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
    • 3. 发明申请
    • DATA SUBSTITUTION SCHEME FOR OVERSAMPLED DATA
    • 数据替代数据替代数据
    • WO2009128852A1
    • 2009-10-22
    • PCT/US2008/069061
    • 2008-07-02
    • QUALCOMM IncorporatedGARUDADRI, HarinathMAJUMDAR, SomdebJULIAN, David, JonathanGANAPATHY, Chinnappa, K.
    • GARUDADRI, HarinathMAJUMDAR, SomdebJULIAN, David, JonathanGANAPATHY, Chinnappa, K.
    • H04L1/00G10L19/00
    • H04L1/0045G10L19/005H04L1/0057
    • Low latency and computationally efficient techniques may be employed to account for errors in data such as low bit-width, oversampled data. In some aspects these techniques may be employed to mitigate audio artifacts associated with sigma-delta modulated audio data. In some aspects an error may be detected in a set of encoded data based on an outcome of a channel decoding process. Upon determining that a set of data may contain at least one error, the set of data may be replaced with another set of data that is based on one or more neighboring data sets. For example, in some aspects a set of data including at least one bit in error may be replaced with data that is generated by applying a cross-fading operation to neighboring data sets. In some aspects a given data bit may be flipped as a result of a linear prediction operation that is applied to PCM equivalent data that is associated with the given data bit and its neighboring data bits. In some aspects a set of data including at least one bit in error may be replaced with data that is generated by performing linear interpolation operations on PCM equivalent data that is associated with neighboring data sets.
    • 可以采用低延迟和计算有效的技术来解决数据中的错误,例如低位宽度,过采样数据。 在一些方面,可以采用这些技术来减轻与Σ-Δ调制音频数据相关联的音频伪影。 在一些方面,可以基于信道解码过程的结果在一组编码数据中检测到错误。 在确定一组数据可能包含至少一个错误时,可以用基于一个或多个相邻数据集的另一组数据替换该数据集。 例如,在一些方面,包括至少一个错误位的一组数据可以被通过对相邻数据集应用交叉衰落操作而产生的数据代替。 在一些方面,作为施加到与给定数据位及其相邻数据位相关联的PCM等效数据的线性预测操作的结果,可以翻转给定数据位。 在一些方面,包括至少一个错误位的一组数据可以由通过对与相邻数据集相关联的PCM等效数据执行线性内插操作而产生的数据代替。
    • 6. 发明申请
    • SYSTEM AND METHOD FOR EFFICIENT STORAGE OF VOICE RECOGNITION MODELS
    • 有效存储语音识别模型的系统和方法
    • WO2002059871A2
    • 2002-08-01
    • PCT/US2002/000890
    • 2002-01-10
    • QUALCOMM INCORPORATED
    • GARUDADRI, Harinath
    • G10L15/00
    • G10L15/06
    • A method and system that improves voice recognition by improving storage of voice recognition (VR) templates. The improved storage means that more VR models can be stored in memory. The more VR models that are stored in memory, the more robust the VR system and therefore the more accurate the VR system. Lossy compression techniques are used to compress VR models. In one embodiment, A-law compression and A-law expansion are used to compress and expand VR models. In another embodiment, Mu-law compression and Mu-law expansion are used to compress and expand VR models. VR models are compressed during a training process and they are expanded during voice recognition.
    • 通过改进语音识别(VR)模板的存储来改善语音识别的方法和系统。 改进的存储意味着更多的VR型号可以存储在存储器中。 存储在存储器中的VR模型越多,VR系统越强大,因此VR系统越准确。 有损压缩技术用于压缩VR模型。 在一个实施例中,使用A律压缩和A律扩展来压缩和扩展VR模型。 在另一个实施例中,Mu法压缩和Mu法扩展用于压缩和扩展VR模型。 VR模型在训练过程中被压缩,并且在语音识别期间被扩展。