公开(公告)号：EP4362007A1

公开(公告)日：2024-05-01

申请号：EP23192655.1

申请日：2023-08-22

申请人： Spotify AB

发明人： DURAND, Simon ,  STOLLER, Daniel

IPC分类号： G10H1/36 ,  G10L25/30 ,  G10L15/16

CPC分类号： G10H2220/01120130101 ,  G10H2240/32520130101 ,  G10H2250/23520130101 ,  G10H2210/03120130101 ,  G10H2250/31120130101 ,  G10H1/361 ,  G10H1/368 ,  G10H2240/13120130101 ,  G10L25/30 ,  H04N21/4622 ,  H04N21/43074 ,  H04N21/8113 ,  H04N21/4666 ,  G06F40/30

摘要： A method includes obtaining lyrics text and audio for a media item and generating, using a first encoder, a first plurality of embeddings representing symbols that appear in the lyrics text for the media item. The method includes generating, using a second encoder, a second plurality of embeddings representing an acoustic representation of the audio for the media item. The method includes determining respective similarities between embeddings of the first plurality of embeddings and embeddings of the second plurality of embeddings and aligning the lyrics text and the audio for the media item based on the respective similarities. The method includes, while streaming the audio for the media item, providing, for display, the aligned lyrics text with the streamed audio.

公开(公告)号：EP4343761A1

公开(公告)日：2024-03-27

申请号：EP23191912.7

申请日：2023-08-17

申请人： Spotify AB

发明人： BITTNER, Rachel ,  VAN BALEN, Jan ,  STOLLER, Daniel ,  BOSCH VICENTE, Juan José

IPC分类号： G10L21/0208 ,  G10L21/003 ,  G10L25/30

摘要： This disclosure is directed to an enhanced audio file generator. One aspect is a method of enhancing input speech in an input audio file, the method comprising receiving the input audio file representing the input speech, wherein the input audio file is recorded at an audio recording device, and generating an enhanced audio file by applying an audio transformation model to the input audio file, wherein applying the audio transformation model to generate the enhanced audio file comprises extracting parameters defining audio features from the input audio file, the parameters including a noise parameter defining noise in the input audio file and one or more other preset parameters respectively defining other audio features, synthesizing clean speech based on the extracted parameters including the noise parameter, wherein synthesizing the clean speech comprises transforming the noise parameter to defined value(s); and generating the enhanced audio file with the synthesized clean speech.

公开(公告)号：EP3792915A1

公开(公告)日：2021-03-17

申请号：EP19213434.4

申请日：2019-12-04

申请人： Spotify AB

发明人： STOLLER, Daniel ,  DURAND, Simon ,  EWERT, Sebastian

IPC分类号： G10L15/26 ,  G10L15/16 ,  G10L15/183 ,  G10L15/22

摘要： An electronic device receives audio data for a media item. The electronic device generates, from the audio data, a plurality of samples, each sample having a predefined maximum length. The electronic device, using a neural network trained to predict textual unit probabilities, generates a probability matrix of textual units for a first portion of a first sample of the plurality of samples. The probability matrix includes information about textual units, timing information, and respective probabilities of respective textual units at respective times. The electronic device identifies, for the first portion of the first sample, a first sequence of textual units based on the generated probability matrix.

公开(公告)号：EP3648100A1

公开(公告)日：2020-05-06

申请号：EP19205617.4

申请日：2019-10-28

申请人： Spotify AB

发明人： STOLLER, Daniel ,  DURAND, Simon ,  EWERT, Sebastian

IPC分类号： G10L15/26 ,  G10L15/16 ,  G10L15/183 ,  G10L15/22

摘要： An electronic device receives audio data for a media item. The electronic device generates, from the audio data, a plurality of samples, each sample having a predefined maximum length. The electronic device, using a neural network trained to predict character probabilities, generates a probability matrix of characters for a first portion of a first sample of the plurality of samples. The probability matrix includes character information, timing information, and respective probabilities of respective characters at respective times. The electronic device identifies, for the first portion of the first sample, a first sequence of characters based on the generated probability matrix.