence pauses identified by the first and/or second segmentation techniques based on the first relative weighting; and perform speech-to-text processing operations including divide the speech data set into data segments representing speech segments of the speech audio based on the converged set of likely sentence pauses, and derive a second relative weighting based on the audio noise level for selecting words indicated by an acoustic model or by a language model as being most likely spoken in the speech audio for inclusion in a transcript.

Dual use of audio noise level in speech-to-text framework

An apparatus includes processor(s) to: use an acoustic model to generate a first set of probabilities of speech sounds uttered within speech audio; derive at least a first candidate word most likely spoken in the speech audio using the first set; analyze the first set to derive a degree of uncertainty therefor; compare the degree of uncertainty to a threshold; in response to at least the degree of uncertainty being less than the threshold, select the first candidate word as a next word most likely spoken in the speech audio; in response to at least the degree of uncertainty being greater than the threshold, select, as the next word most likely spoken in the speech audio, a second candidate word indicated as being most likely spoken based on a second set of probabilities generated by a language model; and add the next word most likely spoken to a transcript.

Dynamic model selection in speech-to-text processing

An apparatus includes processor(s) to: divide a speech data set into multiple data chunks that each represent a chunk of speech audio; derive a threshold amplitude based on at least one peak amplitude of the speech audio; designate each data chunk with a peak amplitude below the threshold amplitude a pause data chunk; within a set of temporally consecutive data chunks of the multiple data chunks, identify a longest subset of temporally consecutive pause data chunks; within the set of temporally consecutive data chunks, designate the longest subset of temporally consecutive pause data chunks as a likely sentence pause of a candidate set of likely sentence pauses; based on at least the candidate set, divide the speech data set into multiple data segments that each represent a speech segment of the speech audio; and perform speech-to-text conversion, to identify a sentence spoken in each speech segment.

Growing community of inventors

Cary, NC, United States of America

Xu Yang