Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets have been relatively small compared to those used in other domains (e.g., ImageNet) and the associated evaluations have been more focused. In order to better facilitate deep learning research in Speech Enhancement, we present a noisy speech dataset (MS-SNSD) that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired. We show that increasing dataset sizes increases noise suppression performance as expected. In addition, we provide an open-source evaluation methodology to evaluate the results subjectively at scale using crowdsourcing, with a reference algorithm to normalize the results. To demonstrate the dataset and evaluation framework we apply it to several noise suppressors and compare the subjective Mean Opinion Score (MOS) with objective quality measures such as SNR, PESQ, POLQA, and VISQOL and show why MOS is still required. Our subjective MOS evaluation is the first large scale evaluation of Speech Enhancement algorithms that we are aware of.
Microsoft Corporation（微软公司）；Microsoft Research（微软研究院）
The INTERSPEECH 2020 Deep Noise Suppression Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. Many publications report reasonable performance on the synthetic test set drawn from the same distribution as that of the training set. However, often the model performance degrades significantly on real recordings. Also, most…
Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech
Delft University of Technology（代尔夫特理工大学）；Erasmus Medical Centre (EMC)（埃因霍温医学院）；Indian Inst. of Information Technology Allahabad（阿利哈巴德信息科技学院）；Dept. of Plastic and Reconstructive Surgery（整形外科与重建外科系）；Dept. of Electronics and Communication（电子与通信系）
Subjective evaluation results for two low-latency deep neural networks (DNN) are compared to a matured version of a traditional Wiener-filter based noise suppressor. The target use-case is real-world single-channel speech enhancement applications, e.g., communications. Real-world recordings consisting of additive stationary and non-stationary noise types are included. The evaluation is divided into four outcomes: speech quality, noise transparency, speech intelligibility or listening effort, and noise level w.r.t. speech. It is shown that DNNs improve noise suppression in all conditions in com…
The INTERSPEECH 2020 Deep Noise Suppression (DNS) Challenge is intended to promote collaborative research in real-time single-channel Speech Enhancement aimed to maximize the subjective (perceptual) quality of the enhanced speech. A typical approach to evaluate the noise suppression methods is to use objective metrics on the test set obtained by splitting the original dataset. While the performance is good on the synthetic test set, often the model performance degrades significantly on real recordings. Also, most of the conventional objective metrics do not correlate well with subjective tests…
MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models
Graduate School of Informatics, Nagoya University, Japan（名古屋大学信息科学研究生院，日本）；National Institute of Information and Communications Technology (NICT), Japan（日本信息通信技术研究所）；Information Technology Center, Nagoya University, Japan（名古屋大学信息技术中心，日本）
Human subjective evaluation is the gold standard to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. We have recently developed a non-intrusive speech quality metric called Deep Noise Suppression Mean Opinion Score (DNSMOS) using the scores from ITU-T Rec. P.808 subjective evaluation. The P.808 scores reflect the overall quality of the audio clip. ITU-T Rec. P.835 subjective evaluation framework gives the standalone quality scores of speech and background noise in addition to the overall quality. In this work, we train…
Human subjective evaluation is the gold standard to evaluate speech quality optimized for human perception. Perceptual objective metrics serve as a proxy for subjective scores. The conventional and widely used metrics require a reference clean speech signal, which is unavailable in real recordings. The no-reference approaches correlate poorly with human ratings and are not widely adopted in the research community. One of the biggest use cases of these perceptual objective metrics is to evaluate noise suppression algorithms. This paper introduces a multi-stage self-teaching based perceptual obj…
Carl von Ossietzky University Oldenburg（奥尔登堡大学）；Fraunhofer IDMT（弗劳恩霍夫数字媒体技术研究所）
Listening to the audio of TV broadcast signals can be challenging for hearing-impaired as well as normal-hearing listeners, especially when background sounds are prominent or too loud compared to the speech signal. This can result in a reduced satisfaction and increased listening effort of the listeners. Since the broadcast sound is usually premixed, we perform a subjective evaluation for quantifying the potential of speech enhancement systems based on audio source separation and recurrent neural networks (RNN). Recently, RNNs have shown promising results in the context of sound source separat…
Traditionally, the quality of acoustic echo cancellers is evaluated using intrusive speech quality assessment measures such as ERLE \cite{g168} and PESQ \cite{p862}, or by carrying out subjective laboratory tests. Unfortunately, the former are not well correlated with human subjective measures, while the latter are time and resource consuming to carry out. We provide a new tool for speech quality assessment for echo impairment which can be used to evaluate the performance of acoustic echo cancellers. More precisely, we develop a neural network model to evaluate call quality degradations in two…
