This paper investigates several aspects of training a RNN (recurrent neural network) that impact the objective and subjective quality of enhanced speech for real-time single-channel speech enhancement. Specifically, we focus on a RNN that enhances short-time speech spectra on a single-frame-in, single-frame-out basis, a framework adopted by most classical signal processing methods. We propose two novel mean-squared-error-based learning objectives that enable separate control over the importance of speech distortion versus noise reduction. The proposed loss functions are evaluated by widely accepted objective quality and intelligibility measures and compared to other competitive online methods. In addition, we study the impact of feature normalization and varying batch sequence lengths on the objective quality of enhanced speech. Finally, we show subjective ratings for the proposed approach and a state-of-the-art real-time RNN-based method.
We present a self-supervised speech restoration method without paired speech corpora. Because the previous general speech restoration method uses artificial paired data created by applying various distortions to high-quality speech corpora, it cannot sufficiently represent acoustic distortions of real data, limiting the applicability. Our model consists of analysis, synthesis, and channel modules that simulate the recording process of degraded speech and is trained with real degraded speech data in a self-supervised manner. The analysis module extracts distortionless speech features and distor…
Deep learning based speech enhancement has made rapid development towards improving quality, while models are becoming more compact and usable for real-time on-the-edge inference. However, the speech quality scales directly with the model size, and small models are often still unable to achieve sufficient quality. Furthermore, the introduced speech distortion and artifacts greatly harm speech quality and intelligibility, and often significantly degrade automatic speech recognition (ASR) rates. In this work, we shed light on the success of the spectral complex compressed mean squared error (MSE…
Phase serves as a critical component of speech that influences the quality and intelligibility. Current speech enhancement algorithms are beginning to address phase distortions, but the algorithms focus on normal-hearing (NH) listeners. It is not clear whether phase enhancement is beneficial for hearing-impaired (HI) listeners. We investigated the influence of phase distortion on speech quality through a listening study, in which NH and HI listeners provided speech-quality ratings using the MUSHRA procedure. In one set of conditions, the speech was mixed with babble noise at 4 different signal…
Texas A M University（德州农工大学）；Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Concordia University（康考迪亚大学）
A speech enhancement method based on probabilistic geometric approach to spectral subtraction (PGA) performed on short time magnitude spectrum is presented in this paper. A confidence parameter of noise estimation is introduced in the gain function of the proposed method to prevent subtraction of the overestimated and underestimated noise, which not only removes the noise efficiently but also prevents the speech distortion. The noise compensated magnitude spectrum is then recombined with the unchanged phase spectrum to produce a modified complex spectrum prior to synthesize an enhanced frame. …
Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the …
We present an end-to-end deep learning approach to denoising speech signals by processing the raw waveform directly. Given input audio containing speech corrupted by an additive background signal, the system aims to produce a processed signal that contains only the speech content. Recent approaches have shown promising results using various deep network architectures. In this paper, we propose to train a fully-convolutional context aggregation network using a deep feature loss. That loss is based on comparing the internal feature activations in a different network, trained for acoustic environ…
Wakayama University（和歌山大学）；NTT Communication Science Laboratories（NTT通信科学基础研究所）
In this study, we propose a new concept, the gammachirp envelope distortion index (GEDI), based on the signal-to-distortion ratio in the auditory envelope, SDRenv to predict the intelligibility of speech enhanced by nonlinear algorithms. The objective of GEDI is to calculate the distortion between enhanced and clean-speech representations in the domain of a temporal envelope extracted by the gammachirp auditory filterbank and modulation filterbank. We also extend GEDI with multi-resolution analysis (mr-GEDI) to predict the speech intelligibility of sounds under non-stationary noise conditions.…
