A Multistream Feature Framework Based on Bandpass Modulation Filtering for Robust Speech Recognition [0.03%]
一种基于带通调制滤波的鲁棒性语音识别多流特征框架
Sridhar Krishna Nemala,Kailash Patil,Mounya Elhilali
Sridhar Krishna Nemala
There is strong neurophysiological evidence suggesting that processing of speech signals in the brain happens along parallel paths which encode complementary information in the signal. These parallel streams are organized around a duality o...
Efficient Approximation of Head-Related Transfer Functions in Subbands for Accurate Sound Localization [0.03%]
基于子带的高效头相关传输函数(HRTF)逼近方法及其在精确声源定位中的应用
Damián Marelli,Robert Baumgartner,Piotr Majdak
Damián Marelli
Head-related transfer functions (HRTFs) describe the acoustic filtering of incoming sounds by the human morphology and are essential for listeners to localize sound sources in virtual auditory displays. Since rendering complex virtual scene...
Subglottal Impedance-Based Inverse Filtering of Voiced Sounds Using Neck Surface Acceleration [0.03%]
基于亚 glottal 阻抗的逆滤波 voiced sounds 采用颈部表面加速度
Matías Zañartu,Julio C Ho,Daryush D Mehta et al.
Matías Zañartu et al.
A model-based inverse filtering scheme is proposed for an accurate, non-invasive estimation of the aerodynamic source of voiced sounds at the glottis. The approach, referred to as subglottal impedance-based inverse filtering (IBIF), takes a...
A Dual-Microphone Speech Enhancement Algorithm Based on the Coherence Function [0.03%]
基于相干函数的双麦克风语音增强算法
Nima Yousefian,Philipos C Loizou
Nima Yousefian
A novel dual-microphone speech enhancement technique is proposed in the present paper. The technique utilizes the coherence between the target and noise signals as a criterion for noise reduction and can be generally applied to arrays with ...
Spoken Language Derived Measures for Detecting Mild Cognitive Impairment [0.03%]
基于口语特征的轻度认知障碍检测方法研究
Brian Roark,Margaret Mitchell,John-Paul Hosom et al.
Brian Roark et al.
Spoken responses produced by subjects during neuropsychological exams can provide diagnostic markers beyond exam performance. In particular, characteristics of the spoken language itself can discriminate between subject groups. We present r...
Reasons why current speech-enhancement algorithms do not improve speech intelligibility and suggested solutions [0.03%]
当前的语音增强算法为什么不能提高语音可懂度以及可能的解决方案
Philipos C Loizou,Gibak Kim
Philipos C Loizou
Existing speech enhancement algorithms can improve speech quality but not speech intelligibility, and the reasons for that are unclear. In the present paper, we present a theoretical framework that can be used to analyze potential factors t...
Estimators of The Magnitude-Squared Spectrum and Methods for Incorporating SNR Uncertainty [0.03%]
幅度平方谱的估计方法及信噪比不确定性的引入方法
Yang Lu,Philipos C Loizou
Yang Lu
Statistical estimators of the magnitude-squared spectrum are derived based on the assumption that the magnitude-squared spectrum of the noisy speech signal can be computed as the sum of the (clean) signal and noise magnitude-squared spectra...
Jiucang Hao,Te-Won Lee,Terrence J Sejnowski
Jiucang Hao
This paper presents a novel probabilistic approach to speech enhancement. Instead of a deterministic logarithmic relationship, we assume a probabilistic relationship between the frequency coefficients and the log-spectra. The speech model i...
Dagen Wang,Shrikanth Narayanan
Dagen Wang
An algorithm for automatic speech prominence detection is reported in this paper. We describe a comparative analysis on various acoustic features for word prominence detection and report results using a spoken dialog corpus with manually as...
Dagen Wang,Shrikanth S Narayanan
Dagen Wang
In this paper, we propose a direct method for speech rate estimation from acoustic features without requiring any automatic speech transcription. We compare various spectral and temporal signal analysis and smoothing strategies to better ch...