专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明公开

EP4336381A1 SYSTEM AND METHOD FOR MUSIC ENTITY MATCHING 审中-公开
公开(公告)号：EP4336381A1
公开(公告)日：2024-03-13
申请号：EP22194930.8
申请日：2022-09-09
申请人： Sparwk AS
发明人： Liang, Beici , Suk Choi, Jin , Jenssen, Robin
IPC分类号： G06F16/683
摘要： A method and system for matching music related entities, and more specifically to automatically linking a sound recording with the underlying musical work for matching the related music rights holders to the corresponding real-world entities. The method is executed in a music entity matching system running on a computing device. In implementations of matching music related entities, the music entity matching system receives musical audio recordings from the first and the second audio source. Audio data are then extracted from the corresponding audio files, and creator name data are extracted from the metadata. The extracted audio data are compared and pairs of candidates from each source are linked based on similarity. Music entities from each linked pair are then compared for determining and presenting a final matching result of the rights holders of musical audio recordings.

2. 发明公开

EP4235458A3 SYSTEMS AND METHODS FOR IDENTIFYING AND PROVIDING INFORMATION ABOUT SEMANTIC ENTITIES IN AUDIO SIGNALS 审中-实审
公开(公告)号：EP4235458A3
公开(公告)日：2023-10-11
申请号：EP23171114.4
申请日：2018-07-30
申请人： Google LLC
发明人： WANTLAND, Tim , BARBELLO, Brandon
IPC分类号： G06F16/683
摘要： Systems and methods for determining identifying semantic entities in audio signals are provided. A method can include obtaining, by a computing device comprising one or more processors and one or more memory devices, an audio signal concurrently heard by a user. The method can further include analyzing, by a machine-learned model stored on the computing device, at least a portion of the audio signal in a background of the computing device to determine one or more semantic entities. The method can further include displaying the one or more semantic entities on a display screen of the computing device.

3. 发明公开

EP4033484A3 RECOGNITION OF SEMANTIC INFORMATION OF A SPEECH SIGNAL, TRAINING A RECOGNITION MODEL 无效
公开(公告)号：EP4033484A3
公开(公告)日：2023-02-01
申请号：EP22177557.0
申请日：2022-06-07
申请人： Apollo Intelligent Connectivity (Beijing) Technology Co., Ltd.
发明人： ZHOU, Yi , ZUO, Shengyong
IPC分类号： G10L15/18 , G10L15/06 , G06F16/683 , G11B27/028 , G06N3/08 , G10L15/16 , G11B27/02 , G10L15/04
摘要： A method and an apparatus for processing an audio signal, a method and an apparatus for training a voice recognition model, a method and an apparatus for training a semantic recognition model, an electronic device and a storage medium are provided, which relate to a field of artificial intelligence, and in particular to fields of voice recognition, natural language processing and deep learning. The method for processing an audio signal includes: recognizing an audio signal to be processed, so as to obtain a target voice segment in the audio signal to be processed and a first sentence associated with the target voice segment, wherein the audio signal to be processed is obtained based on a predetermined text; determining a second sentence associated with the target voice segment in the predetermined text; comparing the first sentence with the second sentence, so as to obtain a first comparison result; and labeling the target voice segment based on the second sentence and the first comparison result, so as to obtain a voice segment having a first labeling data. The first labeling data includes the second sentence and a first data indicating the first comparison result.

4. 发明公开

EP4120099A1 APPARATUS FOR PROCESSING FINGERPRINT HASHES OF AUDIO STREAM 审中-实审
公开(公告)号：EP4120099A1
公开(公告)日：2023-01-18
申请号：EP21185512.7
申请日：2021-07-14
申请人： Utopia Music AG
发明人： Wahlgren, Linus , Flach, Max
IPC分类号： G06F16/683
摘要： An apparatus (150) for processing fingerprint hashes of an audio stream. The apparatus includes: one or more hardware caches (114, 124), each hardware cache (114, 124) configured to store one or more files (116, 126), each file (116, 126) containing a part (118, 128) of a fixed size continuous data structure (122), and the fixed size continuous data structure (122) containing fixed size data items (120, 130), each fixed size data item (120, 130) representing a stored unique fingerprint hash; one or more random access memories (108); and one or more processors (102). The one or more processors (102) are configured to cause performance of at least the following: obtaining (162) generated fingerprint hashes of an audio stream (152); matching (164) recursively each generated fingerprint hash (110) of the audio stream (152) against stored unique fingerprint hashes (112) of the tracks using match time offsets between the audio stream and each track in order to identify the audio stream; wherein the matching (164) comprises retrieving (172), into the one or more random access memories (108) from one of the one or more files (116, 126), each stored unique fingerprint hash (112) addressed by each generated fingerprint hash (110) and represented by each fixed size data item (120, 130).