Recent years have seen a surge in the number of available frameworks for speech enhancement (SE) and recognition. Whether model-based or constructed via deep learning, these frameworks often rely in isolation on either time-domain signals or time-frequency (TF) representations of speech data. In this study, we investigate the advantages of each set of approaches by separately examining their impact on speech intelligibility and quality. Furthermore, we combine the fragmented benefits of time-domain and TF speech representations by introducing two new cross-domain SE frameworks. A quantitative …
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；Carnegie Mellon University（卡内基梅隆大学）
A promising approach for multi-microphone speech separation involves two deep neural networks (DNN), where the predicted target speech from the first DNN is used to compute signal statistics for time-invariant minimum variance distortionless response (MVDR) beamforming, and the MVDR result is then used as extra features for the second DNN to predict target speech. Previous studies suggested that the MVDR result can provide complementary information for the second DNN to better predict target speech. However, on fixed-geometry arrays, both DNNs can take in, for example, the real and imaginary (…
Indian Institute of Science（印度科学理工学院）；Indian Railways（印度铁路公司）
The goal in speech enhancement is to obtain an estimate of clean speech starting from the noisy signal by minimizing a chosen distortion measure, which results in an estimate that depends on the unknown clean signal or its statistics. Since access to such prior knowledge is limited or not possible in practice, one has to estimate the clean signal statistics. In this paper, we develop a new risk minimization framework for speech enhancement, in which, one optimizes an unbiased estimate of the distortion/risk instead of the actual risk. The estimated risk is expressed solely as a function of the…
Speech, Audio and Music Intelligence (SAMI), ByteDance（字节跳动语音、音频和音乐智能（SAMI）部门）
Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on single-task speech restoration (SSR), such as speech denoising or speech declipping. However, SSR systems only focus on one task and do not address the general speech restoration problem. In addition, previous SSR systems show limited performance in some speech restoration tasks such as speech super-resolution. To overcome those limitations, we propose a general speech restoration (GSR) task that attempts to remove multiple distortions simultaneously. Furthermore, we propose VoiceFixer, a generative …
This paper describes our submission to the L3DAS22 Challenge Task 1, which consists of speech enhancement with 3D Ambisonic microphones. The core of our approach combines Deep Neural Network (DNN) driven complex spectral mapping with linear beamformers such as the multi-frame multi-channel Wiener filter. Our proposed system has two DNNs and a linear beamformer in between. Both DNNs are trained to perform complex spectral mapping, using a combination of waveform and magnitude spectrum losses. The estimated signal from the first DNN is used to drive a linear beamformer, and the beamforming resul…
Department of Brain and Cognitive Sciences, MIT, USA（脑科学与认知科学系，麻省理工学院）；McGovern Institute for Brain Research, MIT, USA（脑研究麦戈文研究所，麻省理工学院）；Center for Brains, Minds and Machines, MIT, USA（脑、心智与机器中心，麻省理工学院）；MIT-IBM Watson AI Lab, IBM Research, USA（麻省理工-IBM沃森人工智能实验室，IBM研究院）
Multi-frame approaches for single-microphone speech enhancement, e.g., the multi-frame minimum-power-distortionless-response (MFMPDR) filter, are able to exploit speech correlations across neighboring time frames. In contrast to single-frame approaches such as the Wiener gain, it has been shown that multi-frame approaches achieve a substantial noise reduction with hardly any speech distortion, provided that an accurate estimate of the correlation matrices and especially the speech interframe correlation (IFC) vector is available. Typical estimation procedures of the IFC vector require an estim…
The speech enhancement task usually consists of removing additive noise or reverberation that partially mask spoken utterances, affecting their intelligibility. However, little attention is drawn to other, perhaps more aggressive signal distortions like clipping, chunk elimination, or frequency-band removal. Such distortions can have a large impact not only on intelligibility, but also on naturalness or even speaker identity, and require of careful signal reconstruction. In this work, we give full consideration to this generalized speech enhancement task, and show it can be tackled with a time…
Feature mapping using deep neural networks is an effective approach for single-channel speech enhancement. Noisy features are transformed to the enhanced ones through a mapping network and the mean square errors between the enhanced and clean features are minimized. In this paper, we propose a cycle-consistent speech enhancement (CSE) in which an additional inverse mapping network is introduced to reconstruct the noisy features from the enhanced ones. A cycle-consistent constraint is enforced to minimize the reconstruction loss. Similarly, a backward cycle of mappings is performed in the oppos…
Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of perceptual losses. Perceptual loss discourages distortion to certain speech properties and we analyze it using six large-scale pre-trained models: speaker classification, acoustic model, speaker embedding, emotion classification, and two self-supervised speech encoders (PASE+, wav2vec 2.0). We first build a strong baseline (w/o PERL) using Conformer Transformer N…
Recently, the convolutional weighted power minimization distortionless response (WPD) beamformer was proposed, which unifies multi-channel weighted prediction error dereverberation and minimum power distortionless response beamforming. To optimize the convolutional filter, the desired speech component is modeled with a time-varying Gaussian model, which promotes the sparsity of the desired speech component in the short-time Fourier transform domain compared to the noisy microphone signals. In this paper we generalize the convolutional WPD beamformer by using an lp-norm cost function, introduci…
We explore the possibility of leveraging accelerometer data to perform speech enhancement in very noisy conditions. Although it is possible to only partially reconstruct user's speech from the accelerometer, the latter provides a strong conditioning signal that is not influenced from noise sources in the environment. Based on this observation, we feed a multi-modal input to SEANet (Sound EnhAncement Network), a wave-to-wave fully convolutional model, which adopts a combination of feature losses and adversarial losses to reconstruct an enhanced version of user's speech. We trained our model wit…
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（语音与语言信息处理国家级工程研究中心，中国科学技术大学）
Westlake University（西湖大学）；Westlake Institute for Advanced Study（西湖高等研究院）；Zhejiang University（浙江大学）
This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections. This type of target suddenly truncates the reverberation, and thus it may not be suitable for network training. The proposed RTS target suppresses reverberation and meanwhile maintains the exponential decaying property of reverberation, which will ease the network training, and thus reduce signal distortion caused by the prediction error. Moreover, this work e…
Logitech Europe S.A.（罗技欧洲公司）；Imperial College London（帝国理工学院）；Swiss Federal Institute of Technology Lausanne（洛桑瑞士联邦理工学院）
Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their efficacy remains limited for very low signal-to-noise ratios or when parts of the signal are missing. To address these limitations, here we propose an end-to-end framework for speech inpainting, the context-based retrieval of missing or severely distorted parts of time-frequency representation of speech. The framework is based on a convolutional U-Net trained vi…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社NTT通信科学实验室）
This paper proposes a method for estimating a convolutional beamformer that can perform denoising and dereverberation simultaneously in an optimal way. The application of dereverberation based on a weighted prediction error (WPE) method followed by denoising based on a minimum variance distortionless response (MVDR) beamformer has conventionally been considered a promising approach, however, the optimality of this approach cannot be guaranteed. To realize the optimal integration of denoising and dereverberation, we present a method that unifies the WPE dereverberation method and a variant of t…
With the increasing demand for audio communication and online conference, ensuring the robustness of Acoustic Echo Cancellation (AEC) under the complicated acoustic scenario including noise, reverberation and nonlinear distortion has become a top issue. Although there have been some traditional methods that consider nonlinear distortion, they are still inefficient for echo suppression and the performance will be attenuated when noise is present. In this paper, we present a real-time AEC approach using complex neural network to better modeling the important phase information and frequency-time-…
National Engineering Research Center of Speech and Language Information Processing（语音及语言信息处理国家工程研究中心）；University of Science and Technology of China（中国科学技术大学）
Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the other hand, it was shown that self-supervised pre-training enables the utilization of a large amount of unlabeled noisy data, which is rather beneficial for the noise robustness of ASR. However, the potential of the (optimal) integration of SE and self-supervised pre-training still remains unclear. In order to find an appropriate combination and reduce the im…
Google Research（谷歌研究院）；Google Chrome Audio（谷歌Chrome音频团队）
