Abstract: A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

Abstract: Portions of text data generated from inverse text normalization may be redacted. Text data for redaction may be obtained. One or more inverse text normalization models may be applied to the text data to generate normalized text data. A machine learning model, trained to recognize text for redaction, may be applied to identify portions of the normalized text data for redaction. The identified portions may be redacted and the redacted normalized text provided to a destination.

Abstract: Techniques for at least the generation of a chatbot built from a custom vocabulary and to use runtime hints during inference are described. In some examples, the generation of the chatbot includes receiving a request to build a chatbot using a bot definition and a custom vocabulary, wherein the chatbot is to use runtime hints during usage; building the chatbot from the bot definition and custom vocabulary by at least: generating automatic speech recognition (ASR) artifacts to be used in decoding audio input into the chatbot into text for at least one other component of the chatbot to use in determining a next act to be performed, the ASR artifacts including artifacts that use the custom vocabulary and artifacts that do not use the custom vocabulary, and storing the ASR artifacts.

Abstract: Techniques for managing access to sensitive data in transcriptions are described. A method for managing access to sensitive data in transcriptions may include receiving a request to generate a redacted transcript of content, obtaining a transcript of the content, sending at least a portion of the transcript to a model endpoint to identify sensitive entities in the transcript, receiving an inference response identifying one or more sensitive entities in the transcript, and generating the redacted transcript based at least one the transcript and the inference response.

Abstract: Domain specialty instructions may be generated for performing text analysis tasks. An input text may be received for performing a text analysis task. A domain specialty may be identified for the input text. Specialty domain identifiers may be inserted as part of generating instructions to perform the text analysis task using a pre-trained large language model fine-tuned to a domain that includes multiple domain specialties. The pre-trained large language model may perform the text analysis task on the input text using the generated instructions. A result of the text analysis tsk performed on the input text may be provided.

Abstract: A set of alternative vocal input styles for specifying a parameter of a dialog-driven application is determined. During execution of the application, an audio prompt requesting input in one of the styles is presented. A value of the parameter is determined by applying a collection of analysis tools to vocal input obtained after the prompt is presented. A task of the application is initiated using the value.

Abstract: Techniques for personalized batch and streaming speech-to-text transcription of audio reduce the error rate of automatic speech recognition (ASR) systems in transcribing rare and out-of-vocabulary words. The techniques achieve personalization of connectionist temporal classification (CT) models by using adaptive boosting to perform biasing at the level of sub-words. In addition to boosting, the techniques encompass a phone alignment network to bias sub-word predictions towards rare long-tail words and out-of-vocabulary words. A technical benefit of the techniques is that the accuracy of speech-to-text transcription of rare and out-of-vocabulary words in a custom vocabulary by automatic speech recognition (ASR) system can be improved without having to train the ASR system on the custom vocabulary. Instead, the techniques allow the same ASR system trained on a base vocabulary to realize the accuracy improvements for different custom vocabularies spanning different domains.

Abstract: Pairs of text collections are obtained. An individual pair comprises (a) a source text collection which includes a first group of text sequences and (b) an annotated analysis result of the source text collection, comprising a second group of text sequences and a set of evidence mappings generated by an evidence mapping model. An evidence mapping indicates, for a particular text sequence of the second group, another text sequence of the first group which provides evidence for the particular text sequence. A quality metric of the model is obtained using an automated evaluation methodology in which a question is generated from the particular text sequence, and an analysis of a pair of answers (including 10 an answer generated using an evidence mapping) to the question is performed. The quality metric is provided via a programmatic interface.

Abstract: Domain specialty instructions may be generated for performing text analysis tasks. An input text may be received for performing a text analysis task. One or more domain entities may be extracted from the input text using a machine learning model trained to recognize entities of a domain in a given text. The one or more domain entities may be inserted as part of generating instructions to perform the text analysis task using a pre-trained machine learning model fine-tuned to the domain. The pre-trained machine learning model may be caused to perform the text analysis task using the generated instructions and a result of the text analysis task may be provided.

Abstract: Pairs of text collections are obtained. An individual pair comprises (a) a source text collection which includes a first group of text sequences and (b) an annotated analysis result of the source text collection, comprising a second group of text sequences and a set of evidence mappings generated by an evidence mapping model. An evidence mapping indicates, for a particular text sequence of the second group, another text sequence of the first group which provides evidence for the particular text sequence. A quality metric of the model is obtained using an automated evaluation methodology in which a question is generated from the particular text sequence, and an analysis of a pair of answers (including an answer generated using an evidence mapping) to the question is performed. The quality metric is provided via a programmatic interface.

