公开(公告)号：US20240232594A1

公开(公告)日：2024-07-11

申请号：US18289292

申请日：2021-05-03

Applicant: Google LLC

Inventor： Yang Yang ,  Claudionor Jose Nunes Coelho, Jr. ,  Hao Zhuang ,  Aki Oskari Kuusela

IPC: G06N3/063 ,  G06N3/0464 ,  G06N3/082

CPC classification number: G06N3/063 ,  G06N3/0464 ,  G06N3/082

Abstract: Methods, systems, and apparatus, including computer-readable media, are described for globally tuning and generating ML hardware accelerators. A design system selects an architecture representing a baseline processor configuration. An ML cost model of the system generates performance data about the architecture at least by modeling how the architecture executes computations of a neural network that includes multiple layers. Based on the performance data, the architecture is dynamically tuned to satisfy a performance objective when the architecture implements the neural network and executes machine-learning computations for a target application. In response to dynamically tuning the architecture, the system generates a configuration of an ML accelerator that specifies customized hardware configurations for implementing each of the multiple layers of the neural network.

公开(公告)号：US20240249741A1

公开(公告)日：2024-07-25

申请号：US18159679

申请日：2023-01-25

Applicant: Google LLC

Inventor： George Chiachi Sung ,  Yang Yang ,  Shao-Fu Shih ,  Hakan Erdogan ,  Jamie Menjay Lin

IPC: G10L21/0232 ,  G10L15/06 ,  G10L15/16 ,  G10L15/22 ,  G10L21/0308 ,  G10L25/18

CPC classification number: G10L21/0232 ,  G10L15/063 ,  G10L15/16 ,  G10L15/22 ,  G10L21/0308 ,  G10L25/18 ,  G10L2021/02082

Abstract: A method includes receiving, as input, reference audio data representing a reference audio signal captured by an audio input device. The method also includes receiving, as input, from a beamformer, spatially-filtered audio data representing an output of the beamformer, the beamformer configured to spatially filter, based on additional audio data captured by one or more additional audio input devices, the reference audio data to attenuate one or more interfering signals in the spatially-filtered audio data. The method processes, using a trained guided speech-enhancement network, the reference audio data and the spatially-filtered audio data to generate, as output, enhanced audio data, the guided speech-enhancement network processing the reference audio data and the spatially-filtered audio data to further attenuate, in the enhanced audio data, the one or more interfering signals attenuated by the beamformer.