会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 2. 发明授权
    • EVALUATION OF DOWNBEATS FROM A MUSICAL AUDIO SIGNAL
    • AUSWERTUNG VONGRUNDSCHLÄGENAUS EINEM MUSIKALISCHEN TONSIGNAL
    • EP2845188B1
    • 2017-02-01
    • EP12875874.5
    • 2012-04-30
    • Nokia Technologies Oy
    • ERONEN, Antti Johannes
    • G10H1/40G10H1/00
    • G10H1/40G10H1/383G10H2210/051G10H2210/066G10H2210/076G10H2230/015
    • A server system 500 is provided for receiving video clips having an associated audio/musical track for processing at the server system. The system comprises a beat tracking module for identifying beat time instants (ti) in the audio signal and a chord change estimation module for determining a chord change likelihood from chroma accent information in the audio signal at the beat time instants (ti). Further, first and second accent-based estimation modules are provided for determining respective first and second accent-based downbeat likelihood values from the audio signal at the beat time instants (ti) using respective different algorithms. A final stage of processing identifies downbeats occurring at beat time instants (ti) using a predefined score-based algorithm that takes as input numerical representations of chord change likelihood and the first and second accent-based downbeat likelihood values at the beat time instants (ti).
    • 服务器系统500被提供用于接收具有相关联的音频/音轨的视频剪辑,用于在服务器系统处理。 该系统包括用于识别音频信号中的拍子时刻(ti)的拍子跟踪模块和用于在拍子时刻(ti))处从音频信号中的色度重音信息确定和弦变化似然度的和弦变化估计模块。 此外,第一和第二基于重音的估计模块被提供用于使用各自不同的算法来确定来自音频信号在节拍时刻(ti)的相应的第一和第二基于重音的失真似然值。 处理的最后阶段使用预定义的基于分数的算法来识别在节拍时刻(ti)发生的失真,该算法将作为输入的和弦变化似然率的数字表示和在拍子时刻(ti)处的第一和第二基于重音的下垂似然值 )。
    • 4. 发明公开
    • SOUND PROCESSING METHOD AND TERMINAL DEVICE
    • 声音处理方法和终端装置
    • EP3067891A1
    • 2016-09-14
    • EP14859910.3
    • 2014-11-04
    • Huawei Device Co., Ltd.
    • AN, KangQIU, CunshouCHANG, Qing
    • G10L21/00
    • G10K15/08G10H1/361G10H1/366G10H2210/281G10H2230/015G10H2250/061G10L21/02H03M1/12H03M1/66H04R3/002H04R3/005
    • Embodiments of the present invention provide a sound processing method and a terminal device, where the method includes: acquiring an analog first sound signal; performing analog-to-digital conversion on the first sound signal, so as to generate a digital second sound signal; performing reverberation processing, at a system bottom layer, on the second sound signal, so as to generate a digital third sound signal; performing digital sound mixing processing on the third sound signal and a background sound signal sent from an application layer, so as to generate a digital fourth sound signal; performing digital-to-analog conversion on the fourth sound signal, so as to generate an analog fifth sound signal; performing analog sound mixing processing on the first sound signal and the fifth sound signal, so as to generate an analog sixth sound signal; and playing the sixth sound signal. In the embodiments of the present invention, by performing reverberation beautification processing, at a system bottom layer, on a sound signal, a delay of a sound on which beautification processing is performed can be reduced, thereby implementing real-time input, real-time beautification, and real-time output of the sound and improving user experience.
    • 本发明实施例提供一种声音处理方法和终端设备,所述方法包括:获取模拟第一声音信号; 对所述第一声音信号进行模数转换,以生成数字第二声音信号; 在系统底层对所述第二声音信号进行混响处理,以生成数字第三声音信号; 对所述第三声音信号和应用层发送的背景声音信号进行数字混音处理,生成数字第四声音信号; 对所述第四声音信号进行数模转换,以生成模拟的第五声音信号; 对所述第一声音信号和所述第五声音信号进行模拟混音处理,以生成模拟的第六声音信号; 并播放第六个声音信号。 在本发明的实施例中,通过进行混响美化处理,在系统底层,对声音信号进行美化处理的声音延迟可以减少,从而实现实时输入,实时 美化和实时输出声音并改善用户体验。