公开(公告)号：US11645460B2

公开(公告)日：2023-05-09

申请号：US17135283

申请日：2020-12-28

Applicant: GENESYS TELECOMMUNICATIONS LABORATORIES, INC.

Inventor： Avraham Faizakof ,  Arnon Mazza ,  Lev Haikin ,  Eyal Orbach

IPC: G06F40/232 ,  G06N20/00 ,  G06F40/279 ,  G06F40/169 ,  G10L15/04 ,  G10L15/06 ,  G10L15/197 ,  G10L15/22

CPC classification number: G06F40/232 ,  G06F40/169 ,  G06F40/279 ,  G06N20/00 ,  G10L15/04 ,  G10L15/063 ,  G10L15/197 ,  G10L15/22

Abstract: A first text corpus comprising punctuated and capitalized text is received. The words in the first text corpus are then annotated with a set of labels indicating a punctuation and a capitalization of each word. At an initial training stage, a machine learning model is trained on a first training set using the annotated words from the first text corpus and the labels. A second text corpus is received representing conversational speech. The words in the second text corpus are then annotated with the set of labels. In a re-training stage, the machine learning model is re-trained on a second training set comprising the annotated words from the second text corpus, and the labels. At an inference stage, the trained machine learning model is applied to a target set of words representing conversational speech to predict a punctuation and capitalization of each word in the target set.

公开(公告)号：US20210193169A1

公开(公告)日：2021-06-24

申请号：US16723154

申请日：2019-12-20

Applicant: Genesys Telecommunications Laboratories, Inc.

Inventor： Avraham Faizakof ,  Lev Haikin ,  Yochai Konig ,  Arnon Mazza

IPC: G10L25/63 ,  G10L15/02 ,  G10L15/04 ,  G10L15/06

Abstract: A method comprising: receiving a plurality of audio segments comprising a speech signal, wherein said audio segments represent a plurality of verbal interactions; receiving labels associated with an emotional state expressed in each of said audio segments; dividing each of said audio segments into a plurality of frames, based on a specified frame duration; extracting a plurality of acoustic features from each of said frames; computing statistics over said acoustic features with respect to sequences of frames representing phoneme boundaries in said audio segments; at a training stage, training a machine learning model on a training set comprising: said statistics associated with said audio segments, and said labels; and at an inference stage, applying said trained model to one or more target audio segments comprising a speech signal, to detect an emotional state expressed in said target audio segments.

公开(公告)号：US11341986B2

公开(公告)日：2022-05-24

申请号：US16723154

申请日：2019-12-20

Applicant: Genesys Telecommunications Laboratories, Inc.

Inventor： Avraham Faizakof ,  Lev Haikin ,  Yochai Konig ,  Arnon Mazza

IPC: G10L25/63 ,  G10L15/22 ,  G10L15/26 ,  G06F40/30 ,  G10L15/02 ,  G10L15/04 ,  G10L15/06

Abstract: A method comprising: receiving a plurality of audio segments comprising a speech signal, wherein said audio segments represent a plurality of verbal interactions; receiving labels associated with an emotional state expressed in each of said audio segments; dividing each of said audio segments into a plurality of frames, based on a specified frame duration; extracting a plurality of acoustic features from each of said frames; computing statistics over said acoustic features with respect to sequences of frames representing phoneme boundaries in said audio segments; at a training stage, training a machine learning model on a training set comprising: said statistics associated with said audio segments, and said labels; and at an inference stage, applying said trained model to one or more target audio segments comprising a speech signal, to detect an emotional state expressed in said target audio segments.