DeLiang Wang

Haohe Liu, Woosung Choi, Xubo Liu et al.

Speech super-resolution (SR) is a task to increase speech sampling rate by generating high-frequency components. Existing speech SR methods are trained in constrained experimental settings, such as a fixed upsampling ratio. These strong constraints can potentially lead to poor generalization ability in mismatched real-world cases. In this paper, we propose a neural vocoder based speech super-resolution method (NVSR) that can handle a variety of input resolution and upsampling ratios. NVSR consists of a mel-bandwidth extension module, a neural vocoder module, and a post-processing module. Our proposed system achieves state-of-the-art results on the VCTK multi-speaker benchmark. On 44.1 kHz target resolution, NVSR outperforms WSRGlow and Nu-wave by 8% and 37% respectively on log spectral distance and achieves a significantly better perceptual quality. We also demonstrate that prior knowledge in the pre-trained vocoder is crucial for speech SR by performing mel-bandwidth extension with a simple replication-padding method. Samples can be found in https://haoheliu.github.io/nvsr.

Haohe Liu, Qiuqiang Kong, Qiao Tian et al.

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on single-task speech restoration (SSR), such as speech denoising or speech declipping. However, SSR systems only focus on one task and do not address the general speech restoration problem. In addition, previous SSR systems show limited performance in some speech restoration tasks such as speech super-resolution. To overcome those limitations, we propose a general speech restoration (GSR) task that attempts to remove multiple distortions simultaneously. Furthermore, we propose VoiceFixer, a generative framework to address the GSR task. VoiceFixer consists of an analysis stage and a synthesis stage to mimic the speech analysis and comprehension of the human auditory system. We employ a ResUNet to model the analysis stage and a neural vocoder to model the synthesis stage. We evaluate VoiceFixer with additive noise, room reverberation, low-resolution, and clipping distortions. Our baseline GSR model achieves a 0.499 higher mean opinion score (MOS) than the speech enhancement SSR model. VoiceFixer further surpasses the GSR baseline model on the MOS score by 0.256. Moreover, we observe that VoiceFixer generalizes well to severely degraded real speech recordings, indicating its potential in restoring old movies and historical speeches. The source code is available at https://github.com/haoheliu/voicefixer_main.

Vahid Ahmadi Kalkhorani, Cheng Yu, Anurag Kumar et al.

Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal convolutional layers. Audio and visual features are fused in an early fusion layer before feeding to AV-CrossNet blocks. We evaluate AV-CrossNet on multiple datasets, including LRS, VoxCeleb, and COG-MHEAR challenge. Evaluation results demonstrate that AV-CrossNet advances the state-of-the-art performance in all audiovisual tasks, even on untrained and mismatched datasets.

Heming Wang, Yao Qian, Xiaofei Wang et al.

Noise robustness is essential for deploying automatic speech recognition (ASR) systems in real-world environments. One way to reduce the effect of noise interference is to employ a preprocessing module that conducts speech enhancement, and then feed the enhanced speech to an ASR backend. In this work, instead of suppressing background noise with a conventional cascaded pipeline, we employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We propose to combine a reconstruction module with contrastive learning and perform multi-task continual pre-training on noisy data. The reconstruction module is used for auxiliary learning to improve the noise robustness of the learned representation and thus is not required during inference. Experiments demonstrate the effectiveness of our proposed method. Our model substantially reduces the word error rate (WER) for the synthesized noisy LibriSpeech test sets, and yields around 4.1/7.5% WER reduction on noisy clean/other test sets compared to data augmentation. For the real-world noisy speech from the CHiME-4 challenge (1-channel track), we have obtained the state of the art ASR performance without any denoising front-end. Moreover, we achieve comparable performance to the best supervised approach reported with only 16% of labeled data.

Asutosh Pandey, Buye Xu, Anurag Kumar et al.

Deep neural networks are often coupled with traditional spatial filters, such as MVDR beamformers for effectively exploiting spatial information. Even though single-stage end-to-end supervised models can obtain impressive enhancement, combining them with a traditional beamformer and a DNN-based post-filter in a multistage processing provides additional improvements. In this work, we propose a two-stage strategy for multi-channel speech enhancement that does not require a traditional beamformer for additional performance. First, we propose a novel attentive dense convolutional network (ADCN) for estimating real and imaginary parts of complex spectrogram. ADCN obtains state-of-the-art results among single-stage models. Next, we use ADCN with a recently proposed triple-path attentive recurrent network (TPARN) for estimating waveform samples. The proposed strategy uses two insights; first, using different approaches in two stages; and second, using a stronger model in the first stage. We illustrate the efficacy of our strategy by evaluating multiple models in a two-stage approach with and without a traditional beamformer.

Ashutosh Pandey, Buye Xu, Anurag Kumar et al.

