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. 发明申请

WO2015134452A1 OPTIMIZATION OF AUDIO FINGERPRINT SEARCH 审中-公开
标题翻译：优化音视频指纹搜索
公开(公告)号：WO2015134452A1
公开(公告)日：2015-09-11
申请号：PCT/US2015/018429
申请日：2015-03-03
申请人： INTERACTIVE INTELLIGENCE GROUP, INC.
发明人： CHELUVARAJA, Srinath , IYER, Ananth Nagaraja , WYSS, Felix Immanuel
IPC分类号： G06F17/30 , G06F17/27
CPC分类号： G06F17/30743 , G10L25/51
摘要： A system and method are presented for optimization of audio fingerprint search. In an embodiment, the audio fingerprints are organized into a recursive tree with different branches containing fingerprint sets that are dissimilar to each other. The tree is constructed using a clustering algorithm based on a similarity measure. The similarity measure may comprise a Hamming distance for a binary fingerprint or a Euclidean distance for continuous valued fingerprints. In another embodiment, each fingerprint is stored at a plurality of resolutions and clustering is performed hierarchically. The recognition of an incoming fingerprint begins from the root of the tree and proceeds down its branches until a match or mismatch is declared. In yet another embodiment, a fingerprint definition is generalized to include more detailed audio information than in the previous definition.
摘要翻译：提出了一种用于音频指纹搜索优化的系统和方法。在一个实施例中，音频指纹被组织成具有不同分支的递归树，该分支包含彼此不相似的指纹集。使用基于相似性度量的聚类算法构建树。相似性度量可以包括二进制指纹的汉明距离或连续值指纹的欧几里德距离。在另一个实施例中，每个指纹以多个分辨率存储，并且分层地进行聚类。输入指纹的识别从树的根开始，并向下延伸到其分支，直到声明匹配或不匹配。在另一个实施例中，指纹定义被概括为包括比先前定义中更详细的音频信息。

2. 发明申请

WO2015134579A1 SYSTEM AND METHOD TO CORRECT FOR PACKET LOSS IN ASR SYSTEMS 审中-公开
标题翻译：纠正ASR系统中分组丢失的系统和方法
公开(公告)号：WO2015134579A1
公开(公告)日：2015-09-11
申请号：PCT/US2015/018692
申请日：2015-03-04
申请人： INTERACTIVE INTELLIGENCE GROUP, INC.
发明人： CHELUVARAJA, Srinath , IYER, Ananth Nagaraja , GANAPATHIRAJU, Aravind , WYSS, Felix Immanuel
IPC分类号： G10L15/14
CPC分类号： G10L19/005 , G10L15/02 , G10L15/08 , G10L15/14 , G10L15/20 , G10L25/18 , G10L25/21 , G10L2015/025 , G10L2019/0012
摘要： A system and method are presented for the correction of packet loss in audio in automatic speech recognition (ASR) systems. Packet loss correction, as presented herein, occurs at the recognition stage without modifying any of the acoustic models generated during training. The behavior of the ASR engine in the absence of packet loss is thus not altered. To accomplish this, the actual input signal may be rectified, the recognition scores may be normalized to account for signal errors, and a best-estimate method using information from previous frames and acoustic models may be used to replace the noisy signal.
摘要翻译：提出了一种用于在自动语音识别（ASR）系统中校正音频中的分组丢失的系统和方法。如本文所示，分组丢失校正发生在识别阶段，而不修改在训练期间产生的任何声学模型。因此，在没有丢包的情况下，ASR引擎的行为不会改变。为了实现这一点，实际输入信号可以被纠正，识别分数可以被归一化以考虑信号误差，并且可以使用使用来自先前帧和声学模型的信息的最佳估计方法来代替噪声信号。

3. 发明申请

WO2017117412A1 SYSTEM AND METHOD FOR NEURAL NETWORK BASED FEATURE EXTRACTION FOR ACOUSTIC MODEL DEVELOPMENT 审中-公开
标题翻译：基于神经网络的声学模型开发特征提取系统和方法
公开(公告)号：WO2017117412A1
公开(公告)日：2017-07-06
申请号：PCT/US2016/069257
申请日：2016-12-29
申请人： INTERACTIVE INTELLIGENCE GROUP, INC.
发明人： CHELUVARAJA, Srinath , IYER, Ananth Nagaraja
IPC分类号： G10L15/06 , G06F17/27 , G06F17/28 , G06N99/00 , G09B19/04 , G10L13/08
CPC分类号： G10L15/144 , G06N3/02 , G10L15/14 , G10L15/16 , G10L25/24 , G10L25/27
摘要： A system and method are presented for neural network based feature extraction for acoustic model development. A neural network may be used to extract acoustic features from raw MFCCs or the spectrum, which are then used for training acoustic models for speech recognition systems. Feature extraction may be performed by optimizing a cost function used in linear discriminant analysis. General non-linear functions generated by the neural network are used for feature extraction. The transformation may be performed using a cost function from linear discriminant analysis methods which perform linear operations on the MFCCs and generate lower dimensional features for speech recognition. The extracted acoustic features may then be used for training acoustic models for speech recognition systems.
摘要翻译：针对声学模型开发的基于神经网络的特征提取提出了一种系统和方法。神经网络可用于从原始MFCC或频谱中提取声学特征，然后将其用于训练用于语音识别系统的声学模型。特征提取可以通过优化线性判别分析中使用的成本函数来执行。由神经网络产生的一般非线性函数被用于特征提取。该变换可以使用线性判别分析方法中的成本函数来执行，该线性判别分析方法对MFCC执行线性运算并且生成用于语音识别的较低维度特征。提取的声学特征然后可以用于训练语音识别系统的声学模型。

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