公开(公告)号：US09614962B2

公开(公告)日：2017-04-04

申请号：US14834196

申请日：2015-08-24

Applicant: Marchex, Inc.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: H04M1/64 ,  H04M3/51 ,  G10L25/51 ,  H04M3/22 ,  G10L25/93 ,  H04M3/42 ,  G10L25/78 ,  H04L12/24 ,  H04L12/26

CPC classification number: H04M3/5175 ,  G10L25/51 ,  G10L25/78 ,  G10L25/93 ,  H04L41/5067 ,  H04L43/0852 ,  H04M3/2281 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/559

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

公开(公告)号：US20170366668A1

公开(公告)日：2017-12-21

申请号：US15475456

申请日：2017-03-31

Applicant: Marchex, Inc.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: H04M3/51 ,  G10L25/93 ,  G10L25/51 ,  H04M3/42 ,  H04M3/22 ,  H04L12/26 ,  G10L25/78 ,  H04L12/24

CPC classification number: H04M3/5175 ,  G10L25/51 ,  G10L25/78 ,  G10L25/93 ,  H04L41/5067 ,  H04L43/0852 ,  H04M3/2281 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/559

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

公开(公告)号：US09118751B2

公开(公告)日：2015-08-25

申请号：US13842769

申请日：2013-03-15

Applicant: Marchex, Inc.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: H04M1/64 ,  H04M3/22 ,  G10L25/51 ,  H04M3/51 ,  G10L25/78 ,  H04L12/24 ,  H04L12/26

CPC classification number: H04M3/5175 ,  G10L25/51 ,  G10L25/78 ,  G10L25/93 ,  H04L41/5067 ,  H04L43/0852 ,  H04M3/2281 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/559

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Abstract translation: 用于分析和分类呼叫而不进行转录的设施和方法。 该设施分析音频的各个帧以识别语音并测量每个频道（例如，主叫频道，代理频道）在语音中花费的时间量。 诸如R因子或MOS分数和其他元数据的附加电话指标可以作为音频分析输入被考虑。 该设施然后将框架作为一个整体进行分析，并且制定会话的聚集框架表示，以进一步识别对话模式并表征呼叫分类。 基于集群帧表示中的数据，该设施能够对呼叫分类进行估计。 可以利用对话模式与呼叫分类的相关性来制定呼叫分类问题的有针对性的解决方案，将某些广告渠道定位到其他广告渠道，评估广告刊登位置，评分呼叫者和识别垃圾邮件发送者。

公开(公告)号：US10348896B2

公开(公告)日：2019-07-09

申请号：US15475456

申请日：2017-03-31

Applicant: Marchex, Inc.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: H04M3/51 ,  G10L25/51 ,  H04M3/22 ,  G10L25/93 ,  H04M3/42 ,  G10L25/78 ,  H04L12/24 ,  H04L12/26

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialog patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialog patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

公开(公告)号：US20150365530A1

公开(公告)日：2015-12-17

申请号：US14834196

申请日：2015-08-24

Applicant: MARCHEX, INC.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: H04M3/51 ,  H04M3/42 ,  G10L25/93 ,  H04M3/22

CPC classification number: H04M3/5175 ,  G10L25/51 ,  G10L25/78 ,  G10L25/93 ,  H04L41/5067 ,  H04L43/0852 ,  H04M3/2281 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/559

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Abstract translation: 用于分析和分类呼叫而不进行转录的设施和方法。 该设施分析音频的各个帧以识别语音并测量每个频道（例如，主叫频道，代理频道）在语音中花费的时间量。 诸如R因子或MOS分数和其他元数据的附加电话指标可以作为音频分析输入被考虑。 该设施然后将框架作为一个整体进行分析，并且制定会话的聚集框架表示，以进一步识别对话模式并表征呼叫分类。 基于集群帧表示中的数据，该设施能够对呼叫分类进行估计。 可以利用对话模式与呼叫分类的相关性来制定呼叫分类问题的有针对性的解决方案，将某些广告渠道定位到其他广告渠道，评估广告刊登位置，评分呼叫者和识别垃圾邮件发送者。

公开(公告)号：US20140270114A1

公开(公告)日：2014-09-18

申请号：US13842769

申请日：2013-03-15

Applicant: MARCHEX, INC.

Inventor： Chris Kolbegger ,  Jason Flaks ,  Tim Graber ,  Bryan Rieger ,  Ziad Ismail ,  Govindaraj Ramanathan ,  Darren Spehr ,  Matthew Berk

IPC: G10L15/04

CPC classification number: H04M3/5175 ,  G10L25/51 ,  G10L25/78 ,  G10L25/93 ,  H04L41/5067 ,  H04L43/0852 ,  H04M3/2281 ,  H04M3/42221 ,  H04M3/5166 ,  H04M2203/559

Abstract: A facility and method for analyzing and classifying calls without transcription. The facility analyzes individual frames of an audio to identify speech and measure the amount of time spent in speech for each channel (e.g., caller channel, agent channel). Additional telephony metrics such as R-factor or MOS score and other metadata may be factored in as audio analysis inputs. The facility then analyzes the frames together as a whole and formulates a clustered-frame representation of a conversation to further identify dialogue patterns and characterize call classification. Based on the data in the clustered-frame representation, the facility is able to make estimations of call classification. The correlation of dialogue patterns to call classification may be utilized to develop targeted solutions for call classification issues, target certain advertising channels over others, evaluate advertising placements at scale, score callers, and to identify spammers.

Abstract translation: 用于分析和分类呼叫而不进行转录的设施和方法。 该设施分析音频的各个帧以识别语音并测量每个频道（例如，主叫频道，代理频道）在语音中花费的时间量。 诸如R因子或MOS分数和其他元数据的附加电话指标可以作为音频分析输入被考虑。 该设施然后将框架作为一个整体进行分析，并且制定会话的聚集框架表示，以进一步识别对话模式并表征呼叫分类。 基于集群帧表示中的数据，该设施能够对呼叫分类进行估计。 可以利用对话模式与呼叫分类的相关性来制定呼叫分类问题的有针对性的解决方案，将某些广告渠道定位到其他广告渠道，评估广告刊登位置，评分呼叫者和识别垃圾邮件发送者。