Meng Yu

Meng Yu, Lei Sun, Jianhao Zeng et al.

Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias. This bias refers to the misalignment between the SNR of the denoising sample and its corresponding timestep during the inference phase. Specifically, during training, the SNR of a sample is strictly coupled with its timestep. However, this correspondence is disrupted during inference, leading to error accumulation and impairing the generation quality. We provide comprehensive empirical evidence and theoretical analysis to substantiate this phenomenon and propose a simple yet effective differential correction method to mitigate the SNR-t bias. Recognizing that diffusion models typically reconstruct low-frequency components before focusing on high-frequency details during the reverse denoising process, we decompose samples into various frequency components and apply differential correction to each component individually. Extensive experiments show that our approach significantly improves the generation quality of various diffusion models (IDDPM, ADM, DDIM, A-DPM, EA-DPM, EDM, PFGM++, and FLUX) on datasets of various resolutions with negligible computational overhead. The code is at https://github.com/AMAP-ML/DCW.

Xiangyan Qu, Zhenlong Yuan, Jing Tang et al. · tsinghua

Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.

Vinay Kothapally, Yong Xu, Meng Yu et al.

While current deep learning (DL)-based beamforming techniques have been proved effective in speech separation, they are often designed to process narrow-band (NB) frequencies independently which results in higher computational costs and inference times, making them unsuitable for real-world use. In this paper, we propose DL-based mel-subband spatio-temporal beamformer to perform speech separation in a car environment with reduced computation cost and inference time. As opposed to conventional subband (SB) approaches, our framework uses a mel-scale based subband selection strategy which ensures a fine-grained processing for lower frequencies where most speech formant structure is present, and coarse-grained processing for higher frequencies. In a recursive way, robust frame-level beamforming weights are determined for each speaker location/zone in a car from the estimated subband speech and noise covariance matrices. Furthermore, proposed framework also estimates and suppresses any echoes from the loudspeaker(s) by using the echo reference signals. We compare the performance of our proposed framework to several NB, SB, and full-band (FB) processing techniques in terms of speech quality and recognition metrics. Based on experimental evaluations on simulated and real-world recordings, we find that our proposed framework achieves better separation performance over all SB and FB approaches and achieves performance closer to NB processing techniques while requiring lower computing cost.

Meng Yu, Kun Zhan

Most existing graph diffusion models have significant bias problems. We observe that the forward diffusion's maximum perturbation distribution in most models deviates from the standard Gaussian distribution, while reverse sampling consistently starts from a standard Gaussian distribution, which results in a reverse-starting bias. Together with the inherent exposure bias of diffusion models, this results in degraded generation quality. This paper proposes a comprehensive approach to mitigate both biases. To mitigate reverse-starting bias, we employ a newly designed Langevin sampling algorithm to align with the forward maximum perturbation distribution, establishing a new reverse-starting point. To address the exposure bias, we introduce a score correction mechanism based on a newly defined score difference. Our approach, which requires no network modifications, is validated across multiple models, datasets, and tasks, achieving state-of-the-art results.Code is at https://github.com/kunzhan/spp

Wenfu Wang, Chenxing Li, Liqiang Zhang et al.

In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.

Meng Yu, Te Cui, Haoyang Lu et al.

Image dehazing poses significant challenges in environmental perception. Recent research mainly focus on deep learning-based methods with single modality, while they may result in severe information loss especially in dense-haze scenarios. The infrared image exhibits robustness to the haze, however, existing methods have primarily treated the infrared modality as auxiliary information, failing to fully explore its rich information in dehazing. To address this challenge, the key insight of this study is to design a visible-infrared fusion network for image dehazing. In particular, we propose a multi-scale Deep Structure Feature Extraction (DSFE) module, which incorporates the Channel-Pixel Attention Block (CPAB) to restore more spatial and marginal information within the deep structural features. Additionally, we introduce an inconsistency weighted fusion strategy to merge the two modalities by leveraging the more reliable information. To validate this, we construct a visible-infrared multimodal dataset called AirSim-VID based on the AirSim simulation platform. Extensive experiments performed on challenging real and simulated image datasets demonstrate that VIFNet can outperform many state-of-the-art competing methods. The code and dataset are available at https://github.com/mengyu212/VIFNet_dehazing.

Wanyu Zang, Yang Yu, Meng Yu

We introduce a structure-aware approach for symbolic piano accompaniment that decouples high-level planning from note-level realization. A lightweight transformer predicts an interpretable, per-measure style plan conditioned on section/phrase structure and functional harmony, and a retriever then selects and reharmonizes human-performed piano patterns from a corpus. We formulate retrieval as pattern matching under an explicit energy with terms for harmonic feasibility, structural-role compatibility, voice-leading continuity, style preferences, and repetition control. Given a structured lead sheet and optional keyword prompts, the system generates piano-accompaniment MIDI. In our experiments, transformer style-planner-guided retrieval produces diverse long-form accompaniments with strong style realization. We further analyze planner ablations and quantify inter-style isolation. Experimental results demonstrate the effectiveness of our inference-time approach for piano accompaniment generation.

