We propose a feature enhancement algorithm to improve robust automatic speech recognition (ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel frequency domain using deep ...neural networks and a set of time-frequency unit level features that has previously been used to estimate the ideal binary mask. The estimated IRM is used to filter out noise from a noisy Mel spectrogram before performing cepstral feature extraction for ASR. On the noisy subset of the Aurora-4 robust ASR corpus, the proposed enhancement obtains a relative improvement of over 38% in terms of word error rates using ASR models trained in clean conditions, and an improvement of over 14% when the models are trained using the multi-condition training data. In terms of instantaneous SNR estimation performance, the proposed system obtains a mean absolute error of less than 4 dB in most frequency channels.
Towards Scaling Up Classification-Based Speech Separation Wang, Yuxuan; Wang, DeLiang
IEEE transactions on audio, speech and language processing/IEEE transactions on audio, speech, and language processing,
07/2013, Volume:
21, Issue:
7
Journal Article
Peer reviewed
Open access
Formulating speech separation as a binary classification problem has been shown to be effective. While good separation performance is achieved in matched test conditions using kernel support vector ...machines (SVMs), separation in unmatched conditions involving new speakers and environments remains a big challenge. A simple yet effective method to cope with the mismatch is to include many different acoustic conditions into the training set. However, large-scale training is almost intractable for kernel machines due to computational complexity. To enable training on relatively large datasets, we propose to learn more linearly separable and discriminative features from raw acoustic features and train linear SVMs, which are much easier and faster to train than kernel SVMs. For feature learning, we employ standard pre-trained deep neural networks (DNNs). The proposed DNN-SVM system is trained on a variety of acoustic conditions within a reasonable amount of time. Experiments on various test mixtures demonstrate good generalization to unseen speakers and background noises.
On Training Targets for Supervised Speech Separation Yuxuan Wang; Narayanan, Arun; DeLiang Wang
IEEE/ACM transactions on audio, speech, and language processing,
2014-Dec., 2014-Dec, 2014-12-00, 20141201, Volume:
22, Issue:
12
Journal Article
Peer reviewed
Open access
Formulation of speech separation as a supervised learning problem has shown considerable promise. In its simplest form, a supervised learning algorithm, typically a deep neural network, is trained to ...learn a mapping from noisy features to a time-frequency representation of the target of interest. Traditionally, the ideal binary mask (IBM) is used as the target because of its simplicity and large speech intelligibility gains. The supervised learning framework, however, is not restricted to the use of binary targets. In this study, we evaluate and compare separation results by using different training targets, including the IBM, the target binary mask, the ideal ratio mask (IRM), the short-time Fourier transform spectral magnitude and its corresponding mask (FFT-MASK), and the Gammatone frequency power spectrum. Our results in various test conditions reveal that the two ratio mask targets, the IRM and the FFT-MASK, outperform the other targets in terms of objective intelligibility and quality metrics. In addition, we find that masking based targets, in general, are significantly better than spectral envelope based targets. We also present comparisons with recent methods in non-negative matrix factorization and speech enhancement, which show clear performance advantages of supervised speech separation.
This study proposes a complex spectral mapping approach for single- and multi-channel speech enhancement, where deep neural networks (DNNs) are used to predict the real and imaginary (RI) components ...of the direct-path signal from noisy and reverberant ones. The proposed system contains two DNNs. The first one performs single-channel complex spectral mapping. The estimated complex spectra are used to compute a minimum variance distortion-less response (MVDR) beamformer. The RI components of beamforming results, which encode spatial information, are then combined with the RI components of the mixture to train the second DNN for multi-channel complex spectral mapping. With estimated complex spectra, we also propose a novel method of time-varying beamforming. State-of-the-Art performance is obtained on the speech enhancement and recognition tasks of the CHiME-4 corpus. More specifically, our system obtains 6.82%, 3.19% and 1.99% word error rates (WER) respectively on the single-, two-, and six-microphone tasks of CHiME-4, significantly surpassing the current best results of 9.15%, 3.91% and 2.24% WER.
Recently, supervised classification has been shown to work well for the task of speech separation. We perform an in-depth evaluation of such techniques as a front-end for noise-robust automatic ...speech recognition (ASR). The proposed separation front-end consists of two stages. The first stage removes additive noise via time-frequency masking. The second stage addresses channel mismatch and the distortions introduced by the first stage; a non-linear function is learned that maps the masked spectral features to their clean counterpart. Results show that the proposed front-end substantially improves ASR performance when the acoustic models are trained in clean conditions. We also propose a diagonal feature discriminant linear regression (dFDLR) adaptation that can be performed on a per-utterance basis for ASR systems employing deep neural networks and HMM. Results show that dFDLR consistently improves performance in all test conditions. Surprisingly, the best average results are obtained when dFDLR is applied to models trained using noisy log-Mel spectral features from the multi-condition training set. With no channel mismatch, the best results are obtained when the proposed speech separation front-end is used along with multi-condition training using log-Mel features followed by dFDLR adaptation. Both these results are among the best on the Aurora-4 dataset.
