Abstract: Disclosed herein are methods and systems for implementing a multi-model computer architecture for entity identification. A method includes receiving data regarding a plurality of entities. The method includes generating a plurality of entity profiles for the plurality entities and a network graph data structure (e.g., a node graph) comprising edges between nodes for the plurality of entity profiles. The method includes executing a model using identifiers of the plurality of entity profiles, an event topic, and the edges between the nodes as input to generate one or more composite scores for the plurality of entity profiles. The method includes selecting one or more entities for the event based on the generated one or more composite scores. The method includes generating a record comprising associations between identifications of the entities and the event.

Abstract: A real-time speech-to-speech generator and sign gestures converter system is disclosed. The system is still challenging for deaf or hearing impaired people. Embodiments of the invention provide direct speech to speech translation system and further conversion to sign gestures is disclosed. Direct speech to speech translation and further sign gesture conversion uses a one-tier approach, creating a unified-model for whole application. The single-model ecosystem takes in audio (MEL spectrogram) as an input and gives out audio (MEL spectrogram) as an output to a speech-sign converter device with a display. This solves the bottleneck problem by converting the translated speech directly to sign language gesture from first language with emotion by preserving phonetic information along the way. This model needs parallel audio samples in two languages.

Abstract: Areal-time speech-to-speech generator and sign gestures converter system is disclosed. The system is still challenging for deaf or hearing impaired people. Embodiments of the invention provide direct speech to speech translation system and further conversion to sign gestures is disclosed. Direct speech to speech translation and further sign gesture conversion uses a one-tier approach, creating a unified-model for whole application. The single-model ecosystem takes in audio (MEL spectrogram) as an input and gives out audio (MEL spectrogram) as an output to a speech-sign converter device with a display. This solves the bottleneck problem by converting the translated speech directly to sign language gesture from first language with emotion by preserving phonetic information along the way. This model needs parallel audio samples in two languages.

Abstract: Information loss in speech to text conversion and Inability to preserve vocal emotion information without changing the artificial intelligence model infrastructure in a conventional speech to speech translation system are essential drawback of the conventional techniques. Embodiments of the invention provide direct speech to speech translation system is disclosed. Direct speech to speech translation system uses a one-tier approach, creating a unified-model for whole application. The single-model ecosystem takes in audio (mel spectrogram) as an input and gives out audio (mel spectrogram) as an output. This solves the bottleneck problem by not converting speech directly to text but having text as a byproduct of speech to speech translation, preserving phonetic information along the way. This model also uses pre-processing and post-processing scripts but only for the whole model. This model needs parallel audio samples in two languages.

Abstract: Information loss in speech to text conversion and Inability to preserve vocal emotion information without changing the artificial intelligence model infrastructure in a conventional speech to speech translation system are essential drawback of the conventional techniques. Embodiments of the invention provide direct speech to speech translation system is disclosed. Direct speech to speech translation system uses a one-tier approach, creating a unified-model for whole application. The single-model ecosystem takes in audio (mel spectrogram) as an input and gives out audio (mel spectrogram) as an output. This solves the bottleneck problem by not converting speech directly to text but having text as a byproduct of speech to speech translation, preserving phonetic information along the way. This model also uses pre-processing and post-processing scripts but only for the whole model. This model needs parallel audio samples in two languages.

Abstract: In one embodiment, a polymeric sheet, comprising: a foamed layer comprising a polymeric material, wherein the polymeric material has a Tg of greater than or equal to 100° C.; and wherein the sheet has a weight reduction of 10% to 60%, as compared to a solid sheet of the same geometry and size formed from the same polymeric material. The sheet, at the thickness of 1.0 mm, has a smoke density of less than or equal to 200 particles after four minutes of burning according to ASTM E662-06. The sheet is thermoformable.

