公开(公告)号：US10297241B2

公开(公告)日：2019-05-21

申请号：US16123478

申请日：2018-09-06

申请人： YAMAHA CORPORATION

发明人： Dan Sasai

IPC分类号： G10H7/00 ,  G10H1/40 ,  G10H1/00 ,  G10L25/51 ,  G10G3/04 ,  G10L25/27 ,  G10L25/54

摘要： A sound signal processing method according to an embodiment includes a step of acquiring an input sound signal, a step of acquiring a beat number per unit time period from the input sound signal, a step of normalizing the input sound signal with the beat number per unit time period, a step of calculating a beat spectrum of the normalized input sound signal, and a step of calculating a rhythm similarity between the beat spectrum of the normalized input sound signal and a normalized beat spectrum calculated from a reference sound signal.

公开(公告)号：US12105752B2

公开(公告)日：2024-10-01

申请号：US17705100

申请日：2022-03-25

申请人： Yamaha Corporation

发明人： Dan Sasai

IPC分类号： G06F16/683 ,  G06F16/65 ,  G06F16/68 ,  G10H1/00

CPC分类号： G06F16/683 ,  G06F16/65 ,  G06F16/686 ,  G10H1/0008

摘要： An audio analysis device comprises an electronic controller including at least one processor. The electronic controller is configured to execute a plurality of modules including a signal acquisition module configured to acquire an audio signal representing performance sounds of a musical piece, a signal analysis module configured to calculate, for each of a plurality of music categories, a feature value that includes a degree of certainty that the musical piece belongs to the music category, by analyzing the audio signal, and a music selection module configured to select one or more candidate musical pieces whose feature value is similar to the feature value calculated for the musical piece from among a plurality of candidate musical pieces.

公开(公告)号：US10963509B2

公开(公告)日：2021-03-30

申请号：US16086055

申请日：2017-03-10

申请人： YAMAHA CORPORATION

发明人： Dan Sasai

IPC分类号： G06F16/65 ,  G06F16/638 ,  G06F16/635

摘要： An update method includes acquiring a list of plural pieces of content selected from a library including plural pieces of content, selecting, from the list, first content to be deleted from the list, selecting, from the library, second content to be interchanged with the first content based on details of the list, and interchanging the first content with the second content in the list.

公开(公告)号：US09378719B2

公开(公告)日：2016-06-28

申请号：US13956165

申请日：2013-07-31

申请人： Yamaha Corporation

发明人： Dan Sasai ,  Takuya Fujishima

IPC分类号： G10H1/40 ,  G10H1/42 ,  G10H1/36 ,  G06F17/30

CPC分类号： G10H1/40 ,  G06F17/30 ,  G10H1/36 ,  G10H1/42 ,  G10H2210/061 ,  G10H2210/071 ,  G10H2210/341 ,  G10H2240/141

摘要： When a music audio to be analyzed is to be divided into a plurality of possible pattern segments based on estimated beat positions, it is divided in a plurality of different ways according to individual division models obtained by sequentially shifting the leading or first beat position of the possible pattern segments. Such division can provide plural sets of possible pattern segments with each of the sets corresponding to one of the division models. For each of the sets, comparison is made between individual possible pattern segments and individual reference performance patterns. For each of the possible pattern segments of the set, at least one reference performance pattern that matches the possible pattern segment is determined. Then, at least one combination of reference performance patterns is identified for each of the sets of possible pattern segments. One optimal combination is selected from among the identified combinations.

摘要翻译： 当要分析的音乐音乐将基于估计的拍子位置被划分为多个可能的图案片段时，根据通过顺序地移动第一拍摄位置的前导或第一拍摄位置而获得的各个分割模型将其分成多个不同的方式 可能的模式段。 这种分割可以提供多组可能的模式段，其中每个集合对应于一个分割模型。 对于每个集合，在各个可能的模式段和各个参考性能模式之间进行比较。 对于集合的每个可能的模式段，确定与可能的模式段匹配的至少一个参考性能模式。 然后，针对可能的图案片段组中的每一组识别参考性能图案的至少一个组合。 从所识别的组合中选择一种最佳组合。

公开(公告)号：US09275616B2

公开(公告)日：2016-03-01

申请号：US14573237

申请日：2014-12-17

申请人： YAMAHA CORPORATION

发明人： Norihiro Uemura ,  Dan Sasai ,  Motoichi Tamura

IPC分类号： A63H5/00 ,  G10H1/00 ,  G06K9/00

CPC分类号： G10H1/0008 ,  G06K9/00476

摘要： The method analyzes, on the basis of the musical score image data, an image note sequence that is a time series of a plurality of notes included in the image of a musical score of a given music piece, acquires, on the basis of a logical musical score data, a logical note sequence that is a time series of a plurality of notes included in the musical score of the given music piece, and then identifies correspondence relationship between the individual notes in the image note sequence and the individual notes in the logical note sequence by comparing the image note sequence and the logical note sequence. Further, the method displays the musical score image of the given music piece on the basis of the musical score image data, and controls a display state of the displayed image of the musical score by use of the identified correspondence relationship.

摘要翻译： 该方法基于音乐分数图像数据分析作为给定乐曲的乐谱图像中包含的多个音符的时间序列的图像音符序列，基于逻辑 乐谱数据，作为包含在给定乐曲的乐谱中的多个音符的时间序列的逻辑音符序列，然后识别图像音符序列中的各个音符与逻辑中的各个音符之间的对应关系 通过比较图像笔记序列和逻辑音符序列来记录序列。 此外，该方法基于乐谱图像数据显示给定乐曲的乐谱图像，并且通过使用所识别的对应关系来控制乐谱的显示图像的显示状态。