The quality of the speech communication systems, which include noise suppression algorithms, are typically evaluated in laboratory experiments according to the ITU-T Rec. P.835, in which participants rate background noise, speech signal, and overall quality separately. This paper introduces an open-source toolkit for conducting subjective quality evaluation of noise suppressed speech in crowdsourcing. We followed the ITU-T Rec. P.835, and P.808 and highly automate the process to prevent moderator's error. To assess the validity of our evaluation method, we compared the Mean Opinion Scores (MOS…
Edinburgh Napier University（爱丁堡龙比亚大学）；University of Wolverhampton（伍尔弗汉普顿大学）；University of Stirling（斯特林大学）；Sonova AG（索诺瓦公司）
This paper presents, a first of its kind, audio-visual (AV) speech enhacement challenge in real-noisy settings. A detailed description of the AV challenge, a novel real noisy AV corpus (ASPIRE), benchmark speech enhancement task, and baseline performance results are outlined. The latter are based on training a deep neural architecture on a synthetic mixture of Grid corpus and ChiME3 noises (consisting of bus, pedestrian, cafe, and street noises) and testing on the ASPIRE corpus. Subjective evaluations of five different speech enhancement algorithms (including SEAGN, spectrum subtraction (SS) ,…
Deep learning-based speech enhancement has shown unprecedented performance in recent years. The most popular mono speech enhancement frameworks are end-to-end networks mapping the noisy mixture into an estimate of the clean speech. With growing computational power and availability of multichannel microphone recordings, prior works have aimed to incorporate spatial statistics along with spectral information to boost up performance. Despite an improvement in enhancement performance of mono output, the spatial image preservation and subjective evaluations have not gained much attention in the lit…
Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of current speech enhancement has been limited by the amount of training data. To relax this limitation, Noisy-target Training (NyTT) that utilizes noisy speech as a training target has been proposed. Although it has been experimentally shown that NyTT can train a DNN without clean speech, a detailed analysis has not been conducted and its behavior has not been unde…
The University of Tokyo（东京大学）；Sony Corporation（索尼公司）
Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in large quantity with a variety of acoustic conditions, many different speaker characteristics and for a given sampling rate (e.g., 48kHz for fullband SE). However, obtaining such clean speech data is not straightforward - especially, if only considering publicly available datasets. At the same time, a lot of material for automatic speech recognition (ASR) with the desired acoustic/speaker/sampling rate characteristics …
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…
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 acc…
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the scenarios where such systems are used. In this paper, we explore methods that enable supervised speech enhancement systems to train on real-world degraded speech data. Specifically, we propose a semi-supervised approach for speech enhancement in which we first train a modified vector-quantized variational autoencoder that solves a source separation task. We then us…
The perceptual task of speech quality assessment (SQA) is a challenging task for machines to do. Objective SQA methods that rely on the availability of the corresponding clean reference have been the primary go-to approaches for SQA. Clearly, these methods fail in real-world scenarios where the ground truth clean references are not available. In recent years, non-intrusive methods that train neural networks to predict ratings or scores have attracted much attention, but they suffer from several shortcomings such as lack of robustness, reliance on labeled data for training and so on. In this wo…
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…
Technische Universität Berlin（柏林工业大学）；Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI)（德国人工智能研究中心）
Speech communication systems based on Voice-over-IP technology are frequently used by native as well as non-native speakers of a target language, e.g. in international phone calls or telemeetings. Frequently, such calls also occur in a noisy environment, making noise suppression modules necessary to increase perceived quality of experience. Whereas standard tests for assessing perceived quality make use of native listeners, we assume that noise-reduced speech and residual noise may affect native and non-native listeners of a target language in different ways. To test this assumption, we report…
Recently, variational autoencoders have been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. However, variational autoencoders are trained on clean speech only, which results in a limited ability of extracting the speech signal from noisy speech compared to supervised approaches. In this paper, we propose to guide the variational autoencoder with a supervised classifier separately trained on noisy speech. The estimated label is a high-level categorical variable describing the speech signal (e.g. speech activity) allowing f…
National Institute of Technology, Tokuyama College（国立技术院德山高专）；NTT Media Intelligence Laboratories（NTT媒体智能实验室）；Waseda University（早稻田大学）
Improving subjective sound quality of enhanced signals is one of the most important missions in speech enhancement. For evaluating the subjective quality, several methods related to perceptually-motivated objective sound quality assessment (OSQA) have been proposed such as PESQ (perceptual evaluation of speech quality). However, direct use of such measures for training deep neural network (DNN) is not allowed in most cases because popular OSQAs are non-differentiable with respect to DNN parameters. Therefore, the previous study has proposed to approximate the score of OSQAs by an auxiliary DNN…