Abstract: In one embodiment, a polymeric sheet, comprising: a foamed layer comprising a polymeric material, wherein the polymeric material has a Tg of greater than or equal to 100° C.; and wherein the sheet has a weight reduction of 10% to 60%, as compared to a solid sheet of the same geometry and size formed from the same polymeric material. The sheet, at the thickness of 1.0 mm, has a smoke density of less than or equal to 200 particles after four minutes of burning according to ASTM E662-06. The sheet is thermoformable.

Abstract: In one embodiment, the invention relates to a two step process in which a 1,4-butane diol component reacts with a polyethylene terephthalate component under conditions that depolymerize the polyethylene terephthalate component into a molten mixture and the molten mixture is placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers. In another embodiment, the invention relates to a three step process in which a diol component selected from the group consisting of ethylene glycol, propylene glycol, and combinations thereof reacts with a polyethylene terephthalate component under conditions sufficient to depolymerize the polyethylene terephthalate component into a first molten mixture; and where the first molten mixture is combined with 1,4-butane diol under conditions that create a second molten mixture that is subsequently placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers.

Abstract: In one embodiment, the invention relates to a two step process in which a 1,4-butane diol component reacts with a polyethylene terephthalate component under conditions that depolymerize the polyethylene terephthalate component into a molten mixture and the molten mixture is placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers. In another embodiment, the invention relates to a three step process in which a diol component selected from the group consisting of ethylene glycol, propylene glycol, and combinations thereof reacts with a polyethylene terephthalate component under conditions sufficient to depolymerize the polyethylene terephthalate component into a first molten mixture; and where the first molten mixture is combined with 1,4-butane diol under conditions that create a second molten mixture that is subsequently placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers.

Abstract: The invention relates to a process for making modified polybutylene terephthalate random copolymers from a polyethylene terephthalate component. In one embodiment, the invention relates to a two step process in which a 1,4-butane diol component reacts with a polyethylene terephthalate component under conditions that depolymerize the polyethylene terephthalate component into a molten mixture and the molten mixture is placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers.

Abstract: The invention relates to a process for making modified polybutylene terephththalate random copolymers from a polyethylene terephthalate component. The invention relates to a three step process in which a diol component selected from the group consisting of ethylene glycol, propylene glycol, and combinations thereof reacts with a polyethylene terephthalate component under conditions sufficient to depolymerize the polyethylene terephthalate component into a first molten mixture; and where the first molten mixture is combined with 1,4-butanediol under conditions that create a second molten mixture that is subsequently placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers. The invention also relates to compositions made from the process.

Abstract: The present invention relates to a multilayer article, wherein said multilayer article comprises: (i) a first layer comprising an acrylic resin; (ii) at least one translucent second layer comprising (a) an acrylic resin, optionally further comprising an impact modifier; (b) a rubber modified thermoplastic resin composition; (c) optionally a rheology modifier; and (d) a visual effects additive; (iii) a third layer comprising an acrylonitrile-butadiene-styrene (ABS) resin; and (iv) an optional backing layer comprising either a thermosetting polymer substrate, optionally fiber-reinforced, or glass filled ABS resin.

Abstract: The invention relates to a process for making modified polybutylene terephthalate random copolymers from a polyethylene terephthalate component. The invention relates to a three step process in which a diol component selected from the group consisting of ethylene glycol, propylene glycol, and combinations thereof reacts with a polyethylene terephthalate component under conditions sufficient to depolymerize the polyethylene terephthalate component into a first molten mixture; and where the first molten mixture is combined with 1,4-butanediol under conditions that create a second molten mixture that is subsequently placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers. The invention also relates to compositions made from the process.

Abstract: A method is disclosed for preparing an acrylic-styrene-acrylonitrile (ASA) resin, which comprises the steps of: (a) polymerizing a mixture comprising at least one acrylate monomer and at least one polyethylenically unsaturated monomer to form a rubber substrate, followed by (b) polymerizing a mixture of monomers in the presence of the rubber substrate, at least one of which monomers is selected from the group consisting of vinyl aromatic monomers and at least one of which monomers is selected from the group consisting of monoethylenically unsaturated nitrile monomers, and optionally followed by (c) polymerizing one or more monomers in at least one subsequent stage in the presence of the rubber substrate from (b), wherein the one or more monomers comprise at least one monomer selected from the group consisting of (C1-C12)alkyl- and aryl-(meth)acrylate monomers; wherein the amount of unreacted polyethylenically unsaturated monomer remaining in the rubber substrate before step (b) is less than 5.