Deep neural networks (DNNs) are very effective for multichannel speech enhancement with fixed array geometries. However, it is not trivial to use DNNs for ad-hoc arrays with unknown order and placement of microphones. We propose a novel triple-path network for ad-hoc array processing in the time domain. The key idea in the network design is to divide the overall processing into spatial processing and temporal processing and use self-attention for spatial processing. Using self-attention for spatial processing makes the network invariant to the order and the number of microphones. The temporal processing is done independently for all channels using a recently proposed dual-path attentive recurrent network. The proposed network is a multiple-input multiple-output architecture that can simultaneously enhance signals at all microphones. Experimental results demonstrate the excellent performance of the proposed approach. Further, we present analysis to demonstrate the effectiveness of the proposed network in utilizing multichannel information even from microphones at far locations.

Ashutosh Pandey, Buye Xu, Anurag Kumar et al.

In this work, we propose a new model called triple-path attentive recurrent network (TPARN) for multichannel speech enhancement in the time domain. TPARN extends a single-channel dual-path network to a multichannel network by adding a third path along the spatial dimension. First, TPARN processes speech signals from all channels independently using a dual-path attentive recurrent network (ARN), which is a recurrent neural network (RNN) augmented with self-attention. Next, an ARN is introduced along the spatial dimension for spatial context aggregation. TPARN is designed as a multiple-input and multiple-output architecture to enhance all input channels simultaneously. Experimental results demonstrate the superiority of TPARN over existing state-of-the-art approaches.

Hassan Taherian, Ke Tan, DeLiang Wang

Permutation-invariant training (PIT) is a dominant approach for addressing the permutation ambiguity problem in talker-independent speaker separation. Leveraging spatial information afforded by microphone arrays, we propose a new training approach to resolving permutation ambiguities for multi-channel speaker separation. The proposed approach, named location-based training (LBT), assigns speakers on the basis of their spatial locations. This training strategy is easy to apply, and organizes speakers according to their positions in physical space. Specifically, this study investigates azimuth angles and source distances for location-based training. Evaluation results on separating two- and three-speaker mixtures show that azimuth-based training consistently outperforms PIT, and distance-based training further improves the separation performance when speaker azimuths are close. Furthermore, we dynamically select azimuth-based or distance-based training by estimating the azimuths of separated speakers, which further improves separation performance. LBT has a linear training complexity with respect to the number of speakers, as opposed to the factorial complexity of PIT. We further demonstrate the effectiveness of LBT for the separation of four and five concurrent speakers.

Zhong-Qiu Wang, DeLiang Wang

This study investigates robust speaker localization for con-tinuous speech separation and speaker diarization, where we use speaker directions to group non-contiguous segments of the same speaker. Assuming that speakers do not move and are located in different directions, the direction of arrival (DOA) information provides an informative cue for accurate sequential grouping and speaker diarization. Our system is block-online in the following sense. Given a block of frames with at most two speakers, we apply a two-speaker separa-tion model to separate (and enhance) the speakers, estimate the DOA of each separated speaker, and group the separation results across blocks based on the DOA estimates. Speaker diarization and speaker-attributed speech recognition results on the LibriCSS corpus demonstrate the effectiveness of the proposed algorithm.

Ashutosh Pandey, DeLiang Wang

Deep neural networks (DNNs) represent the mainstream methodology for supervised speech enhancement, primarily due to their capability to model complex functions using hierarchical representations. However, a recent study revealed that DNNs trained on a single corpus fail to generalize to untrained corpora, especially in low signal-to-noise ratio (SNR) conditions. Developing a noise, speaker, and corpus independent speech enhancement algorithm is essential for real-world applications. In this study, we propose a self-attending recurrent neural network, or attentive recurrent network (ARN), for time-domain speech enhancement to improve cross-corpus generalization. ARN comprises of recurrent neural networks (RNNs) augmented with self-attention blocks and feedforward blocks. We evaluate ARN on different corpora with nonstationary noises in low SNR conditions. Experimental results demonstrate that ARN substantially outperforms competitive approaches to time-domain speech enhancement, such as RNNs and dual-path ARNs. Additionally, we report an important finding that the two popular approaches to speech enhancement: complex spectral mapping and time-domain enhancement, obtain similar results for RNN and ARN with large-scale training. We also provide a challenging subset of the test set used in this study for evaluating future algorithms and facilitating direct comparisons.

