Target speech separation refers to extracting the target speaker's speech from mixed signals. Despite the recent advances in deep learning based close-talk speech separation, the applications to real-world are still an open issue. Two main challenges are the complex acoustic environment and the real-time processing requirement. To address these challenges, we propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture in reverberant environments, assisted with directional information of the speaker(s). Firstly, against variations brought by complex environment, the key idea is to increase the acoustic representation completeness through the jointly modeling of temporal, spectral and spatial discriminability between the target and interference source. Specifically, temporal, spectral, spatial along with the designed directional features are integrated to create a joint acoustic representation. Secondly, to reduce the latency, we design a fully-convolutional autoencoder framework, which is purely end-to-end and single-pass. All the feature computation is implemented by the network layers and operations to speed up the separation procedure. Evaluation is conducted on simulated reverberant dataset WSJ0-2mix and WSJ0-3mix under speaker-independent scenario. Experimental results demonstrate that the proposed method outperforms state-of-the-art deep learning based multi-channel approaches with fewer parameters and faster processing speed. Furthermore, the proposed temporal-spatial neural filter can handle mixtures with varying and unknown number of speakers and exhibits persistent performance even when existing a direction estimation error. Codes and models will be released soon.
Single-channel speech separation has recently made great progress thanks to learned filterbanks as used in ConvTasNet. In parallel, parameterized filterbanks have been proposed for speaker recognition where only center frequencies and bandwidths are learned. In this work, we extend real-valued learned and parameterized filterbanks into complex-valued analytic filterbanks and define a set of corresponding representations and masking strategies. We evaluate these filterbanks on a newly released noisy speech separation dataset (WHAM). The results show that the proposed analytic learned filterbank…
In this work, we investigate if the learned encoder of the end-to-end convolutional time domain audio separation network (Conv-TasNet) is the key to its recent success, or if the encoder can just as well be replaced by a deterministic hand-crafted filterbank. Motivated by the resemblance of the trained encoder of Conv-TasNet to auditory filterbanks, we propose to employ a deterministic gammatone filterbank. In contrast to a common gammatone filterbank, our filters are restricted to 2 ms length to allow for low-latency processing. Inspired by the encoder learned by Conv-TasNet, in addition to t…
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this work, we propose a modified Mel filter bank to extract MFCCs from subsampled speech. We also propose a stronger metric which effectively captures the correlation between MFCCs of original speech and MFCC of resampled speech. It is found that the proposed method of filter bank construction performs distinguishably well and gives recognition performance on resampled speech close to recognition accuracies on original speech.
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this paper, we study the effect of resampling a speech signal on these speech features. We first derive a relationship between the MFCC param- eters of the resampled speech and the MFCC parameters of the original speech. We propose six methods of calculating the MFCC parameters of downsampled speech by transforming the Mel filter bank used to com- pute MFCC of the original speech. We then experimentally compute the MFCC parameters of the down sampled s…
Various neural network architectures have been proposed in recent years for the task of multi-channel speech separation. Among them, the filter-and-sum network (FaSNet) performs end-to-end time-domain filter-and-sum beamforming and has shown effective in both ad-hoc and fixed microphone array geometries. In this paper, we investigate multiple ways to improve the performance of FaSNet. From the problem formulation perspective, we change the explicit time-domain filter-and-sum operation which involves all the microphones into an implicit filter-and-sum operation in the latent space of only the r…
In this paper, a new speech feature fusion method is proposed for speaker recognition on the basis of the cross gate parallel convolutional neural network (CG-PCNN). The Mel filter bank features (MFBFs) of different frequency resolutions can be extracted from each speech frame of a speaker's speech by several Mel filter banks, where the numbers of the triangular filters in the Mel filter banks are different. Due to the frequency resolutions of these MFBFs are different, there are some complementaries for these MFBFs. The CG-PCNN is utilized to extract the deep features from these MFBFs, which …
EEG-informed attended speaker extraction from recorded speech mixtures with application in neuro-steered hearing prostheses
ESAT Laboratory of KU Leuven（KU莱顿大学ESAT实验室）；KU Leuven（KU莱顿大学）；Department of Electrical Engineering (ESAT)（电气工程系（ESAT））；Department of Neurosciences（神经科学系）
Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Pengcheng Laboratory（鹏城实验室）；Tencent AI Lab（腾讯AI实验室）
To date, mainstream target speech separation (TSS) approaches are formulated to estimate the complex ratio mask (cRM) of the target speech in time-frequency domain under supervised deep learning framework. However, the existing deep models for estimating cRM are designed in the way that the real and imaginary parts of the cRM are separately modeled using real-valued training data pairs. The research motivation of this study is to design a deep model that fully exploits the temporal-spectral-spatial information of multi-channel signals for estimating cRM directly and efficiently in complex doma…
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；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）
In this paper, we propose an end-to-end post-filter method with deep attention fusion features for monaural speaker-independent speech separation. At first, a time-frequency domain speech separation method is applied as the pre-separation stage. The aim of pre-separation stage is to separate the mixture preliminarily. Although this stage can separate the mixture, it still contains the residual interference. In order to enhance the pre-separated speech and improve the separation performance further, the end-to-end post-filter (E2EPF) with deep attention fusion features is proposed. The E2EPF ca…
Université de Lorraine（洛林大学）；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；LORIA（洛林计算机科学与应用研究实验室）
Most of the speech processing applications use triangular filters spaced in mel-scale for feature extraction. In this paper, we propose a new data-driven filter design method which optimizes filter parameters from a given speech data. First, we introduce a frame-selection based approach for developing speech-signal-based frequency warping scale. Then, we propose a new method for computing the filter frequency responses by using principal component analysis (PCA). The main advantage of the proposed method over the recently introduced deep learning based methods is that it requires very limited …
National School of Engineers of Tunis（突尼斯国家工程师学院）；National Institute of Applied Science and Technology（国家应用科学与技术研究所）
In this paper, we address the problem of blind separation of speech mixtures. We propose a new blind speech separation system, which integrates a perceptual filterbank and independent component analysis (ICA) and using kurtosis criterion. The perceptual filterbank was designed by adjusting undecimated wavelet packet decomposition (UWPD) tree in order to accord to critical band characteristics of psycho-acoustic model. Our proposed technique consists on transforming the observations signals into an adequate representation using UWPD and Kurtosis maximization criterion in a new preprocessing ste…
Hand-crafted spatial features (e.g., inter-channel phase difference, IPD) play a fundamental role in recent deep learning based multi-channel speech separation (MCSS) methods. However, these manually designed spatial features are hard to incorporate into the end-to-end optimized MCSS framework. In this work, we propose an integrated architecture for learning spatial features directly from the multi-channel speech waveforms within an end-to-end speech separation framework. In this architecture, time-domain filters spanning signal channels are trained to perform adaptive spatial filtering. These…
We propose Jointly trained Duration Informed Transformer (JDI-T), a feed-forward Transformer with a duration predictor jointly trained without explicit alignments in order to generate an acoustic feature sequence from an input text. In this work, inspired by the recent success of the duration informed networks such as FastSpeech and DurIAN, we further simplify its sequential, two-stage training pipeline to a single-stage training. Specifically, we extract the phoneme duration from the autoregressive Transformer on the fly during the joint training instead of pretraining the autoregressive mode…
Kyoto University（京都大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）
This paper describes multichannel speech enhancement for improving automatic speech recognition (ASR) in noisy environments. Recently, the minimum variance distortionless response (MVDR) beamforming has widely been used because it works well if the steering vector of speech and the spatial covariance matrix (SCM) of noise are given. To estimating such spatial information, conventional studies take a supervised approach that classifies each time-frequency (TF) bin into noise or speech by training a deep neural network (DNN). The performance of ASR, however, is degraded in an unknown noisy envir…
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…
A novel approach for speech segmentation is proposed, based on Multilevel Hybrid (mean/min) Filters (MHF) with the following features: An accurate transition location. Good performance in noisy environments (gaussian and impulsive noise). The proposed method is based on spectral changes, with the goal of segmenting the voice into homogeneous acoustic segments. This algorithm is being used for phoneticallysegmented speech coder, with successful results.