5. 发明授权

EP3996084B1 DETERMINING RELATIONS BETWEEN MUSIC ITEMS 有权
公开(公告)号：EP3996084B1
公开(公告)日：2023-01-18
申请号：EP20205650.3
申请日：2020-11-04
发明人： BOSCH VICENTE, Juan José
IPC分类号： G10H1/00 , G06F16/683

6. 发明公开

EP3963896A1 IMMERSIVE DISPLAY SYSTEM AND METHOD THEREOF 审中-实审
公开(公告)号：EP3963896A1
公开(公告)日：2022-03-09
申请号：EP19941165.3
申请日：2019-12-02
申请人： Samsung Electronics Co., Ltd.
发明人： PANWAR, Sumit , AGGARWAL, Mayur , KUMAR, Yogesh , SINGH, Gurminder , KIM, Hoseon , N, Niyaz
IPC分类号： H04N21/439 , H04N21/81 , G06K9/00 , G06F16/683

7. 发明公开

EP3896581A1 LEARNING TO RANK WITH CROSS-MODAL GRAPH CONVOLUTIONS 审中-公开
公开(公告)号：EP3896581A1
公开(公告)日：2021-10-20
申请号：EP20315159.2
申请日：2020-04-14
申请人： Naver Corporation
发明人： Renders, Jean-Michel , Clinchant, Stéphane , Formal, Thibault
IPC分类号： G06F16/55 , G06F16/583 , G06F16/65 , G06F16/683 , G06F16/75 , G06F16/783
摘要： A computer-implemented method (200) of performing cross-modal information retrieval is provided. A graph representing the set of media objects is generated (240). Each node of the graph corresponds to a media object and is labeled with a set of features corresponding to a text part of the respective media object. Each edge between two nodes represents a similarity between a media part of the two nodes. A first relevance score is computed (250) for each media object of the set of media objects that corresponds to a text-based score. A second relevance score is computed (260) for each media object by inputting the graph into a graph neural network. The first relevance score and the second relevance score are combined (270) to obtain a final ranking score for each media object.

8. 发明公开

EP3882788A1 METHOD FOR SEARCHING FOR CONTENTS HAVING SAME VOICE AS VOICE OF TARGET SPEAKER, AND APPARATUS FOR EXECUTING SAME 审中-实审
公开(公告)号：EP3882788A1
公开(公告)日：2021-09-22
申请号：EP19884526.5
申请日：2019-11-14
申请人： Neosapience, Inc.
发明人： SHON, Suwon , LEE, Younggun , KIM, Taesu
IPC分类号： G06F16/683 , G06F16/432 , G06F16/951 , G10L17/02
摘要： A method for searching content having same voice as a voice of a target speaker from among a plurality of contents includes extracting a feature vector corresponding to the voice of the target speaker, selecting any subset of speakers from a training dataset repeatedly by a predetermined number of times, generating linear discriminant analysis (LDA) transformation matrices using each of the selected any subsets of speakers repeatedly by a predetermined number of times, projecting the extracted speaker feature vector to the selected corresponding subsets of speakers using each of the generated LDA transformation matrices, assigning a value corresponding to nearby speaker class among corresponding subsets of speakers, to each of projection regions of the extracted speaker feature vector, generating a hash value corresponding to the extracted feature vector based on the assigned values, and searching content having a similar hash value to the generated hash value among the contents.

9. 发明公开

EP3796305A1 AUDIO STEM IDENTIFICATION SYSTEMS AND METHODS 有权
公开(公告)号：EP3796305A1
公开(公告)日：2021-03-24
申请号：EP20174092.5
申请日：2020-05-12
申请人： Spotify AB
发明人： PACHET, François , ROY, Pierre , RAMONA, Mathieu , JEHAN, Tristan , BOSCH VICENTE, Juan José
IPC分类号： G10H7/00 , G06F16/683
摘要： Methods, systems and computer program products are provided for identifying an audio stem. Audio stems (t 1 , .., t N ) are stored on a stem database and songs (S 1 , ..., S P ) made with at least a subset of the plurality of the audio stems (t 1 , .., t N ) are stored on a song database. At least partially composed song (S ∗ ) having a predetermined number of pre-selected stems (k) are received. In turn, a probability vector (or relevance value or ranking) is produced for each stem (t 1 , .., t N ) to be complementary to the at least partially composed song (S ∗ ).

10. 发明公开

EP3759612A1 SYSTEMS AND METHODS THAT LEVERAGE DEEP LEARNING TO SELECTIVELY STORE AUDIOVISUAL CONTENT 无效
公开(公告)号：EP3759612A1
公开(公告)日：2021-01-06
申请号：EP19709207.5
申请日：2019-02-18
申请人： Google LLC
发明人： NIEMASIK, James , PLAKAL, Manoj
IPC分类号： G06F16/23 , G06F16/583 , G06F16/683

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式