Despite the rapid advance of automatic speech recognition (ASR) technologies, accurate recognition of cocktail party speech characterised by the interference from overlapping speakers, background noise and room reverberation remains a highly challenging task to date. Motivated by the invariance of visual modality to acoustic signal corruption, audio-visual speech enhancement techniques have been developed, although predominantly targeting overlapping speech separation and recognition tasks. In this paper, an audio-visual multi-channel speech separation, dereverberation and recognition approach featuring a full incorporation of visual information into all three stages of the system is proposed. The advantage of the additional visual modality over using audio only is demonstrated on two neural dereverberation approaches based on DNN-WPE and spectral mapping respectively. The learning cost function mismatch between the separation and dereverberation models and their integration with the back-end recognition system is minimised using fine-tuning on the MSE and LF-MMI criteria. Experiments conducted on the LRS2 dataset suggest that the proposed audio-visual multi-channel speech separation, dereverberation and recognition system outperforms the baseline audio-visual multi-channel speech separation and recognition system containing no dereverberation module by a statistically significant word error rate (WER) reduction of 2.06% absolute (8.77% relative).
Neural network based speech dereverberation has achieved promising results in recent studies. Nevertheless, many are focused on recovery of only the direct path sound and early reflections, which could be beneficial to speech perception, are discarded. The performance of a model trained to recover clean speech degrades when evaluated on early reverberation targets, and vice versa. This paper proposes a novel deep neural network based multichannel speech dereverberation algorithm, in which the dereverberation level is controllable. This is realized by adding a simple floating-point number as ta…
The purpose of speech dereverberation is to remove quality-degrading effects of a time-invariant impulse response filter from the signal. In this report, we describe an approach to speech dereverberation that involves joint estimation of the dry speech signal and of the room impulse response. We explore deep learning models that apply to each task separately, and how these can be combined in a joint model with shared parameters.
Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling
School of Cyber Science and Engineering, Wuhan University（武汉大学计算机科学与工程学院）；School of Artificial Intelligence, Wuhan University（武汉大学人工智能学院）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems, Digital Innovation Research Center, Duke Kunshan University（多模态智能系统苏州市级重点实验室、杜克昆山大学数字创新研究中心）；Hardware Engineering System, OPPO（OPPO硬件工程系统）
The Ohio State University（俄亥俄州立大学）；Center for Cognitive and Brain Sciences, The Ohio State University（俄亥俄州立大学认知与脑科学中心）
This study proposes a multi-microphone complex spectral mapping approach for speech dereverberation on a fixed array geometry. In the proposed approach, a deep neural network (DNN) is trained to predict the real and imaginary (RI) components of direct sound from the stacked reverberant (and noisy) RI components of multiple microphones. We also investigate the integration of multi-microphone complex spectral mapping with beamforming and post-filtering. Experimental results on multi-channel speech dereverberation demonstrate the effectiveness of the proposed approach.