This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve performance and reduce run-time complexity. However, test-time model adaptation may be challenging if collecting data from the test-time speaker is not possible. To this end, we propose using an ensemble model wherein each specialist module denoises noisy utterances from a distinct partition of training set speakers. The gating module inexpensively estimates tes…
SIREM: Speech-Informed MRI Reconstruction with Learned Sampling
Pattern Recognition Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg（埃森哲-埃尔朗根-纽伦堡大学模式识别实验室）；Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔朗根大学医院放射学研究所）；Institut für Informationsverarbeitung, Leibniz Universität Hannover（汉诺威莱比锡大学信息处理研究所）；Department of Radiology, Harvard Medical School and Massachusetts General Hospital（哈佛医学院放射科和麻省总医院）
Singing voice conversion is converting the timbre in the source singing to the target speaker's voice while keeping singing content the same. However, singing data for target speaker is much more difficult to collect compared with normal speech data.In this paper, we introduce a singing voice conversion algorithm that is capable of generating high quality target speaker's singing using only his/her normal speech data. First, we manage to integrate the training and conversion process of speech and singing into one framework by unifying the features used in standard speech synthesis system and s…
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…
CentraleSupélec（巴黎中央理工-高等电力学院）；IETR UMR CNRS 6164（法国国家科学研究中心电子与电信研究所（UMR 6164））；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble-INP（格勒诺布尔国立理工学院）；GIPSA-lab（格勒诺布尔图像、语音、信号与自动化实验室）；Inria（法国国家信息与自动化研究所）；LJK（让·昆塞曼实验室）
Understanding and controlling latent representations in deep generative models is a challenging yet important problem for analyzing, transforming and generating various types of data. In speech processing, inspiring from the anatomical mechanisms of phonation, the source-filter model considers that speech signals are produced from a few independent and physically meaningful continuous latent factors, among which the fundamental frequency $f_0$ and the formants are of primary importance. In this work, we start from a variational autoencoder (VAE) trained in an unsupervised manner on a large dat…
Physics-Informed Neural Operator for Speech Production Analysis
Department of Mechanical Engineering, Nagaoka University of Technology（长冈技术科学大学机械工程系）；Schulich School of Music, McGill University（麦吉尔大学舒立克音乐学院）；Department of Electrical and Computer Engineering, University of British Columbia（不列颠哥伦比亚大学电气与计算机工程系）
This report focuses on algorithms that perform single-channel speech enhancement. The author of this report uses modulation-domain Kalman filtering algorithms for speech enhancement, i.e. noise suppression and dereverberation, in [1], [2], [3], [4] and [5]. Modulation-domain Kalman filtering can be applied for both noise and late reverberation suppression and in [2], [1], [3] and [4], various model-based speech enhancement algorithms that perform modulation-domain Kalman filtering are designed, implemented and tested. The model-based enhancement algorithm in [2] estimates and tracks the speech…
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…
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN training for speech enhancement, we design a perceptual weighting filter loss motivated by the weighting filter as it is employed in analysis-by-synthesis speech coding, e.g., in code-excited linear prediction (CELP). The experimental results show that the proposed simple loss function improves the speech enhancement performance compared to a reference DNN with MS…
Employing deep neural networks (DNNs) to directly learn filters for multi-channel speech enhancement has potentially two key advantages over a traditional approach combining a linear spatial filter with an independent tempo-spectral post-filter: 1) non-linear spatial filtering allows to overcome potential restrictions originating from a linear processing model and 2) joint processing of spatial and tempo-spectral information allows to exploit interdependencies between different sources of information. A variety of DNN-based non-linear filters have been proposed recently, for which good enhance…
Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large pitch-shift scale suffers from audio quality degradation, and speaker characteristics deformation. To address this problem, we propose a feed-forward Transformer based TTS model that is designed based on the source-filter theory. This model, called FastPitchFormant, has a unique structure that handles text and acoustic features in parallel. With modeling each fe…
The key advantage of using multiple microphones for speech enhancement is that spatial filtering can be used to complement the tempo-spectral processing. In a traditional setting, linear spatial filtering (beamforming) and single-channel post-filtering are commonly performed separately. In contrast, there is a trend towards employing deep neural networks (DNNs) to learn a joint spatial and tempo-spectral non-linear filter, which means that the restriction of a linear processing model and that of a separate processing of spatial and tempo-spectral information can potentially be overcome. Howeve…
Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient and the remainder includes background music. Even with the global style token (GST). Therefore, we propose the following method to successfully train an end-to-end TTS model with limited broadcast data. First, the background music is removed from the speech by introducing a music filter. Second, the GST-TTS model with an auxiliary quality classifier is traine…
In this paper, we present a generic and robust multimodal synthesis system that produces highly natural speech and facial expression simultaneously. The key component of this system is the Duration Informed Attention Network (DurIAN), an autoregressive model in which the alignments between the input text and the output acoustic features are inferred from a duration model. This is different from the end-to-end attention mechanism used, and accounts for various unavoidable artifacts, in existing end-to-end speech synthesis systems such as Tacotron. Furthermore, DurIAN can be used to generate hig…
