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
    • 91. 发明授权
    • Hidden trajectory modeling with differential cepstra for speech recognition
    • 用差分cepstra进行隐藏轨迹建模,用于语音识别
    • US07805308B2
    • 2010-09-28
    • US11655704
    • 2007-01-19
    • Li DengDong Yu
    • Li DengDong Yu
    • G10L13/02
    • G10L15/02G10L25/24
    • A novel system for speech recognition uses differential cepstra over time frames as acoustic features, together with the traditional static cepstral features, for hidden trajectory modeling, and provides greater accuracy and performance in automatic speech recognition. According to one illustrative embodiment, an automatic speech recognition method includes receiving a speech input, generating an interpretation of the speech, and providing an output based at least in part on the interpretation of the speech input. The interpretation of the speech uses hidden trajectory modeling with observation vectors that are based on cepstra and on differential cepstra derived from the cepstra. A method is developed that can automatically train the hidden trajectory model's parameters that are corresponding to the components of the differential cepstra in the full acoustic feature vectors.
    • 一种用于语音识别的新型系统使用差分cepstra作为声学特征,以及传统的静态倒频谱特征,用于隐藏轨迹建模,并在自动语音识别中提供更高的精度和性能。 根据一个说明性实施例,自动语音识别方法包括接收语音输入,产生语音的解释,以及至少部分地基于语音输入的解释来提供输出。 语言的解释使用基于cepstra和来自cepstra的差异cepstra的观察向量的隐藏轨迹建模。 开发了一种能够自动训练隐藏轨迹模型参数的方法,该参数对应于全声学特征向量中差分cepstra的分量。
    • 92. 发明申请
    • Hidden trajectory modeling with differential cepstra for speech recognition
    • 用差分cepstra进行隐藏轨迹建模,用于语音识别
    • US20080177546A1
    • 2008-07-24
    • US11655704
    • 2007-01-19
    • Li DengDong Yu
    • Li DengDong Yu
    • G10L15/28
    • G10L15/02G10L25/24
    • A novel system for speech recognition uses differential cepstra over time frames as acoustic features, together with the traditional static cepstral features, for hidden trajectory modeling, and provides greater accuracy and performance in automatic speech recognition. According to one illustrative embodiment, an automatic speech recognition method includes receiving a speech input, generating an interpretation of the speech, and providing an output based at least in part on the interpretation of the speech input. The interpretation of the speech uses hidden trajectory modeling with observation vectors that are based on cepstra and on differential cepstra derived from the cepstra. A method is developed that can automatically train the hidden trajectory model's parameters that are corresponding to the components of the differential cepstra in the full acoustic feature vectors.
    • 一种用于语音识别的新型系统使用差分cepstra作为声学特征,以及传统的静态倒频谱特征,用于隐藏轨迹建模,并在自动语音识别中提供更高的精度和性能。 根据一个说明性实施例,自动语音识别方法包括接收语音输入,产生语音的解释,以及至少部分地基于语音输入的解释来提供输出。 语言的解释使用基于cepstra和来自cepstra的差异cepstra的观察向量的隐藏轨迹建模。 开发了一种能够自动训练隐藏轨迹模型参数的方法,该参数对应于全声学特征向量中差分cepstra的分量。
    • 100. 发明授权
    • Solution-based fabrication of photovoltaic cell
    • 光伏电池基于解决方案的制造
    • US08088309B2
    • 2012-01-03
    • US11933400
    • 2007-10-31
    • Dong YuJacqueline FidanzaBrian M. Sager
    • Dong YuJacqueline FidanzaBrian M. Sager
    • H01B1/22B05D5/12
    • H01L31/06B82Y5/00B82Y10/00B82Y30/00C23C18/1204C23C18/1266C23C18/1295H01L31/0322H01L31/0749H01L31/18Y02E10/541Y02P70/521
    • An ink for forming CIGS photovoltaic cell active layers is disclosed along with methods for making the ink, methods for making the active layers and a solar cell made with the active layer. The ink contains a mixture of nanoparticles of elements of groups IB, IIIA and (optionally) VIA. The particles are in a desired particle size range of between about 1 nm and about 500 nm in diameter, where a majority of the mass of the particles comprises particles ranging in size from no more than about 40% above or below an average particle size or, if the average particle size is less than about 5 nanometers, from no more than about 2 nanometers above or below the average particle size. The use of such ink avoids the need to expose the material to an H2Se gas during the construction of a photovoltaic cell and allows more uniform melting during film annealing, more uniform intermixing of nanoparticles, and allows higher quality absorber films to be formed.
    • 公开了一种用于形成CIGS光伏电池有源层的墨水以及用于制备墨水的方法,制备活性层的方法和由活性层制成的太阳能电池。 油墨含有IB,IIIA和(任选地)VIA组分的纳米颗粒的混合物。 颗粒的直径在约1nm至约500nm之间的所需粒度范围,其中大部分颗粒的质量包括尺寸不超过平均粒度的约40%或以下的颗粒,或 如果平均粒度小于约5纳米,高于或低于平均粒度的不超过约2纳米。 使用这种墨水避免了在构建光伏电池期间将材料暴露于H 2 Se气体的需要,并且允许在膜退火期间更均匀的熔融,更均匀的纳米颗粒的混合,并且允许形成更高质量的吸收膜。