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…
Indiana University（印第安纳大学）；The Ohio State University（俄亥俄州立大学）
Dereverberation is often performed directly on the reverberant audio signal, without knowledge of the acoustic environment. Reverberation time, T60, however, is an essential acoustic factor that reflects how reverberation may impact a signal. In this work, we propose to perform dereverberation while leveraging key acoustic information from the environment. More specifically, we develop a joint learning approach that uses a composite T60 module and a separate dereverberation module to simultaneously perform reverberation time estimation and dereverberation. The reverberation time module provide…
In real life, room effect, also known as room reverberation, and the present background noise degrade the quality of speech. Recently, deep learning-based speech enhancement approaches have shown a lot of promise and surpassed traditional denoising and dereverberation methods. It is also well established that these state-of-the-art denoising algorithms significantly improve the quality of speech as perceived by human listeners. But the role of dereverberation on subjective (perceived) speech quality, and whether the additional artifacts introduced by dereverberation cause more harm than good a…
Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channel speech dereverberation. Temporal convolutional networks (TCNs) are commonly used for sequence modelling in speech enhancement tasks. A feature of TCNs is that they have a receptive field (RF) dependent on the specific model configuration which determines the number of input frames that can be observed to produce an individual output frame. It has been shown that TCNs are capable of performing dereverberation of sim…
We describe a monaural speech enhancement algorithm based on modulation-domain Kalman filtering to blindly track the time-frequency log-magnitude spectra of speech and reverberation. We propose an adaptive algorithm that performs blind joint denoising and dereverberation, while accounting for the inter-frame speech dynamics, by estimating the posterior distribution of the speech log-magnitude spectrum given the log-magnitude spectrum of the noisy reverberant speech. The Kalman filter update step models the non-linear relations between the speech, noise and reverberation log-spectra. The Kalman…
Despite successful applications of end-to-end approaches in multi-channel speech recognition, the performance still degrades severely when the speech is corrupted by reverberation. In this paper, we integrate the dereverberation module into the end-to-end multi-channel speech recognition system and explore two different frontend architectures. First, a multi-source mask-based weighted prediction error (WPE) module is incorporated in the frontend for dereverberation. Second, another novel frontend architecture is proposed, which extends the weighted power minimization distortionless response (W…
This paper presents a joint source separation algorithm that simultaneously reduces acoustic echo, reverberation and interfering sources. Target speeches are separated from the mixture by maximizing independence with respect to the other sources. It is shown that the separation process can be decomposed into cascading sub-processes that separately relate to acoustic echo cancellation, speech dereverberation and source separation, all of which are solved using the auxiliary function based independent component/vector analysis techniques, and their solving orders are exchangeable. The cascaded s…
Federal University of Technology – Paraná（巴拉那联邦技术大学）；Federal University of Santa Catarina（圣卡塔琳娜联邦大学）
The multichannel Wiener filter (MWF) and its variations have been extensively applied to binaural hearing aids. However, its major drawback is the distortion of the binaural cues of the residual noise, changing the original acoustic scenario, which is of paramount importance for hearing impaired people. The MWF-IC method was previously proposed for joint speech dereverberation and noise reduction, preserving the interaural coherence (IC) of diffuse noise fields. In this work, we propose a new variation of the MWF-IC for both speech dereverberation and noise reduction, which preserves the origi…
In this paper, we propose a multi-channel network for simultaneous speech dereverberation, enhancement and separation (DESNet). To enable gradient propagation and joint optimization, we adopt the attentional selection mechanism of the multi-channel features, which is originally proposed in end-to-end unmixing, fixed-beamforming and extraction (E2E-UFE) structure. Furthermore, the novel deep complex convolutional recurrent network (DCCRN) is used as the structure of the speech unmixing and the neural network based weighted prediction error (WPE) is cascaded beforehand for speech dereverberation…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
In this paper, we propose a single-channel speech dereverberation system (DeReGAT) based on convolutional, bidirectional long short-term memory and deep feed-forward neural network (CBLDNN) with generative adversarial training (GAT). In order to obtain better speech quality instead of only minimizing a mean square error (MSE), GAT is employed to make the dereverberated speech indistinguishable form the clean samples. Besides, our system can deal with wide range reverberation and be well adapted to variant environments. The experimental results show that the proposed model outperforms weighted …