Abstract: Disclosed are compositions comprising (i) a rigid thermoplastic resin comprising structural units derived from a (C1-C12)alkyl (meth)acrylate monomer, and optionally a second monomer selected from the group consisting of a vinyl aromatic monomer, a monoethylenically unsaturated nitrile monomer and mixtures thereof, and (ii) a fluoropolymer additive comprising 30 wt. % to 70 wt. % of a fluoropolymer and 70 wt. % to 30 wt. % of a carrier polymer comprising structural units derived from a vinyl aromatic monomer, or a monoethylenically unsaturated nitrile monomer, or mixtures thereof, wherein the fluoropolymer is at least partially encapsulated by the carrier polymer and wherein the amount of fluoropolymer present in the composition is in a range of 2 parts by weight (pbw) to 25 pbw based on 100 pbw of the composition, and wherein the composition is free of both rubber component and filler. Articles made from the compositions and a method to improve physical properties in the compositions are also disclosed.

Abstract: The present invention relates to a multilayer article, wherein said multilayer article comprises: (i) a first layer comprising an acrylic resin; (ii) at least one translucent second layer comprising (a) an acrylic resin, optionally further comprising an impact modifier; (b) a rubber modified thermoplastic resin composition; (c) optionally a rheology modifier; and (d) a visual effects additive; (iii) a third layer comprising an acrylonitrile-butadiene-styrene (ABS) resin; and (iv) an optional backing layer comprising either a thermosetting polymer substrate, optionally fiber-reinforced, or glass filled ABS resin.

Abstract: Disclosed is a method for reducing stringiness during hot plate welding of an article comprising a resinous composition which comprises at least one step of contacting with water a surface of the article to be welded. The method also results in improved cycle time for preparation of the final article.

Abstract: The present invention relates to a method for making a multilayer article, wherein said multilayer article comprises: (i) a first layer comprising an acrylic resin; (ii) at least one translucent second layer comprising (a) an acrylic resin, optionally further comprising an impact modifier; (b) a rubber modified thermoplastic resin composition; (c) optionally a rheology modifier; and (d) a visual effects additive; (iii) a third layer comprising an acrylonitrile-butadiene-styrene (ABS) resin; and (iv) an optional backing layer comprising either a thermosetting polymer substrate, optionally fiber-reinforced, or glass filled ABS resin; and wherein said method comprises the steps of: (I) drying the components of the second layer, either individually or in combination, to a volatiles content of less than 0.06 weight % prior to processing a mixture comprising said components to form said second layer; and (II) coextruding the second and third layers, and optionally the first layer to form the multilayer article.

Abstract: The invention relates to a process for making modified polybutylene terephththalate random copolymers from a polyethylene terephthalate component. The invention relates to a three step process in which a diol component selected from the group consisting of ethylene glycol, propylene glycol, and combinations thereof reacts with a polyethylene terephthalate component under conditions sufficient to depolymerize the polyethylene terephthalate component into a first molten mixture; and where the first molten mixture is combined with 1,4-butanediol under conditions that create a second molten mixture that is subsequently placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers. The invention also relates to compositions made from the process.

Abstract: The invention relates to a process for making modified polybutylene terephthalate random copolymers from a polyethylene terephthalate component. In one embodiment, the invention relates to a two step process in which a 1,4-butane diol component reacts with a polyethylene terephthalate component under conditions that depolymerize the polyethylene terephthalate component into a molten mixture and the molten mixture is placed under subatmospheric conditions that produce the modified polybutylene terephthalate random copolymers.