Abstract: Portions of text data generated from inverse text normalization may be redacted. Text data for redaction may be obtained. One or more inverse text normalization models may be applied to the text data to generate normalized text data. A machine learning model, trained to recognize text for redaction, may be applied to identify portions of the normalized text data for redaction. The identified portions may be redacted and the redacted normalized text provided to a destination.

Abstract: A medical audio summarization service receives a medical conversation and an indication of a user preferred summarization style selected from a plurality of available summarization styles to generate a medical summary that conforms to the user preferred summarization style. A transcript is generated via a medical audio transcription service, and the transcript is used by a natural language processing engine (including a large language model) to generate the medical summary. The large language model is trained to be used to generate medical summaries that conform to respective ones of a plurality of user preferred summarization styles. The large language model is trained using training data comprising previously generated summaries and summary interaction metadata generated from user edits and/or feedback.

Abstract: Domain-specific parameters may be used for tuning speech processing. A pre-trained transformer-based language model may train domain-specific parameters using domain-specific unlabeled text data. This domain-specific parameters can then be appended to candidate texts produced by a speech model on received speech data and input to the transformer-based language model to score the candidate texts. The scores of the candidate texts determined using the pre-trained transformer-based language model can then be used to select a candidate text for further speech processing.

Abstract: Techniques for implementing a chatbot that utilizes context embeddings are described. An exemplary method includes determining a next turn by: applying a language model to the utterance to determine a probability of a sequence of words, generating a context embedding for the utterance based at least on one or more of: a dialog act as defined by a chatbot definition of the chatbot, a topic vector identifying a domain of the chatbot, a previous chatbot response, and one or more slot options; performing neural language model rescoring using the determined probability of a sequence of words as a word embedding and the generated context embedding to predict an hypothesis; determining at least a name of a slot and type to be fulfilled based at least in part on the hypothesis and the chatbot definition; and determining a next turn based at least in part on the chatbot definition, any previous state, and the name of the slot and type to be fulfilled.

Abstract: Techniques for predicting punctuation and casing using multimodal fusion are described.

Abstract: Techniques are described for a contextual natural language understanding (cNLU) framework that is able to incorporate contextual signals of variable history length to perform joint intent classification (IC) and slot labeling (SL) tasks. A user utterance provided by a user within a multi-turn chat dialog between the user and a conversational agent is received. The user utterance and contextual information associated with one or more previous turns of the multi-turn chat dialog is provided to a machine learning (ML) model. An intent classification and one or more slot labels for the user utterance are then obtained from the ML model. The cNLU framework described herein thus uses, in addition to a current utterance itself, various contextual signals as input to a model to generate IC and SL predictions for each utterance of a multi-turn chat dialog.

Abstract: A spoken language understanding (SLU) system may include an automatic speech recognizer (ASR), an audio feature extractor, an optional synchronizer and a language understanding module. The ASR may produce a first set of input data representing transcripts of utterances. The audio feature extractor may produce a second set of input data representing audio features of the utterances, in particular, non-transcript specific characteristics of the speaker in one or more portions the utterances. The two sets of input data may be provided for the language understanding module to predict intents and slot labels for the utterances. The SLU system may use the optional synchronizer to align the two sets of input data before providing them to the language understanding module.

Abstract: A transcription service may receive a request from a developer to build a custom speech-to-text model for a specific domain of speech. The custom speech-to-text model for the specific domain may replace a general speech-to-text model or add to a set of one or more speech-to-text models available for transcribing speech. The transcription service may receive a training data and instructions representing tasks. The transcription service may determine respective schedules for executing the instructions based at least in part on dependencies between the tasks. The transcription service may execute the instructions according to the respective schedules to train a speech-to-text model for a specific domain using the training data set. The transcription service may deploy the trained speech-to-text model as part of a network-accessible service for an end user to convert audio in the specific domain into texts.

Abstract: Techniques for extending sensitive data tagging without reannotating training data are described. A method for extending sensitive data tagging without reannotating training data may include hosting a plurality of models at a model endpoint in a machine learning service, each model trained to identify a different sensitive data type in a transcript of content, adding a new model to the model endpoint, the new model trained to identify a new sensitive data entity in the transcript of content, identifying sensitive entities in the transcript by each of the plurality of models and the new model, merging inference responses generated by each of the plurality of models and the new model using at least one inference policy, and returning a merged inference response identifying a plurality of sensitive entities in the transcript.