UT Austin（德克萨斯大学奥斯汀分校）；FAIR, Meta AI（Meta人工智能基础人工智能研究院）
Reverberation not only degrades the quality of speech for human perception, but also severely impacts the accuracy of automatic speech recognition. Prior work attempts to remove reverberation based on the audio modality only. Our idea is to learn to dereverberate speech from audio-visual observations. The visual environment surrounding a human speaker reveals important cues about the room geometry, materials, and speaker location, all of which influence the precise reverberation effects. We introduce Visually-Informed Dereverberation of Audio (VIDA), an end-to-end approach that learns to remov…
In this paper, we present the Blind Speech Separation and Dereverberation (BSSD) network, which performs simultaneous speaker separation, dereverberation and speaker identification in a single neural network. Speaker separation is guided by a set of predefined spatial cues. Dereverberation is performed by using neural beamforming, and speaker identification is aided by embedding vectors and triplet mining. We introduce a frequency-domain model which uses complex-valued neural networks, and a time-domain variant which performs beamforming in latent space. Further, we propose a block-online mode…
This paper proposes a joint acoustic echo cancellation (AEC) and speech dereverberation (DR) algorithm in the short-time Fourier transform domain. The reverberant microphone signals are described using an auto-regressive (AR) model. The AR coefficients and the loudspeaker-to-microphone acoustic transfer functions (ATFs) are considered time-varying and are modeled simultaneously using a first-order Markov process. This leads to a solution where these parameters can be optimally estimated using Kalman filters. It is shown that the proposed algorithm outperforms vanilla solutions that solve AEC a…
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Southern University of Science and Technology（南方科技大学）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）；National Taiwan University（台湾大学）
Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradation of acoustic applications. Due to a complicated combination of attenuation and time-delay effects, the reverberation property is difficult to characterize, and it remains a challenging task to effectively retrieve the anechoic speech signals from reverberation ones. In the present study, we proposed a novel integrated deep and ensemble learning algorithm (IDEA) for speech dereverberation. The IDEA consists of offline and online phases. In the offline phase…
Tokyo Metropolitan University（东京都立大学）；Carnegie Mellon University（卡内基梅隆大学）；Università Politecnica delle Marche（马尔凯理工大学）
Self-supervised learning representation (SSLR) has demonstrated its significant effectiveness in automatic speech recognition (ASR), mainly with clean speech. Recent work pointed out the strength of integrating SSLR with single-channel speech enhancement for ASR in noisy environments. This paper further advances this integration by dealing with multi-channel input. We propose a novel end-to-end architecture by integrating dereverberation, beamforming, SSLR, and ASR within a single neural network. Our system achieves the best performance reported in the literature on the CHiME-4 6-channel track…
In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural network (DNN) for environment-aware speech dereverberation, which can adaptively attend to the contextual information. More specifically, a FullBand based Temporal Attention approach (FTA) is proposed, which models the correlations between the fullband information of the context frames. In addition, considering the difference between the attenuation of high …
Reverberation is damaging to both the quality and the intelligibility of a speech signal. We propose a novel single-channel method of dereverberation based on a linear filter in the Short Time Fourier Transform domain. Each enhanced frame is constructed from a linear sum of nearby frames based on the channel impulse response. The results show that the method can resolve any reverberant signal with knowledge of the impulse response to a non-reverberant signal.
Single channel speech dereverberation is considered in this work. Inspired by the recent success of Bidirectional Encoder Representations from Transformers (BERT) model in the domain of Natural Language Processing (NLP), we investigate its applicability as backbone sequence model to enhance reverberated speech signal. We present a variation of the basic BERT model: a pre-sequence network, which extracts local spectral-temporal information and/or provides order information, before the backbone sequence model. In addition, we use pre-trained neural vocoder for implicit phase reconstruction. To e…
We propose a method for joint multichannel speech dereverberation with two spatial-aware tasks: direction-of-arrival (DOA) estimation and speech separation. The proposed method addresses involved tasks as a sequence to sequence mapping problem, which is general enough for a variety of front-end speech enhancement tasks. The proposed method is inspired by the excellent sequence modeling capability of bidirectional encoder representation from transformers (BERT). Instead of utilizing explicit representations from pretraining in a self-supervised manner, we utilizes transformer encoded hidden rep…
College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）
Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitations. First, WPE doesn't consider the influence of the additive noise which degrades the performance of dereverberation. Second, it relies on a time-consuming iterative process, and there is no guarantee or a widely accepted criterion on its convergence. In this paper, we integrate deep neural network (DNN) into WPE for dereverberation and denoising. DNN is used to suppress the background noise to meet the noise-free …
Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation. Traditional approaches always treat these two features separately, ignoring their underlying relationship. In this paper, we propose Uformer, a Unet based dilated complex & real dual-path conformer network in both complex and magnitude domain for simultaneous speech enhancement and dereverberation. We exploit time attention (TA) and dilated convolution (DC) to leverage local and global contextual information and frequency attention (FA) to model dimensional information. These three su…
Speech derverberation using a single microphone is addressed in this paper. Motivated by the recent success of the fully convolutional networks (FCN) in many image processing applications, we investigate their applicability to enhance the speech signal represented by short-time Fourier transform (STFT) images. We present two variations: a "U-Net" which is an encoder-decoder network with skip connections and a generative adversarial network (GAN) with U-Net as generator, which yields a more intuitive cost function for training. To evaluate our method we used the data from the REVERB challenge, …
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…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Monaural speech dereverberation is a very challenging task because no spatial cues can be used. When the additive noises exist, this task becomes more challenging. In this paper, we propose a joint training method for simultaneous speech denoising and dereverberation using deep embedding features, which is based on the deep clustering (DC). DC is a state-of-the-art method for speech separation that includes embedding learning and K-means clustering. As for our proposed method, it contains two stages: denoising and dereverberation. At the denoising stage, the DC network is leveraged to extract …
Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息技术创新研究中心）；Mila-Quebec AI Institute（米拉-魁北克人工智能研究院）；Microsoft（微软）
Most of the deep learning-based speech enhancement models are learned in a supervised manner, which implies that pairs of noisy and clean speech are required during training. Consequently, several noisy speeches recorded in daily life cannot be used to train the model. Although certain unsupervised learning frameworks have also been proposed to solve the pair constraint, they still require clean speech or noise for training. Therefore, in this paper, we propose MetricGAN-U, which stands for MetricGAN-unsupervised, to further release the constraint from conventional unsupervised learning. In Me…
In this paper, we propose a model to perform speech dereverberation by estimating its spectral magnitude from the reverberant counterpart. Our models are capable of extracting features that take into account both short and long-term dependencies in the signal through a convolutional encoder (which extracts features from a short, bounded context of frames) and a recurrent neural network for extracting long-term information. Our model outperforms a recently proposed model that uses different context information depending on the reverberation time, without requiring any sort of additional input, …
Several speech processing systems have demonstrated considerable performance improvements when deep complex neural networks (DCNN) are coupled with self-attention (SA) networks. However, the majority of DCNN-based studies on speech dereverberation that employ self-attention do not explicitly account for the inter-dependencies between real and imaginary features when computing attention. In this study, we propose a complex-valued T-F attention (TFA) module that models spectral and temporal dependencies by computing two-dimensional attention maps across time and frequency dimensions. We validate…
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…
Seoul National University（首尔大学）；Supertone Inc.（Supertone公司）
In this work, we tackle a denoising and dereverberation problem with a single-stage framework. Although denoising and dereverberation may be considered two separate challenging tasks, and thus, two modules are typically required for each task, we show that a single deep network can be shared to solve the two problems. To this end, we propose a new masking method called phase-aware beta-sigmoid mask (PHM), which reuses the estimated magnitude values to estimate the clean phase by respecting the triangle inequality in the complex domain between three signal components such as mixture, source and…
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…
This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted Power minimization Distortionless response (WPD) beamformer can perform separation and dereverberation simultaneously, the noise cancellation component still has the potential to progress. We propose an improved neural WPD beamformer called "WPD++" by an enhanced beamforming module in the conventional WPD and a multi-objective loss function for the joint traini…
Google Research（谷歌研究院）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究所）；Skolkovo Institute of Science（斯科尔科沃科学学院（注：此处应为原文笔误，与前一机构关联））
