Abstract: This application relates to a speech recognition method and apparatus, and a computer-readable storage medium, and the method includes: obtaining a first loss function of a speech separation and enhancement model and a second loss function of a speech recognition model; performing back propagation based on the second loss function to train an intermediate model bridged between the speech separation and enhancement model and the speech recognition model, to obtain a representation model; fusing the first loss function and the second loss function, to obtain a target loss function; and jointly training the speech separation and enhancement model, the representation model, and the speech recognition model based on the target loss function, and ending the training when a preset convergence condition is met.

Abstract: This application relates to a speech recognition method and apparatus, and a computer-readable storage medium, and the method includes: obtaining a first loss function of a speech separation and enhancement model and a second loss function of a speech recognition model; performing back propagation based on the second loss function to train an intermediate model bridged between the speech separation and enhancement model and the speech recognition model, to obtain a representation model; fusing the first loss function and the second loss function, to obtain a target loss function; and jointly training the speech separation and enhancement model, the representation model, and the speech recognition model based on the target loss function, and ending the training when a preset convergence condition is met.

Abstract: Aggregation-induced emission luminogens useful for imaging ?-amyloid peptide and aggregates thereof, pharmaceutical compositions comprising the same, and methods of use and preparation thereof.

Abstract: A speech recognition method includes: obtaining first sample speech data corresponding to a target user and a first reference speech recognition result corresponding to the first sample speech data; obtaining a pre-update target model; inputting the first sample speech data into the pre-update target model, and performing speech recognition by using a target speech extraction model, a target feature extraction model, and a target speech recognition model, to obtain a first model output result; obtaining a target model loss value corresponding to the target feature extraction model according to the first model output result and the first reference speech recognition result; and updating a model parameter of the target feature extraction model in the pre-update target model according to the target model loss value, to obtain a post-update target model.

Abstract: A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

Abstract: Aggregation-induced emission luminogens useful for imaging ?-amyloid peptide and aggregates thereof, pharmaceutical compositions comprising the same, and methods of use and preparation thereof.

Abstract: Methods for screening, diagnosing, or predicting presence, progression, or treatment effects of a cognitive dysfunction such as dementia based on an analysis of drawing behavior changes by a pre-trained Naïve Bayes method are provided. The methods include steps of obtaining drawing data of at least one image created by a test subject on a digital device and obtaining personal data of the test subject; reconstructing the at least one image based on the drawing data obtained; converting the drawing data to drawing features comprising a plurality of motion features and a plurality of geometric features; and determining probability that the test subject has a cognitive dysfunction based on the drawing features and the personal data by a pre-trained Naïve Bayes method with a greedy variable selection.

Abstract: A method of training an audio separation network is provided. The method includes obtaining a first separation sample set, the first separation sample set including at least two types of audio with dummy labels, obtaining a first sample set by performing interpolation on the first separation sample set based on perturbation data, obtaining a second separation sample set by separating the first sample set using an unsupervised network, determining losses of second separation samples in the second separation sample set, and adjusting network parameters of the unsupervised network based on the losses of the second separation samples, such that a first loss of a first separation result outputted by an adjusted unsupervised network meets a convergence condition.

Abstract: A speech recognition method includes: obtaining first sample speech data corresponding to a target user and a first reference speech recognition result corresponding to the first sample speech data; obtaining a pre-update target model; inputting the first sample speech data into the pre-update target model, and performing speech recognition by using a target speech extraction model, a target feature extraction model, and a target speech recognition model, to obtain a first model output result; obtaining a target model loss value corresponding to the target feature extraction model according to the first model output result and the first reference speech recognition result; and updating a model parameter of the target feature extraction model in the pre-update target model according to the target model loss value, to obtain a post-update target model.

Abstract: This application relates to a speech recognition method and apparatus, and a computer-readable storage medium, and the method includes: obtaining a first loss function of a speech separation and enhancement model and a second loss function of a speech recognition model; performing back propagation based on the second loss function to train an intermediate model bridged between the speech separation and enhancement model and the speech recognition model, to obtain a representation model; fusing the first loss function and the second loss function, to obtain a target loss function; and jointly training the speech separation and enhancement model, the representation model, and the speech recognition model based on the target loss function, and ending the training when a preset convergence condition is met.

Abstract: This application provides a speech recognition and apparatus and a neural network training method and apparatus, and relates to the field of Artificial Intelligence (AI) technologies. The neural network training method is performed by an electronic device and includes: obtaining sample data, the sample data including a mixed speech spectrum and a labeled phoneme thereof; extracting a target speech spectrum from the mixed speech spectrum by using a first subnetwork; adaptively transforming the target speech spectrum by using a second subnetwork, to obtain an intermediate transition representation; performing phoneme recognition based on the intermediate transition representation by using a third subnetwork; and updating parameters of the first subnetwork, the second subnetwork, and the third subnetwork according to a result of the phoneme recognition and the labeled phoneme.