Southeast University（东南大学）；Centre de Recherche en Information Biomédicale Sino-français (CRIBs)（中法生物医学信息研究中心）；The 28th Research Institute of China Electronics Technology Group Corporation（中国电子科技集团公司第二十八研究所）；Univ Rennes（雷恩大学）
In traditional speech denoising tasks, clean audio signals are often used as the training target, but absolutely clean signals are collected from expensive recording equipment or in studios with the strict environments. To overcome this drawback, we propose an end-to-end self-supervised speech denoising training scheme using only noisy audio signals, named Only-Noisy Training (ONT), without extra training conditions. The proposed ONT strategy constructs training pairs only from each single noisy audio, and it contains two modules: training audio pairs generated module and speech denoising modu…
Center for Advanced Intelligence Project (AIP), RIKEN（理化学研究所先进智能项目中心）；Graduate School of Informatics, Kyoto University（京都大学信息学研究科）；National Institute of Advanced Industrial Science and Technology (AIST)（日本产业技术综合研究所）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院信息处理与通信实验室）
This paper describes the practical response- and performance-aware development of online speech enhancement for an augmented reality (AR) headset that helps a user understand conversations made in real noisy echoic environments (e.g., cocktail party). One may use a state-of-the-art blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) that works well in various environments thanks to its unsupervised nature. Its heavy computational cost, however, prevents its application to real-time processing. In contrast, a supervised beamforming method that use…
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the test-time user, a personalized speech enhancement model can be trained using self-supervised learning. One straightforward approach to model personalization is to use the target speaker's noisy recordings as pseudo-sources. Then, a pseudo denoising model learns to remove injected training noises and recover the pseudo-sources. However, this approach is volatile …
Existing deep learning-based speech denoising approaches require clean speech signals to be available for training. This paper presents a deep learning-based approach to improve speech denoising in real-world audio environments by not requiring the availability of clean speech signals in a self-supervised manner. A fully convolutional neural network is trained by using two noisy realizations of the same speech signal, one used as the input and the other as the output of the network. Extensive experimentations are conducted to show the superiority of the developed deep speech denoising approach…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）；Concordia University（康考迪亚大学）
In this paper, for real time enhancement of noisy speech, a method of threshold determination based on modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of the noisy speech and noise by an Erlang-2 PDF is presented. The proposed method is computationally much faster than the existing wavelet packet based thresholding methods. A custom thresholding function based on a combination of mu-law and semisoft thresholding functions is designed and exploited to apply the statistically derived threshold upon the PWP coefficients. The proposed custom thresholding functi…
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…
University of Sheffield（谢菲尔德大学）；Toshiba Cambridge Research Laboratory（东芝剑桥研究实验室）
In this paper, we explore an improved framework to train a monoaural neural enhancement model for robust speech recognition. The designed training framework extends the existing mixture invariant training criterion to exploit both unpaired clean speech and real noisy data. It is found that the unpaired clean speech is crucial to improve quality of separated speech from real noisy speech. The proposed method also performs remixing of processed and unprocessed signals to alleviate the processing artifacts. Experiments on the single-channel CHiME-3 real test sets show that the proposed method imp…
This paper introduces the single step time domain method named HnH-NRSE, whihc is designed for simultaneous speech intelligibility and quality improvement under noisy-reverberant conditions. In this solution, harmonic and non-harmonic elements of speech are separated by applying zero-crossing and energy criteria. An objective evaluation of the its non-stationarity degree is further used for an adaptive gain to treat masking components. No prior knowledge of speech statistics or room information is required for this technique. Additionally, two combined solutions, IRMO and IRMN, are proposed as…
Bose Corporation（博士公司）；Georgia Institute of Technology（佐治亚理工学院）
Modern speech enhancement (SE) networks typically implement noise suppression through time-frequency masking, latent representation masking, or discriminative signal prediction. In contrast, some recent works explore SE via generative speech synthesis, where the system's output is synthesized by a neural vocoder after an inherently lossy feature-denoising step. In this paper, we propose a denoising vocoder (DeVo) approach, where a vocoder accepts noisy representations and learns to directly synthesize clean speech. We leverage rich representations from self-supervised learning (SSL) speech mod…
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. …
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