Typically, neural network-based speech dereverberation models are trained on paired data, composed of a dry utterance and its corresponding reverberant utterance. The main limitation of this approach is that such models can only be trained on large amounts of data and a variety of room impulse responses when the data is synthetically reverberated, since acquiring real paired data is costly. In this paper we propose a CycleGAN-based approach that enables dereverberation models to be trained on unpaired data. We quantify the impact of using unpaired data by comparing the proposed unpaired model …
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…
Neural networks (NNs) have been widely applied in speech processing tasks, and, in particular, those employing microphone arrays. Nevertheless, most existing NN architectures can only deal with fixed and position-specific microphone arrays. In this paper, we present an NN architecture that can cope with microphone arrays whose number and positions of the microphones are unknown, and demonstrate its applicability in the speech dereverberation task. To this end, our approach harnesses recent advances in deep learning on set-structured data to design an architecture that enhances the reverberant …
Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning models that have been proposed for sequence modelling in the task of dereverberating speech. In this work a weighted multi-dilation depthwise-separable convolution is proposed to replace standard depthwise-separable convolutions in TCN models. This proposed convolution enables the TCN to dynamically focus on more or less local information in its receptive field at each convolution…
Unsupervised Multi-channel Speech Dereverberation via Diffusion
Department of Electrical and Computer Engineering, University of Illinois Urbana-Champaign（电气与计算机工程系，伊利诺伊大学厄巴纳-香槟分校）；Department of Computer Science and Engineering, Southern University of Science and Technology（计算机科学与工程系，南方科技大学）
In multi-microphone speech enhancement, reverberation as well as additive noise and/or interfering speech are commonly suppressed by deconvolution and spatial filtering, e.g., using multi-channel linear prediction (MCLP) on the one hand and beamforming, e.g., a generalized sidelobe canceler (GSC), on the other hand. In this paper, we consider several reverberant speech components, whereof some are to be dereverberated and others to be canceled, as well as a diffuse (e.g., babble) noise component to be suppressed. In order to perform both deconvolution and spatial filtering, we integrate MCLP a…
Newcastle University（纽卡斯尔大学）；University of Oxford（牛津大学）
Self-supervised learning (SSL) achieves great success in monaural speech enhancement, while the accuracy of the target speech estimation, particularly for unseen speakers, remains inadequate with existing pre-tasks. As speech signal contains multi-faceted information including speaker identity, paralinguistics, and spoken content, the latent representation for speech enhancement becomes a tough task. In this paper, we study the effectiveness of each feature which is commonly used in speech enhancement and exploit the feature combination in the SSL case. Besides, we propose an ensemble training…
Instituto de Investigación en Señales, Sistemas e Inteligencia Computacional, sinc(i), UNL, CONICET, FICH（信号、系统与计算智能研究所（sinc(i)），国立滨海大学，国家科学技术研究委员会，水利科学学院）；Instituto de Matemática Aplicada del Litoral, IMAL, UNL, CONICET（滨海应用数学研究所（IMAL），国立滨海大学，国家科学技术研究委员会）；Universidad Nacional del Litoral（国立滨海大学）
When recorded in an enclosed room, a sound signal will most certainly get affected by reverberation. This not only undermines audio quality, but also poses a problem for many human-machine interaction technologies that use speech as their input. In this work, a new blind, two-stage dereverberation approach based in a generalized β-divergence as a fidelity term over a non-negative representation is proposed. The first stage consists of learning the spectral structure of the signal solely from the observed spectrogram, while the second stage is devoted to model reverberation. Both steps are take…
University of Passau（帕绍大学）；Imperial College London（帝国理工学院）
This paper presents our contribution to the 3rd CHiME Speech Separation and Recognition Challenge. Our system uses Bidirectional Long Short-Term Memory (BLSTM) Recurrent Neural Networks (RNNs) for Single-channel Speech Enhancement (SSE). Networks are trained to predict clean speech as well as noise features from noisy speech features. In addition, the system applies two methods of dereverberation on the 6-channel recordings of the challenge. The first is the Phase-Error based Filtering (PEF) that uses time-varying phase-error filters based on estimated time-difference of arrival of the speech …
University of Science and Technology of China（中国科学技术大学）；National Institute of Informatics（国立信息学研究所）
This paper presents a denoising and dereverberation hierarchical neural vocoder (DNR-HiNet) to convert noisy and reverberant acoustic features into a clean speech waveform. We implement it mainly by modifying the amplitude spectrum predictor (ASP) in the original HiNet vocoder. This modified denoising and dereverberation ASP (DNR-ASP) can predict clean log amplitude spectra (LAS) from input degraded acoustic features. To achieve this, the DNR-ASP first predicts the noisy and reverberant LAS, noise LAS related to the noise information, and room impulse response related to the reverberation info…