Abstract: The present subject matter relates to a fluorescent compound having aggregation-induced emission (AIE) characteristics. The compound can be a rod-like chiral luminogen bearing a chiral moiety at one end and long aliphatic chains at an opposing end. The compound emits circularly polarized light or luminescence (CPL) in the aggregate state. For example, the compound does not exhibit a chiroptical signal when dispersed in solution, but demonstrates tunable CPL signals in the aggregate state.

Abstract: Methods for screening, diagnosing, or predicting presence, progression, or treatment effects of a cognitive dysfunction such as dementia based on an analysis of drawing behavior changes by a pre-trained Naïve Bayes method are provided. The methods include steps of obtaining drawing data of at least one image created by a test subject on a digital device and obtaining personal data of the test subject; reconstructing the at least one image based on the drawing data obtained; converting the drawing data to drawing features comprising a plurality of motion features and a plurality of geometric features; and determining probability that the test subject has a cognitive dysfunction based on the drawing features and the personal data by a pre-trained Naïve Bayes method with a greedy variable selection.

Abstract: The present subject matter relates to a fluorescent compound having aggregation-induced emission (AIE) characteristics. The compound can be a rod-like chiral luminogen bearing a chiral moiety at one end and long aliphatic chains at an opposing end. The compound emits circularly polarized light or luminescence (CPL) in the aggregate state. For example, the compound does not exhibit a chiroptical signal when dispersed in solution, but demonstrates tunable CPL signals in the aggregate state.

Abstract: The present subject matter relates to compositions containing and synthesis of fluorescent materials e made from tetraphenylethylene (TPE) derivative compounds exhibiting aggregation induced emission (AIE) properties. Further contemplated herein are applications for TPE derivative compounds such as electroluminescent devices since they have a high efficiency, low turn on voltage, and excellent brightness. Additionally, application of TPE derivatives exhibiting AIE properties in various fields such as OLEDs, fingerprinting and forensic technology, and various other biological and industrial sectors are discussed.

Abstract: Provided herein are fluorescent bioprobes comprising fluorogens that exhibit aggregation-induced emission (AIE) labeled on biomolecules. The present subject matter relates to a fluorescent bioprobe comprising one or more fluorogen labeled on chitosan. The present subject matter is also directed to methods of preparing the fluorescent bioprobes, methods of labeling and detecting DNA and/or proteins with the fluorescent bioprobe, and methods of cell imaging including live cell tracking.

Abstract: Provided herein are magnetic silica fluorescent nanoparticles and fluorescent silica nanoparticles comprising an aggregation induced emission luminogen and magnetite nanoparticles and use of the same as a fluorescent bioprobe for intracellular imaging and a protein carrier. Also provided are processes for preparing and fabricating the same.

Abstract: Provided herein are a luminogen compound of formula (I) including a AIE luminophore moiety conjugated with a maleimide moiety and a use of the same for detecting thiol groups in biomolecules. Also provided is a dye molecule, a biosensor or a bioprobe comprising the luminogen compound of formula (I) in use for detecting thiol groups in biomolecules. The detection method of the present subject matter not only has high thio-selectivity and sensitivity, but also is rapid, convenient and handy.

Abstract: Fluorescent bioprobes comprising luminogen formed nanoparticles comprising luminogens with aggregation-induced emission (AIE) properties, which can be used for long-term cell tracking. The luminogens are nonemissive in organic solution but become highly emissive when aggregated in aqueous solution. The fluorescent molecules can readily pass through cell membranes, stain only the cell cytoplasm, and form highly emissive nanoaggregates in aqueous media without any obvious cytoxicity in the living cells. Furthermore, the molecules can be retained inside the cells without noticeable leakage to the outside. Therefore, these AIE-based compounds can be used as selective and cell-compatible fluroescent bioprobes for long-term live cell tracking and imaging.

Abstract: The present subject matter relates to compositions containing and synthesis of fluorescent materials e made from tetraphenylethylene (TPE) derivative compounds exhibiting aggregation induced emission (AIE) properties. Further contemplated herein are applications for TPE derivative compounds such as electroluminescent devices since they have a high efficiency, low turn on voltage, and excellent brightness. Additionally, application of TPE derivatives exhibiting AIE properties in various fields such as OLEDs, fingerprinting and forensic technology, and various other biological and industrial sectors are discussed.