We explore a variety of neural networks configurations for one- and two-channel spectrogram-mask-based speech enhancement. Our best model improves on previous state-of-the-art performance on the CHiME2 speech enhancement task by 0.4 decibels in signal-to-distortion ratio (SDR). We examine trade-offs such as non-causal look-ahead, computation, and parameter count versus enhancement performance and find that zero-look-ahead models can achieve, on average, within 0.03 dB SDR of our best bidirectional model. Further, we find that 200 milliseconds of look-ahead is sufficient to achieve equivalent p…
Technion -- Israel Institute of Technology（以色列理工学院）
Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to …
Distortion resulting from acoustic echo suppression (AES) is a common issue in full-duplex communication. To address the distortion problem, a multi-frame minimum variance distortionless response (MFMVDR) filtering technique is proposed. The MFMVDR filter with parameter estimation which was used in speech enhancement problems is extended in this study from a deep learning perspective. To alleviate numerical instability of the MFMVDR filter, we propose to directly estimate the inverse of the correlation matrix. The AES system is advantageous in that no double-talk detection is required. The neg…
Usually, hearing impaired people use hearing aids which are implemented with speech enhancement algorithms. Estimation of speech and estimation of nose are the components in single channel speech enhancement system. The main objective of any speech enhancement algorithm is estimation of noise power spectrum for non stationary environment. VAD (Voice Activity Detector) is used to identify speech pauses and during these pauses only estimation of noise. MMSE (Minimum Mean Square Error) speech enhancement algorithm did not enhance the intelligibility, quality and listener fatigues are the perceptu…
In this paper, a neural network-augmented algorithm for noise-robust online dereverberation with a Kalman filtering variant of the weighted prediction error (WPE) method is proposed. The filter stochastic variations are predicted by a deep neural network (DNN) trained end-to-end using the filter residual error and signal characteristics. The presented framework allows for robust dereverberation on a single-channel noisy reverberant dataset similar to WHAMR!. The Kalman filtering WPE introduces distortions in the enhanced signal when predicting the filter variations from the residual error only…
Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Chi Mei Hospital（奇美医院）；National Chi Nan University（国立暨南国际大学）；Carnegie Mellon University（卡内基梅隆大学）
Real-world audio recordings are often degraded by factors such as noise, reverberation, and equalization distortion. This paper introduces HiFi-GAN, a deep learning method to transform recorded speech to sound as though it had been recorded in a studio. We use an end-to-end feed-forward WaveNet architecture, trained with multi-scale adversarial discriminators in both the time domain and the time-frequency domain. It relies on the deep feature matching losses of the discriminators to improve the perceptual quality of enhanced speech. The proposed model generalizes well to new speakers, new spee…
In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations, which is crucial to obtain good results. The model is optimized through a set of losses defined over both waveform and multi-resolution spectrograms. The proposed method outperforms the state-of-the-art models in terms of denoised speech quality from various objective and subjective evaluation metrics. We release our code and models at https://github.com/nvidi…
Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising
Graduate School of Informatics, Kyoto University（京都大学情报学研究科）；Center for Advanced Intelligence Project (AIP), RIKEN（理化学研究所先进智能项目中心）；National Institute of Advanced Industrial Science and Technology (AIST)（日本国立先进工业科学技术研究院）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎综合理工学院巴黎电信学院LTCI（注：LTCI为实验室名称，按要求提取到机构级别即巴黎电信学院及巴黎综合理工学院））；Graduate School of Engineering, Kyoto University（京都大学工学研究科）
Graz University of Technology（格拉茨技术大学）；Ruperts Karls University（海德堡大学）
While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by the demand for embedded systems and their usage in ubiquitous computing and IoT applications. In this article, we provide a resource-efficient approach for multi-channel speech enhancement based on Deep Neural Networks (DNNs). In particular, we use reduced-precision DNNs for estimating a speech mask from noisy, multi-channel microphone observations. This spe…
Modern neural speech enhancement models usually include various forms of phase information in their training loss terms, either explicitly or implicitly. However, these loss terms are typically designed to reduce the distortion of phase spectrum values at specific frequencies, which ensures they do not significantly affect the quality of the enhanced speech. In this paper, we propose an effective phase reconstruction strategy for neural speech enhancement that can operate in noisy environments. Specifically, we introduce a phase continuity loss that considers relative phase variations across t…
