2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)最新文献_第9页

Factorization for analog-to-digital matrix multiplication 模数矩阵乘法的因式分解

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178132

Edward H. Lee, Madeleine Udell, S. Wong

引用次数: 5

A sequential dictionary learning algorithm with enforced sparsity 一种具有强制稀疏性的顺序字典学习算法

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178697

A. Seghouane, M. Hanif

引用次数: 31

On the von mises approximation for the distribution of the phase angle between two independent complex Gaussian vectors 两个独立复高斯矢量间相位角分布的von mises近似

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178571

N. Letzepis

引用次数: 2

Utilizing spectro-temporal correlations for an improved speech presence probability based noise power estimation 利用频谱时间相关性改进语音存在概率噪声功率估计

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7177992

Martin Krawczyk-Becker, Dörte Fischer, Timo Gerkmann

{"title":"Utilizing spectro-temporal correlations for an improved speech presence probability based noise power estimation","authors":"Martin Krawczyk-Becker, Dörte Fischer, Timo Gerkmann","doi":"10.1109/ICASSP.2015.7177992","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7177992","url":null,"abstract":"For the enhancement of speech degraded by noise, accurate estimation of the noise power spectral density (PSD) is indispensable, especially if only a single microphone signal is available. Fast and accurate tracking of the noise PSD is particularly challenging in highly non-stationary noise types, since the distinction between speech and noise components becomes more difficult. Short-time discrete Fourier transform (STFT) based noise PSD estimation algorithms which employ estimates of the speech presence probability (SPP) with fixed priors have been shown to yield good tracking performance even in adverse noise conditions. In this paper, we compare two methods to incorporate spectro-temporal correlations to improve the tracking performance. The first method smoothes the noisy observation over time and frequency before computing the SPP, while the second is based on a Hidden Markov Model (HMM) of the speech presence and absence states. We show that the proposed modifications lead to improved noise PSD estimators which are less sensitive to spectral outliers of the noise and track changes in the noise PSD more quickly than the reference method. Further, when employed in a common speech enhancement setup, the proposed estimators achieve an increased noise reduction while keeping speech distortions at a comparable level.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122262047","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Histogram-PMHT with an evolving Poisson prior 具有进化泊松先验的pmht直方图

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178734

H. Vu, S. Davey, S. Arulampalam, F. Fletcher, C. Lim

引用次数: 10

Location-aware object detection via coherent region grouping 通过相干区域分组的位置感知目标检测

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178178

Shen-Chi Chen, Kevin Lin, Chu-Song Chen, Y. Hung

引用次数: 1

Tyler's estimator performance analysis 泰勒估计器性能分析

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7179061

I. Soloveychik, A. Wiesel

引用次数: 1

Combination of two-dimensional cochleogram and spectrogram features for deep learning-based ASR 基于深度学习的ASR的二维耳蜗图和声谱图特征的结合

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178827

Andros Tjandra, S. Sakti, Graham Neubig, T. Toda, M. Adriani, Satoshi Nakamura

{"title":"Combination of two-dimensional cochleogram and spectrogram features for deep learning-based ASR","authors":"Andros Tjandra, S. Sakti, Graham Neubig, T. Toda, M. Adriani, Satoshi Nakamura","doi":"10.1109/ICASSP.2015.7178827","DOIUrl":"https://doi.org/10.1109/ICASSP.2015.7178827","url":null,"abstract":"This paper explores the use of auditory features based on cochleograms; two dimensional speech features derived from gammatone filters within the convolutional neural network (CNN) framework. Furthermore, we also propose various possibilities to combine cochleogram features with log-mel filter banks or spectrogram features. In particular, we combine within low and high levels of CNN framework which we refer to as low-level and high-level feature combination. As comparison, we also construct the similar configuration with deep neural network (DNN). Performance was evaluated in the framework of hybrid neural network - hidden Markov model (NN-HMM) system on TIMIT phoneme sequence recognition task. The results reveal that cochleogram-spectrogram feature combination provides significant advantages. The best accuracy was obtained by high-level combination of two dimensional cochleogram-spectrogram features using CNN, achieved up to 8.2% relative phoneme error rate (PER) reduction from CNN single features or 19.7% relative PER reduction from DNN single features.","PeriodicalId":117666,"journal":{"name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121720037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 20

An iterative deflation algorithm for exact CP tensor decomposition 精确CP张量分解的迭代压缩算法

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178714

A. P. D. Silva, P. Comon, A. D. Almeida

引用次数: 11

Joint training of front-end and back-end deep neural networks for robust speech recognition 面向鲁棒语音识别的前端和后端深度神经网络联合训练

2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Pub Date : 2015-04-19 DOI: 10.1109/ICASSP.2015.7178797

Tian Gao, Jun Du, Lirong Dai, Chin-Hui Lee

引用次数: 73