Abstract: A medical scan report labeling system is operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data is received from the first client device in response. An alias mapping pair in a medical label alias database is identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report are transmitted to a second client device of an expert user for display, and accuracy data is received from the second client device in response. The medical code is mapped to the first medical scan in the medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan.

Abstract: A medical scan report labeling system is operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data is received from the first client device in response. An alias mapping pair in a medical label alias database is identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report are transmitted to a second client device of an expert user for display, and accuracy data is received from the second client device in response. The medical code is mapped to the first medical scan in the medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan.

Abstract: A medical scan report labeling system is operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data is received from the first client device in response. An alias mapping pair in a medical label alias database is identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report are transmitted to a second client device of an expert user for display, and accuracy data is received from the second client device in response. The medical code is mapped to the first medical scan in the medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan.

Abstract: Described herein are systems and methods to identify and address sources of bias in an end-to-end speech model. In one or more embodiments, the end-to-end model may be a recurrent neural network with two 2D-convolutional input layers, followed by multiple bidirectional recurrent layers and one fully connected layer before a softmax layer. In one or more embodiments, the network is trained end-to-end using the CTC loss function to directly predict sequences of characters from log spectrograms of audio. With optimized recurrent layers and training together with alignment information, some unwanted bias induced by using purely forward only recurrences may be removed in a deployed model.

Abstract: Described herein are systems and methods for creating and using Convolutional Recurrent Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by the large-scale state-of-the-art speech recognition systems, in embodiments, the strengths of convolutional layers to utilize the structure in the data in time and frequency domains are combined with recurrent layers to utilize context for the entire processed frame. The effect of architecture parameters were examined to determine preferred model embodiments given the performance versus model size tradeoff. Various training strategies are provided to improve performance. In embodiments, using only ˜230 k parameters and yielding acceptably low latency, a CRNN model embodiment demonstrated high accuracy and robust performance in a wide range of environments.

Abstract: A medical scan report labeling system is operable to transmit a medical report that includes natural language text to a first client device for display. Identified medical condition term data is received from the first client device in response. An alias mapping pair in a medical label alias database is identified by determining that a medical condition term of the alias mapping pair compares favorably to the identified medical condition term data. A medical code that corresponds to the alias mapping pair and a medical scan that corresponds to the medical report are transmitted to a second client device of an expert user for display, and accuracy data is received from the second client device in response. The medical code is mapped to the first medical scan in the medical scan database when the accuracy data indicates that the medical code compares favorably to the medical scan.

Abstract: Described herein are systems and methods for creating and using Convolutional Recurrent Neural Networks (CRNNs) for small-footprint keyword spotting (KWS) systems. Inspired by the large-scale state-of-the-art speech recognition systems, in embodiments, the strengths of convolutional layers to utilize the structure in the data in time and frequency domains are combined with recurrent layers to utilize context for the entire processed frame. The effect of architecture parameters were examined to determine preferred model embodiments given the performance versus model size tradeoff. Various training strategies are provided to improve performance. In embodiments, using only ˜230 k parameters and yielding acceptably low latency, a CRNN model embodiment demonstrated high accuracy and robust performance in a wide range of environments.

Abstract: Described herein are systems and methods to identify and address sources of bias in an end-to-end speech model. In one or more embodiments, the end-to-end model may be a recurrent neural network with two 2D-convolutional input layers, followed by multiple bidirectional recurrent layers and one fully connected layer before a softmax layer. In one or more embodiments, the network is trained end-to-end using the CTC loss function to directly predict sequences of characters from log spectrograms of audio. With optimized recurrent layers and training together with alignment information, some unwanted bias induced by using purely forward only recurrences may be removed in a deployed model.