This paper presents a speech enhancement method, where an adaptive threshold is statistically determined based on Gaussian modeling of Teager energy (TE) operated perceptual wavelet packet (PWP) coefficients of noisy speech. In order to obtain an enhanced speech, the threshold thus derived is applied upon the PWP coefficients by employing a Gaussian pdf dependent custom thresholding function, which is designed based on a combination of modified hard and semisoft thresholding functions. The effectiveness of the proposed method is evaluated for car and multi-talker babble noise corrupted speech …
Technische Universität Berlin（柏林工业大学）；Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI)（德国人工智能研究中心）
The ground truth used for training image, video, or speech quality prediction models is based on the Mean Opinion Scores (MOS) obtained from subjective experiments. Usually, it is necessary to conduct multiple experiments, mostly with different test participants, to obtain enough data to train quality models based on machine learning. Each of these experiments is subject to an experiment-specific bias, where the rating of the same file may be substantially different in two experiments (e.g. depending on the overall quality distribution). These different ratings for the same distortion levels c…
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…
This letter proposes a novel blind acoustic mask (BAM) designed to adaptively detect noise components and preserve target speech segments in time-domain. A robust standard deviation estimator is applied to the non-stationary noisy speech to identify noise masking elements. The main contribution of the proposed solution is the use of this noise statistics to derive an adaptive information to define and select samples with lower noise proportion. Thus, preserving speech intelligibility. Additionally, no information of the target speech and noise signals statistics is previously required to this …
Graduate School of Informatics, Kyoto University（京都大学信息学研究生院）；Center for Advanced Intelligence Project, RIKEN（理化学研究所高级智能项目中心）
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervised approach requires a very large amount of pair data for training, it is not robust against unknown environments. Another approach is to use non-negative matrix factorization (NMF) based on basis spectra trained on clean speech in advance and those adapted to noise on the fly. T…
Research Center for Information Technology Innovation, Academic Sinica（中央研究院资讯科技创新研究中心）；National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）
In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-in knowledge of a "language model", a listener may effectively suppress noise interference and retrieve the target speech signals. Accordingly, we argue that familiarity with the underlying linguistic content of spoken utterances benefits speech enhancement (SE) in noisy environments. In this study, in addition to the conventional modeling for learning the acoustic noisy-clean speech mapping, an abstract symbolic sequential modeling is incorporate…
This paper introduces a new method referred to as KISS-GEV (for Keep It Super Simple Generalized eigenvalue) beamforming. While GEV beamforming usually relies on deep neural network for estimating target and noise time-frequency masks, this method uses a signal processing approach based on the direction of arrival (DoA) of the target. This considerably reduces the amount of computations involved at test time, and works for speech enhancement in unseen conditions as there is no need to train a neural network with noisy speech. The proposed method can also be used to separate speech from a mixtu…
National Taiwan University（台湾大学）；Yuan Ze University（元智大学）；National Central University（中央大学）；Academia Sinica（中央研究院）
Cycle-consistent generative adversarial networks (CycleGAN) were successfully applied to speech enhancement (SE) tasks with unpaired noisy-clean training data. The CycleGAN SE system adopted two generators and two discriminators trained with losses from noisy-to-clean and clean-to-noisy conversions. CycleGAN showed promising results for numerous SE tasks. Herein, we investigate a potential limitation of the clean-to-noisy conversion part and propose a novel noise-informed training (NIT) approach to improve the performance of the original CycleGAN SE system. The main idea of the NIT approach is…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Adobe Research（奥多比研究院）
Supervised learning for single-channel speech enhancement requires carefully labeled training examples where the noisy mixture is input into the network and the network is trained to produce an output close to the ideal target. To relax the conditions on the training data, we consider the task of training speech enhancement networks in a self-supervised manner. We first use a limited training set of clean speech sounds and learn a latent representation by autoencoding on their magnitude spectrograms. We then autoencode on speech mixtures recorded in noisy environments and train the resulting a…
We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by using a contextual enhancement neural network that can optionally make use of different types of side inputs: (1) a reference signal of the playback audio, which is necessary for echo cancellation; (2) a noise context, which is useful for speech enhancement; and (3) an embedding vector representing the voice characteristic of the target speaker of interest, wh…
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）
