Abstract: The invention relates to sets of biomarkers and methods of use thereof for diagnosing, staging, treating, and assessing the response of a treatment for neurocognitive disorders characterised by tau toxicity, such as Alzheimer’s disease.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products. A computing device stores reference song characterization data and receives digital audio data. The computing device determines whether the digital audio data represents music and then performs a different process to recognize that the digital audio data represents a particular reference song. The computing device then outputs an indication of the particular reference song.

Abstract: In general, the subject matter described in this disclosure can be embodied in methods, systems, and program products for indicating a reference song. A computing device stores reference song characterization data that identifies a plurality of audio characteristics for each reference song in a plurality of reference songs. The computing device receives digital audio data that represents audio recorded by a microphone, converts the digital audio data from time-domain format into frequency-domain format, and uses the digital audio data in the frequency-domain format in a music-characterization process. In response to determining that characterization values for the digital audio data are most relevant to characterization values for a particular reference song, the computing device outputs an indication of the particular reference song.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for speech recognition using complex linear projection are disclosed. In one aspect, a method includes the actions of receiving audio data corresponding to an utterance. The method further includes generating frequency domain data using the audio data. The method further includes processing the frequency domain data using complex linear projection. The method further includes providing the processed frequency domain data to a neural network trained as an acoustic model. The method further includes generating a transcription for the utterance that is determined based at least on output that the neural network provides in response to receiving the processed frequency domain data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network.

Abstract: Defoamer compositions effective for the suppression of oil-based and water-based foams. The defoamer compositions comprise a fumed metal oxide, such as fumed silica, or another silica-based material dispersed in an organic solvent. The fumed metal oxide of silica-based material is preferably present at a low weight percentage and may be coated with polydimethylsiloxane (“PDMS”). The defoamer composition may also include one or more traditional defoamer compositions.

Abstract: A recovery vehicle for rescuing stranded vehicles from confined or restricted areas includes a wheeled chassis (2, 6) on which is mounted a vehicle support body (40) movable by an hydraulic mechanism (44) between an inoperative position superimposed on the chassis (2, 6) and an operative position extending rearwardly of the chassis (2, 6). The vehicle support body (40) is rotatable about a vertical axis relative to the chassis (2, 6) by a primary hydraulic ram located substantially within the confines of the chassis (2, 6). The vehicle support body (40) also is pivotal on the chassis (2, 6) to engage the rear end of the vehicle support body on the ground when in its operative position. Such an arrangement enables recovery of stranded vehicles other than aligned with the recovery vehicle.

Abstract: A load transfer device for loading or unloading an entire storage compartment, such as the interior of a freight hauling trailer, in one cycle includes a long vertically flexible load support and transfer member that is as long and as wide as the storage compartment and which has a chisel-like leading edge to slip under freight articles resting on a floor, the transfer member being empowered by a motor mounted on it at the rear end to move longitudinally in and out of the storage compartment.