In this paper, we introduce a spectral-domain inverse filtering approach for single-channel speech de-reverberation using deep convolutional neural network (CNN). The main goal is to better handle realistic reverberant conditions where the room impulse response (RIR) filter is longer than the short-time Fourier transform (STFT) analysis window. To this end, we consider the convolutive transfer function (CTF) model for the reverberant speech signal. In the proposed framework, the CNN architecture is trained to directly estimate the inverse filter of the CTF model. Among various choices for the …
University of Potsdam（波茨坦大学）；Research Focus Cognitive Science（认知科学研究中心）；Otto von Guericke University Magdeburg（奥托·冯·格里克马格德堡大学）；Artificial Intelligence Lab（人工智能实验室）
The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers. This is one reason why the internal structure of such models is very unintuitive. In neuroscience, activity of real brains can be visualized by highlighting active regions. Inspired by those techniques, we train a convolutional speech recognition model, where filters are arranged in a 2D grid and neighboring filters are similar to each other. We show, how those topographic filter maps visualize artificial neuron activations more intuitively. Moreover, we investigate, w…
University of Chinese Academy of Sciences（中国科学院大学）
Most deep learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a causal neural beam filter that fully exploits the spatial-spectral information in the beam domain. Specifically, multiple beams are designed to steer towards all directions using a parameterized super-directive beamformer in the first stage. After that, the neural spatial filter is learned by simulta…
NTT Communication Science Laboratories, NTT Corporation（NTT公司NTT通信科学实验室）
WaveCycleGAN has recently been proposed to bridge the gap between natural and synthesized speech waveforms in statistical parametric speech synthesis and provides fast inference with a moving average model rather than an autoregressive model and high-quality speech synthesis with the adversarial training. However, the human ear can still distinguish the processed speech waveforms from natural ones. One possible cause of this distinguishability is the aliasing observed in the processed speech waveform via down/up-sampling modules. To solve the aliasing and provide higher quality speech synthesi…
Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven. In this paper, by using expert knowledge from statistical signal processing for network design and optimization, we extend the conventional Kalman filtering (KF) to the supervised learning scheme, and propose the neural Kalman filtering (NKF) for speech enhancement. Two intermediate clean speech estimates are first produced from recurrent neural networks (RNN) and l…
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…
Neural-based text-to-speech (TTS) systems achieve very high-fidelity speech generation because of the rapid neural network developments. However, the huge labeled corpus and high computation cost requirements limit the possibility of developing a high-fidelity TTS system by small companies or individuals. On the other hand, a neural vocoder, which has been widely adopted for the speech generation in neural-based TTS systems, can be trained with a relatively small unlabeled corpus. Therefore, in this paper, we explore a general framework to develop a neural post-filter (NPF) for low-cost TTS sy…
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…
Nagoya Institute of Technology（名古屋工业大学）；Techno-Speech, Inc.（Techno-Speech公司）
This paper integrates a classic mel-cepstral synthesis filter into a modern neural speech synthesis system towards end-to-end controllable speech synthesis. Since the mel-cepstral synthesis filter is explicitly embedded in neural waveform models in the proposed system, both voice characteristics and the pitch of synthesized speech are highly controlled via a frequency warping parameter and fundamental frequency, respectively. We implement the mel-cepstral synthesis filter as a differentiable and GPU-friendly module to enable the acoustic and waveform models in the proposed system to be simulta…
This paper proposes a single-channel speech enhancement method to reduce the noise and enhance speech at low signal-to-noise ratio (SNR) levels and non-stationary noise conditions. Specifically, we focus on modeling the noise using a Gaussian mixture model (GMM) based on a multi-stage process with a parametric Wiener filter. The proposed noise model estimates a more accurate noise power spectral density (PSD), and allows for better generalization under various noise conditions compared to traditional Wiener filtering methods. Simulations show that the proposed approach can achieve better perfo…
The Hong Kong Polytechnic University（香港理工大学）；Peking University（北京大学）；KU Leuven（鲁汶大学）；Anhui University（安徽大学）；Northwestern University（西北大学）
Fine tuning self supervised pretrained models using pseudo labels can effectively improve speech recognition performance. But, low quality pseudo labels can misguide decision boundaries and degrade performance. We propose a simple yet effective strategy to filter low quality pseudo labels to alleviate this problem. Specifically, pseudo-labels are produced over the entire training set and filtered via average probability scores calculated from the model output. Subsequently, an optimal percentage of utterances with high probability scores are considered reliable training data with trustworthy l…
Institute of Information Science, Academia Sinica（中央研究院信息科学研究所）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院信息科技创新研究中心）
Children speech recognition is indispensable but challenging due to the diversity of children's speech. In this paper, we propose a filter-based discriminative autoencoder for acoustic modeling. To filter out the influence of various speaker types and pitches, auxiliary information of the speaker and pitch features is input into the encoder together with the acoustic features to generate phonetic embeddings. In the training phase, the decoder uses the auxiliary information and the phonetic embedding extracted by the encoder to reconstruct the input acoustic features. The autoencoder is trained…