Hao Zhang, DeLiang Wang

Building on the deep learning based acoustic echo cancellation (AEC) in the single-loudspeaker (single-channel) and single-microphone setup, this paper investigates multi-channel AEC (MCAEC) and multi-microphone AEC (MMAEC). We train a deep neural network (DNN) to predict the near-end speech from microphone signals with far-end signals used as additional information. We find that the deep learning approach avoids the non-uniqueness problem in traditional MCAEC algorithms. For the AEC setup with multiple microphones, rather than employing AEC for each microphone, a single DNN is trained to achieve echo removal for all microphones. Also, combining deep learning based AEC with deep learning based beamforming further improves the system performance. Experimental results show the effectiveness of both bidirectional long short-term memory (BLSTM) and convolutional recurrent network (CRN) based methods for MCAEC and MMAEC. Furthermore, deep learning based methods are capable of removing echo and noise simultaneously and work well in the presence of nonlinear distortions.

Yixuan Zhang, Yuzhou Liu, DeLiang Wang

Music source separation is important for applications such as karaoke and remixing. Much of previous research focuses on estimating short-time Fourier transform (STFT) magnitude and discarding phase information. We observe that, for singing voice separation, phase can make considerable improvement in separation quality. This paper proposes a complex ratio masking method for voice and accompaniment separation. The proposed method employs DenseUNet with self attention to estimate the real and imaginary components of STFT for each sound source. A simple ensemble technique is introduced to further improve separation performance. Evaluation results demonstrate that the proposed method outperforms recent state-of-the-art models for both separated voice and accompaniment.

Ashutosh Pandey, DeLiang Wang

We propose a dual-path self-attention recurrent neural network (DP-SARNN) for time-domain speech enhancement. We improve dual-path RNN (DP-RNN) by augmenting inter-chunk and intra-chunk RNN with a recently proposed efficient attention mechanism. The combination of inter-chunk and intra-chunk attention improves the attention mechanism for long sequences of speech frames. DP-SARNN outperforms a baseline DP-RNN by using a frame shift four times larger than in DP-RNN, which leads to a substantially reduced computation time per utterance. As a result, we develop a real-time DP-SARNN by using long short-term memory (LSTM) RNN and causal attention in inter-chunk SARNN. DP-SARNN significantly outperforms existing approaches to speech enhancement, and on average takes 7.9 ms CPU time to process a signal chunk of 32 ms.

Peidong Wang, Zhuo Chen, DeLiang Wang et al.

We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES contains two methods, speaker separation using speaker inventories (SSUSI) and speaker separation using estimated speech (SSUES). SSUSI performs speaker separation with the help of speaker inventory. By combining the advantages of permutation invariant training (PIT) and speech extraction, SSUSI significantly outperforms conventional approaches. SSUES is a widely applicable technique that can substantially improve speaker separation performance using the output of first-pass separation. We evaluate the models on both speaker separation and speech recognition metrics.

Zhong-Qiu Wang, Peidong Wang, DeLiang Wang

We propose multi-microphone complex spectral mapping, a simple way of applying deep learning for time-varying non-linear beamforming, for speaker separation in reverberant conditions. We aim at both speaker separation and dereverberation. Our study first investigates offline utterance-wise speaker separation and then extends to block-online continuous speech separation (CSS). Assuming a fixed array geometry between training and testing, we train deep neural networks (DNN) to predict the real and imaginary (RI) components of target speech at a reference microphone from the RI components of multiple microphones. We then integrate multi-microphone complex spectral mapping with minimum variance distortionless response (MVDR) beamforming and post-filtering to further improve separation, and combine it with frame-level speaker counting for block-online CSS. Although our system is trained on simulated room impulse responses (RIR) based on a fixed number of microphones arranged in a given geometry, it generalizes well to a real array with the same geometry. State-of-the-art separation performance is obtained on the simulated two-talker SMS-WSJ corpus and the real-recorded LibriCSS dataset.

Ashutosh Pandey, DeLiang Wang

Speech enhancement in the time domain is becoming increasingly popular in recent years, due to its capability to jointly enhance both the magnitude and the phase of speech. In this work, we propose a dense convolutional network (DCN) with self-attention for speech enhancement in the time domain. DCN is an encoder and decoder based architecture with skip connections. Each layer in the encoder and the decoder comprises a dense block and an attention module. Dense blocks and attention modules help in feature extraction using a combination of feature reuse, increased network depth, and maximum context aggregation. Furthermore, we reveal previously unknown problems with a loss based on the spectral magnitude of enhanced speech. To alleviate these problems, we propose a novel loss based on magnitudes of enhanced speech and a predicted noise. Even though the proposed loss is based on magnitudes only, a constraint imposed by noise prediction ensures that the loss enhances both magnitude and phase. Experimental results demonstrate that DCN trained with the proposed loss substantially outperforms other state-of-the-art approaches to causal and non-causal speech enhancement.

Zhong-Qiu Wang, DeLiang Wang

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.