In this paper, a speech enhancement method based on noise compensation performed on short time magnitude as well phase spectra is presented. Unlike the conventional geometric approach (GA) to spectral subtraction (SS), here the noise estimate to be subtracted from the noisy speech spectrum is proposed to be determined by exploiting the low frequency regions of current frame of noisy speech rather than depending only on the initial silence frames. This approach gives the capability of tracking non-stationary noise thus resulting in a non-stationary noise-driven geometric approach of spectral su…
ViVoLab（ViVo实验室）；Aragon Institute for Engineering Research (I3A)（阿拉贡工程研究所（I3A））；University of Zaragoza（萨拉戈萨大学）
This paper proposes a deep speech enhancement method which exploits the high potential of residual connections in a wide neural network architecture, a topology known as Wide Residual Network. This is supported on single dimensional convolutions computed alongside the time domain, which is a powerful approach to process contextually correlated representations through the temporal domain, such as speech feature sequences. We find the residual mechanism extremely useful for the enhancement task since the signal always has a linear shortcut and the non-linear path enhances it in several steps by …
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 two-step enhancement method based on spectral subtraction and phase spectrum compensation is presented in this paper for noisy speeches in adverse environments involving non-stationary noise and medium to low levels of SNR. The magnitude of the noisy speech spectrum is modified in the first step of the proposed method by a spectral subtraction approach, where a new noise estimation method based on the low frequency information of the noisy speech is introduced. We argue that this method of noise estimation is capable of estimating the non-stationary noise accurately. The phase spectrum of th…
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…
Acoustical mismatch among training and testing phases degrades outstandingly speech recognition results. This problem has limited the development of real-world nonspecific applications, as testing conditions are highly variant or even unpredictable during the training process. Therefore the background noise has to be removed from the noisy speech signal to increase the signal intelligibility and to reduce the listener fatigue. Enhancement techniques applied, as pre-processing stages; to the systems remarkably improve recognition results. In this paper, a novel approach is used to enhance the p…
We present a single-channel phase-sensitive speech enhancement algorithm that is based on modulation-domain Kalman filtering and on tracking the speech phase using circular statistics. With Kalman filtering, using that speech and noise are additive in the complex STFT domain, the algorithm tracks the speech log-spectrum, the noise log-spectrum and the speech phase. Joint amplitude and phase estimation of speech is performed. Given the noisy speech signal, conventional algorithms use the noisy phase for signal reconstruction approximating the speech phase with the noisy phase. In the proposed K…
Winterlight Labs（Winterlight实验室）；University of Toronto（多伦多大学）；Vector Institute for Artificial Intelligence（Vector人工智能研究所）；Li Ka Shing Knowledge Institute（李嘉诚知识研究院）；St Michael’s Hospital（圣迈克尔医院）；Surgical Safety Technologies Inc.（手术安全技术公司）
A significant number of studies apply acoustic and linguistic characteristics of human speech as prominent markers of dementia and depression. However, studies on discriminating depression from dementia are rare. Co-morbid depression is frequent in dementia and these clinical conditions share many overlapping symptoms, but the ability to distinguish between depression and dementia is essential as depression is often curable. In this work, we investigate the ability of clustering approaches in distinguishing between depression and dementia from human speech. We introduce a novel aggregated data…
This paper proposes novel algorithms for speaker embedding using subjective inter-speaker similarity based on deep neural networks (DNNs). Although conventional DNN-based speaker embedding such as a $d$-vector can be applied to multi-speaker modeling in speech synthesis, it does not correlate with the subjective inter-speaker similarity and is not necessarily appropriate speaker representation for open speakers whose speech utterances are not included in the training data. We propose two training algorithms for DNN-based speaker embedding model using an inter-speaker similarity matrix obtained…
Emotions are subjective constructs. Recent end-to-end speech emotion recognition systems are typically agnostic to the subjective nature of emotions, despite their state-of-the-art performance. In this work, we introduce an end-to-end Bayesian neural network architecture to capture the inherent subjectivity in the arousal dimension of emotional expressions. To the best of our knowledge, this work is the first to use Bayesian neural networks for speech emotion recognition. At training, the network learns a distribution of weights to capture the inherent uncertainty related to subjective arousal…
The Graduate Center, CUNY（纽约城市大学研究生中心）；Brooklyn College（布鲁克林学院）；Computer Science（计算机科学系）；Computer and Information Science（计算机与信息科学系）
Noise suppression systems generally produce output speech with compromised quality. We propose to utilize the high quality speech generation capability of neural vocoders for noise suppression. We use a neural network to predict clean mel-spectrogram features from noisy speech and then compare two neural vocoders, WaveNet and WaveGlow, for synthesizing clean speech from the predicted mel spectrogram. Both WaveNet and WaveGlow achieve better subjective and objective quality scores than the source separation model Chimera++. Further, WaveNet and WaveGlow also achieve significantly better subject…
