ID 原文 译文
24235 该文提出一种基于自适应逼近残差的稀疏表示语音降噪方法。 A sparse representation speech denoising method based on adapted stopping residue error is proposed.
24236 在字典学习阶段基于 K 奇异值分解(K-Singular Value Decomposition, K-SVD)算法获得干净语音谱的过完备字典，在稀疏表示阶段基于权重因子调整后的噪声谱和估计的交叉项对逼近残差持续自适应地更新，并采用正交匹配追踪(Orthogonal Matching Pursuit, OMP)方法对干净语音谱进行稀疏重构。 Firstly, an over complete dictionary of the clean speech power spectrum is learned by the K-Singular Value Decomposition (K-SVD) algorithm. In the sparse representation stage, the stopping residue error is adaptively achieved according to the estimated cross terms and the noise spectrum which is adjusted by a weighted factor, and the Orthogonal Matching Pursuit (OMP) approach is applied to reconstruct the clean speech spectrum from the noisy speech.
24237 最后结合估计的干净语音谱与带噪语音相位，通过傅里叶逆变换获得重构的干净语音。 Finally, the clean speech is re-synthesis via the inverse Fourier transform with the reconstructed speech spectrum and the noisy speech phase.
24238 实验结果表明所提方法在不同噪声和信噪比条件下相比标准的谱减法，稀疏表示语音降噪算法和基于自回归隐马尔可夫模型的降噪方法有更好的降噪效果。 The experiment results show that the proposed method outperforms the standard spectral subtraction, sparse representation based speech denoising algorithm and the AutoRegressive Hidden Markov Model (AR-HMM) based speech denoising method in terms of subjective and objective measure.
24239 现有基于机器学习的道路分割方法存在当训练样本和目标场景样本分布不匹配时检测效果下降显著的缺陷。 The existing machine learning based road segmentation algorithms maintain obvious shortage that the detection effect decreases dramatically when the distribution of training samples and the scene target samples does not match.
24240 针对该问题，该文提出一种基于深度卷积网络和自编码器的场景自适应道路分割算法。 Focusing on this issue, a scene adaptive road segmentation algorithm based on Deep Convolutional Neural Network (DCNN) and auto encoder is proposed.
24241 首先，采用较为经典的基于慢特征分析(SFA)和 GentleBoost 的方法，实现了带标签置信度样本的在线选取； Firstly, classic Slow Feature Analysis (SFA) and Gentle Boost based method is used to generate online samples whose label contain confidence value.
24242 其次，利用深度卷积神经网络(DCNN)深度结构的特征自动抽取能力，辅以特征自编码器对源-目标场景下特征相似度度量，提出了一种采用复合深度结构的场景自适应分类器模型并设计了训练方法。 After that, using the automatic feature extraction ability of DCNN and performing source-target scene feature similarity calculation with deep auto-encoder, a composite deep structure-based scene adaptive classifier and its training method are designed.
24243 在 KITTI 测试库的测试结果表明，所提算法较现有非场景自适应道路分割算法具有较大的优越性，在检测率上平均提升约 4.5%。 The experiment on KITTI dataset demonstrates that the proposed method outperforms the existed machine learning based road segmentation algorithms which upgrades the detection rate on average of around 4.5%.
24244 针对共形阵列天线自适应波束形成中存在的通用性差、主瓣保形困难、计算复杂度高等问题，该文提出一种基于稀疏重构的稳健自适应波束形成算法。 Adaptive beamforming techniques for conformal arrays suffer from poor universality, difficulty to maintain the main beam and high computational cost. A novel robust adaptive beamforming algorithm for conformal arrays based on sparse reconstruction is proposed to alleviate the existing problems.