Complex Ratio Masking for Monaural Speech Separation Williamson, Donald S.; Wang, Yuxuan; Wang, DeLiang
IEEE/ACM transactions on audio, speech, and language processing,
03/2016, Volume:
24, Issue:
3
Journal Article
Peer reviewed
Open access
Speech separation systems usually operate on the short-time Fourier transform (STFT) of noisy speech, and enhance only the magnitude spectrum while leaving the phase spectrum unchanged. This is done ...because there was a belief that the phase spectrum is unimportant for speech enhancement. Recent studies, however, suggest that phase is important for perceptual quality, leading some researchers to consider magnitude and phase spectrum enhancements. We present a supervised monaural speech separation approach that simultaneously enhances the magnitude and phase spectra by operating in the complex domain. Our approach uses a deep neural network to estimate the real and imaginary components of the ideal ratio mask defined in the complex domain. We report separation results for the proposed method and compare them to related systems. The proposed approach improves over other methods when evaluated with several objective metrics, including the perceptual evaluation of speech quality (PESQ), and a listening test where subjects prefer the proposed approach with at least a 69% rate.
Organic ultralong room‐temperature phosphorescence (RTP) materials have promising applications in anti‐counterfeiting. To improve the encryption level, the exploration of organic materials with ...tunable solid‐state long persistent luminescence is in urgent need. Herein, a series of organic ultralong RTP polymeric systems are prepared by doping versatile indolocarbazole isomers into the poly(vinyl alcohol) (PVA) matrix. Notably, the doping film 11,12‐ICz@PVA exhibits excellent RTP property with an ultralong lifetime of 2.04 s and a high phosphorescence quantum yield of 44.1%. Theoretical calculations reveal that this excellent RTP property can be attributed to the strong electrostatic attraction resulting from the synergistic double hydrogen‐bond between the isomer 11,12‐ICz and PVA matrix. More impressively, color‐tunable and time‐dependent long persistent luminescence is successfully achieved through efficient phosphorescence energy transfer between the indolocarbazole isomers with ultralong blue RTP emissions and commercially available fluorescent dyes with emission colors ranging from green to red doped into the PVA matrix. Besides, diversified encryption patterns are fabricated to demonstrate the promising applications of these water‐soluble doping PVA systems with tunable solid‐state persistent luminescence in advanced anti‐counterfeiting technology.
Color‐tunable and time‐dependent organic afterglow materials are achieved via efficient phosphorescence resonance energy transfer within three‐component doping PVA systems, in which indolocarbazole isomers with ultralong blue RTP emissions act as energy donors while commercially available fluorescent dyes with emission colors ranging from green to red act as energy acceptors.
In real-world situations, speech is masked by both background noise and reverberation, which negatively affect perceptual quality and intelligibility. In this paper, we address monaural speech ...separation in reverberant and noisy environments. We perform dereverberation and denoising using supervised learning with a deep neural network. Specifically, we enhance the magnitude and phase by performing separation with an estimate of the complex ideal ratio mask. We define the complex ideal ratio mask so that direct speech results after the mask is applied to reverberant and noisy speech. Our approach is evaluated using simulated and real room impulse responses, and with background noises. The proposed approach improves objective speech quality and intelligibility significantly. Evaluations and comparisons show that it outperforms related methods in many reverberant and noisy environments.
Monaural speech segregation has been a very challenging problem for decades. By casting speech segregation as a binary classification problem, recent advances have been made in computational auditory ...scene analysis on segregation of both voiced and unvoiced speech. So far, pitch and amplitude modulation spectrogram have been used as two main kinds of time-frequency (T-F) unit level features in classification. In this paper, we expand T-F unit features to include gammatone frequency cepstral coefficients (GFCC), mel-frequency cepstral coefficients, relative spectral transform (RASTA) and perceptual linear prediction (PLP). Comprehensive comparisons are performed in order to identify effective features for classification-based speech segregation. Our experiments in matched and unmatched test conditions show that these newly included features significantly improve speech segregation performance. Specifically, GFCC and RASTA-PLP are the best single features in matched-noise and unmatched-noise test conditions, respectively. We also find that pitch-based features are crucial for good generalization to unseen environments. To further explore complementarity in terms of discriminative power, we propose to use a group Lasso approach to select complementary features in a principled way. The final combined feature set yields promising results in both matched and unmatched test conditions.
Monaural speech separation is a fundamental problem in speech and signal processing. This problem can be approached from a supervised learning perspective by predicting an ideal time-frequency mask ...from features of noisy speech. In reverberant conditions at low signal-to-noise ratios (SNRs), accurate mask prediction is challenging and can benefit from effective features. In this paper, we investigate an extensive set of acoustic-phonetic features extracted in adverse conditions. Deep neural networks are used as the learning machine, and separation performance is evaluated using standard objective speech intelligibility metrics. Separation performance is systematically evaluated in both nonspeech and speech interference, in a variety of SNRs, reverberation times, and direct-to-reverberant energy ratios. Considerable performance improvement is observed by using contextual information, likely due to temporal effects of room reverberation. In addition, we construct feature combination sets using a sequential floating forward selection algorithm, and combined features outperform individual ones. We also find that optimal feature sets in anechoic conditions are different from those in reverberant conditions.