Ashutosh Pandey, DeLiang Wang

In recent years, supervised approaches using deep neural networks (DNNs) have become the mainstream for speech enhancement. It has been established that DNNs generalize well to untrained noises and speakers if trained using a large number of noises and speakers. However, we find that DNNs fail to generalize to new speech corpora in low signal-to-noise ratio (SNR) conditions. In this work, we establish that the lack of generalization is mainly due to the channel mismatch, i.e. different recording conditions between the trained and untrained corpus. Additionally, we observe that traditional channel normalization techniques are not effective in improving cross-corpus generalization. Further, we evaluate publicly available datasets that are promising for generalization. We find one particular corpus to be significantly better than others. Finally, we find that using a smaller frame shift in short-time processing of speech can significantly improve cross-corpus generalization. The proposed techniques to address cross-corpus generalization include channel normalization, better training corpus, and smaller frame shift in short-time Fourier transform (STFT). These techniques together improve the objective intelligibility and quality scores on untrained corpora significantly.

Yuzhou Liu, DeLiang Wang

We address talker-independent monaural speaker separation from the perspectives of deep learning and computational auditory scene analysis (CASA). Specifically, we decompose the multi-speaker separation task into the stages of simultaneous grouping and sequential grouping. Simultaneous grouping is first performed in each time frame by separating the spectra of different speakers with a permutation-invariantly trained neural network. In the second stage, the frame-level separated spectra are sequentially grouped to different speakers by a clustering network. The proposed deep CASA approach optimizes frame-level separation and speaker tracking in turn, and produces excellent results for both objectives. Experimental results on the benchmark WSJ0-2mix database show that the new approach achieves the state-of-the-art results with a modest model size.

Peidong Wang, Ke Tan, DeLiang Wang

Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the distortion problem, compare different acoustic models, and investigate a distortion-independent training scheme for monaural speech recognition. Experimental results suggest that distortion-independent acoustic modeling is able to overcome the distortion problem. Such an acoustic model can also work with speech enhancement models different from the one used during training. Moreover, the models investigated in this paper outperform the previous best system on the CHiME-2 corpus.

Zhong-Qiu Wang, Ke Tan, DeLiang Wang

This study investigates phase reconstruction for deep learning based monaural talker-independent speaker separation in the short-time Fourier transform (STFT) domain. The key observation is that, for a mixture of two sources, with their magnitudes accurately estimated and under a geometric constraint, the absolute phase difference between each source and the mixture can be uniquely determined; in addition, the source phases at each time-frequency (T-F) unit can be narrowed down to only two candidates. To pick the right candidate, we propose three algorithms based on iterative phase reconstruction, group delay estimation, and phase-difference sign prediction. State-of-the-art results are obtained on the publicly available wsj0-2mix and 3mix corpus.

Zhong-Qiu Wang, Jonathan Le Roux, DeLiang Wang et al.

This paper proposes an end-to-end approach for single-channel speaker-independent multi-speaker speech separation, where time-frequency (T-F) masking, the short-time Fourier transform (STFT), and its inverse are represented as layers within a deep network. Previous approaches, rather than computing a loss on the reconstructed signal, used a surrogate loss based on the target STFT magnitudes. This ignores reconstruction error introduced by phase inconsistency. In our approach, the loss function is directly defined on the reconstructed signals, which are optimized for best separation. In addition, we train through unfolded iterations of a phase reconstruction algorithm, represented as a series of STFT and inverse STFT layers. While mask values are typically limited to lie between zero and one for approaches using the mixture phase for reconstruction, this limitation is less relevant if the estimated magnitudes are to be used together with phase reconstruction. We thus propose several novel activation functions for the output layer of the T-F masking, to allow mask values beyond one. On the publicly-available wsj0-2mix dataset, our approach achieves state-of-the-art 12.6 dB scale-invariant signal-to-distortion ratio (SI-SDR) and 13.1 dB SDR, revealing new possibilities for deep learning based phase reconstruction and representing a fundamental progress towards solving the notoriously-hard cocktail party problem.

DeLiang Wang, Jitong Chen

Speech separation is the task of separating target speech from background interference. Traditionally, speech separation is studied as a signal processing problem. A more recent approach formulates speech separation as a supervised learning problem, where the discriminative patterns of speech, speakers, and background noise are learned from training data. Over the past decade, many supervised separation algorithms have been put forward. In particular, the recent introduction of deep learning to supervised speech separation has dramatically accelerated progress and boosted separation performance. This article provides a comprehensive overview of the research on deep learning based supervised speech separation in the last several years. We first introduce the background of speech separation and the formulation of supervised separation. Then we discuss three main components of supervised separation: learning machines, training targets, and acoustic features. Much of the overview is on separation algorithms where we review monaural methods, including speech enhancement (speech-nonspeech separation), speaker separation (multi-talker separation), and speech dereverberation, as well as multi-microphone techniques. The important issue of generalization, unique to supervised learning, is discussed. This overview provides a historical perspective on how advances are made. In addition, we discuss a number of conceptual issues, including what constitutes the target source.