公开(公告)号：US20230110911A1

公开(公告)日：2023-04-13

申请号：US18064638

申请日：2022-12-12

Applicant: NICE LTD.

Inventor： Roman FRENKEL ,  Matan KERET ,  Michal Daisey LERER

IPC: G10L19/00 ,  G10L17/02 ,  G10L25/30

Abstract: A digital audio quality monitoring device uses a deep neural network (DNN) to provide accurate estimates of signal-to-noise ratio (SNR) from a limited set of features extracted from incoming audio. Some embodiments improve the SNR estimate accuracy by selecting a DNN model from a plurality of available models based on a codec used to compress/decompress the incoming audio. Each model has been trained on audio compressed/decompressed by a codec associated with the model, and the monitoring device selects the model associated with the codec used to compress/decompress the incoming audio. Other embodiments are also provided.

公开(公告)号：US20220399945A1

公开(公告)日：2022-12-15

申请号：US17344650

申请日：2021-06-10

Applicant: NICE LTD.

Inventor： Roman FRENKEL ,  Matan KERET ,  Michal Daisey LERER

IPC: H04B17/309 ,  G10L17/02 ,  G10L19/00 ,  G10L25/30 ,  G06N3/08

Abstract: A digital audio quality monitoring device uses a deep neural network (DNN) to provide accurate estimates of signal-to-noise ratio (SNR) from a limited set of features extracted from incoming audio. Some embodiments improve the SNR estimate accuracy by selecting a DNN model from a plurality of available models based on a codec used to compress/decompress the incoming audio. Each model has been trained on audio compressed/decompressed by a codec associated with the model, and the monitoring device selects the model associated with the codec used to compress/decompress the incoming audio. Other embodiments are also provided.