Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology, wherein the at least a portion of the text string has been labeled as corresponding to a particular entity type. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. Based at least in part on the labeling of the at least a portion of the text string as corresponding to the particular entity type, a statistical model may be trained to associate the first concept with a first probability of corresponding to the particular entity type and the second concept with a second probability of corresponding to the particular entity type.

Abstract: Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. The first and second concepts may be included in a set of features of the token. Based at least in part on the set of features of the token, a measure related to a likelihood that the at least a portion of the text string corresponds to a particular entity type may be determined.

Abstract: Cascaded models may be applied to extract facts from a medical text. A first model may be applied to at least a portion of the medical text. The first model extracts at least one first medical fact. The at least one first medical fact is linked to at least first text in the at least a portion of the medical text. A second model may be applied to the first text. The second model extracts at least one second fact that is an attribute of the at least one first medical fact.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. The first and second concepts may be included in a set of features of the token. Based at least in part on the set of features of the token, a measure related to a likelihood that the at least a portion of the text string corresponds to a particular entity type may be determined.

Abstract: Techniques for entity detection include matching a token from at least a portion of a text string with a matching concept in an ontology, wherein the at least a portion of the text string has been labeled as corresponding to a particular entity type. A first concept may be identified as being hierarchically related to the matching concept within the ontology, and a second concept may be identified as being hierarchically related to the first concept within the ontology. Based at least in part on the labeling of the at least a portion of the text string as corresponding to the particular entity type, a statistical model may be trained to associate the first concept with a first probability of corresponding to the particular entity type and the second concept with a second probability of corresponding to the particular entity type.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: An original text that is a representation of a narration of a patient encounter provided by a clinician may be received and re-formatted to produce a formatted text. One or more clinical facts may be extracted from the formatted text. A first fact of the clinical facts may be extracted from a first portion of the formatted text, and the first portion of the formatted text may be a formatted version of a first portion of the original text. A linkage may be maintained between the first fact and the first portion of the original text.

Abstract: A method for applying a user correction to medical fact extraction may include extracting, using at least one processor, a first set of one or more medical facts from a first portion of a text documenting a patient encounter. A correction to the first set of medical facts may be received from a user documenting the patient encounter. A second set of one or more medical facts may be extracted from a second portion of the text based at least in part on the user's correction to the first set of medical facts. An apparatus for applying a user correction to medical fact extraction may include at least one processor and at least one computer-readable storage medium storing processor-executable instructions that, when executed by the at least one processor, perform the above-described method. At least one computer-readable storage medium may be encoded with computer-executable instructions that perform the above-described method.

Abstract: Techniques for applying user corrections to medical fact extraction may include extracting a first set of one or more medical facts from a first portion of text documenting a patient encounter. A correction to the first set of medical facts may be received from a user. The correction may identify a fact that should be associated with the first portion of the text. A second set of one or more medical facts may be extracted from a second portion of the text based at least in part on the user's correction to the first set of medical facts. Extracting the second set of facts may include extracting one or more facts similar to the identified fact from the second portion of the text.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system my identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.

Abstract: Techniques for applying user corrections to medical fact extraction may include extracting a first set of one or more medical facts from a first portion of text documenting a patient encounter. A correction to the first set of medical facts may be received from a user. The correction may identify a fact that should be associated with the first portion of the text. A second set of one or more medical facts may be extracted from a second portion of the text based at least in part on the user's correction to the first set of medical facts. Extracting the second set of facts may include extracting one or more facts similar to the identified fact from the second portion of the text.

Abstract: Techniques are disclosed for automatically generating structured documents based on speech, including identification of relevant concepts and their interpretation. In one embodiment, a structured document generator uses an integrated process to generate a structured textual document (such as a structured textual medical report) based on a spoken audio stream. The spoken audio stream may be recognized using a language model which includes a plurality of sub-models arranged in a hierarchical structure. Each of the sub-models may correspond to a concept that is expected to appear in the spoken audio stream. Different portions of the spoken audio stream may be recognized using different sub-models. The resulting structured textual document may have a hierarchical structure that corresponds to the hierarchical structure of the language sub-models that were used to generate the structured textual document.

Abstract: A system is provided for training an acoustic model for use in speech recognition. In particular, such a system may be used to perform training based on a spoken audio stream and a non-literal transcript of the spoken audio stream. Such a system may identify text in the non-literal transcript which represents concepts having multiple spoken forms. The system may attempt to identify the actual spoken form in the audio stream which produced the corresponding text in the non-literal transcript, and thereby produce a revised transcript which more accurately represents the spoken audio stream. The revised, and more accurate, transcript may be used to train the acoustic model using discriminative training techniques, thereby producing a better acoustic model than that which would be produced using conventional techniques, which perform training based directly on the original non-literal transcript.