公开(公告)号：US20240022224A1

公开(公告)日：2024-01-18

申请号：US18253850

申请日：2021-11-18

Applicant: Dolby Laboratories Licensing Corporation ,  DOLBY INTERNATIONAL AB

Inventor： Giulio CENGARLE ,  Nicholas Laurence ENGEL ,  Patrick Winfrey SCANNELL ,  Davide SCAINI

IPC: H03G5/00 ,  H04R3/04 ,  G10L25/21 ,  G10L25/18 ,  G10L15/18

CPC classification number: H03G5/005 ,  H04R3/04 ,  G10L25/21 ,  G10L25/18 ,  G10L15/1815 ,  H04R2430/03

Abstract: In an embodiment, a method comprises: filtering reference audio content items to separate the reference audio content items into different frequency bands; for each frequency band, extracting a first feature vector from at least a portion of each of the reference audio content items, wherein the first feature vector includes at least one audio characteristic of the reference audio content items; obtaining at least one semantic label from at least a portion of each of the reference audio content items; obtaining a second feature vector consisting of the first feature vectors per frequency band and the at least one semantic label; generating, based on the second feature vector, cluster feature vectors representing centroids of clusters; separating the reference audio content items according to the cluster feature vectors; and computing an average target profile for each cluster based on the reference audio content items in the cluster.

公开(公告)号：US20240160849A1

公开(公告)日：2024-05-16

申请号：US18550429

申请日：2022-04-27

Applicant: Dolby Laboratories Licensing Corporation

Inventor： Andrea FANELLI ,  Mingqing YUN ,  Satej Suresh PANKEY ,  Nicholas Laurence ENGEL ,  Poppy Anne Carrie Crum

IPC: G06F40/30

CPC classification number: G06F40/30

Abstract: Embodiments are disclosed for speaker diarization supporting episodical content. In an embodiment, a method comprises: receiving media data including one or more utterances; dividing the media data into a plurality of blocks; identifying segments of each block of the plurality of blocks associated with a single speaker; extracting embeddings for the identified segments in accordance with a machine learning model, wherein extracting embeddings for identified segments further comprises statistically combining extracted embeddings for identified segments that correspond to a respective continuous utterance associated with a single speaker; clustering the embeddings for the identified segments into clusters; and assigning a speaker label to each of the embeddings for the identified segments in accordance with a result of the clustering. In some embodiments, a voiceprint is used to identify a speaker and the speaker identity for a speaker label.