Yuxin Wang, Lei Ke, Boqiang Zhang et al.

While current multimodal models can answer questions based on 2D images, they lack intrinsic 3D object perception, limiting their ability to comprehend spatial relationships and depth cues in 3D scenes. In this work, we propose N3D-VLM, a novel unified framework that seamlessly integrates native 3D object perception with 3D-aware visual reasoning, enabling both precise 3D grounding and interpretable spatial understanding. Unlike conventional end-to-end models that directly predict answers from RGB/RGB-D inputs, our approach equips the model with native 3D object perception capabilities, enabling it to directly localize objects in 3D space based on textual descriptions. Building upon accurate 3D object localization, the model further performs explicit reasoning in 3D, achieving more interpretable and structured spatial understanding. To support robust training for these capabilities, we develop a scalable data construction pipeline that leverages depth estimation to lift large-scale 2D annotations into 3D space, significantly increasing the diversity and coverage for 3D object grounding data, yielding over six times larger than the largest existing single-image 3D detection dataset. Moreover, the pipeline generates spatial question-answering datasets that target chain-of-thought (CoT) reasoning in 3D, facilitating joint training for both 3D object localization and 3D spatial reasoning. Experimental results demonstrate that our unified framework not only achieves state-of-the-art performance on 3D grounding tasks, but also consistently surpasses existing methods in 3D spatial reasoning in vision-language model.

Tianxin Xie, Wentao Lei, Guanjie Huang et al.

Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content, including virtual reality, world modeling, gaming, and filmmaking. However, existing T2AV models remain incapable of generating physically plausible sounds, primarily due to their limited understanding of physical principles. To situate current research progress, we present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to systematically evaluate the audio physics grounding capabilities of existing T2AV models. PhyAVBench comprises 1,000 groups of paired text prompts with controlled physical variables that implicitly induce sound variations, enabling a fine-grained assessment of models' sensitivity to changes in underlying acoustic conditions. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST). Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation, covering 6 major audio physics dimensions, 4 daily scenarios (music, sound effects, speech, and their mix), and 50 fine-grained test points, ranging from fundamental aspects such as sound diffraction to more complex phenomena, e.g., Helmholtz resonance. Each test point consists of multiple groups of paired prompts, where each prompt is grounded by at least 20 newly recorded or collected real-world videos, thereby minimizing the risk of data leakage during model pre-training. Both prompts and videos are iteratively refined through rigorous human-involved error correction and quality control to ensure high quality. We argue that only models with a genuine grasp of audio-related physical principles can generate physically consistent audio-visual content. We hope PhyAVBench will stimulate future progress in this critical yet largely unexplored domain.

Meng Yu, Kun Zhan

Diffusion models exhibit impressive generative capabilities but are significantly impacted by exposure bias. In this paper, we make a key observation: the energy of predicted noisy samples in the reverse process continuously declines compared to perturbed samples in the forward process. Building on this, we identify two important findings: 1) The reduction in energy follows distinct patterns in the low-frequency and high-frequency subbands; 2) The subband energy of reverse-process reconstructed samples is consistently lower than that of forward-process ones, and both are lower than the original data samples. Based on the first finding, we introduce a dynamic frequency regulation mechanism utilizing wavelet transforms, which separately adjusts the low- and high-frequency subbands. Leveraging the second insight, we derive the rigorous mathematical form of exposure bias. It is worth noting that, our method is training-free and plug-and-play, significantly improving the generative quality of various diffusion models and frameworks with negligible computational cost. The source code is available at https://github.com/kunzhan/wpp.

Yiwen Shao, Wei Liu, Jiahong Li et al.

Extending large language models (LLMs) to the speech domain has recently gained significant attention. A typical approach connects a pretrained LLM with an audio encoder through a projection module and trains the resulting model on large-scale, task-specific instruction-tuning datasets. However, curating such instruction-tuning data for specific requirements is time-consuming, and models trained in this manner often generalize poorly to unseen tasks. In this work, we first formulate that the strongest generalization of a speech-LLM is achieved when it is trained with Self-Generated Instruction-Free Tuning (SIFT), in which supervision signals are generated by a frozen LLM using textual representations of speech as input. Our proposed SIFT paradigm eliminates the need for collecting task-specific question-answer pairs and yields the theoretically best generalization to unseen tasks. Building upon this paradigm, we introduce AZeroS (Auden Zero-instruction-tuned Speech-LLM), which is trained on speech-text pairs derived from publicly available corpora, including approximately 25,000 hours of speech with ASR transcripts and 3,000 hours of speech with paralinguistic labels. Built upon Qwen2.5-7B-Instruct, the model updates only two lightweight projection modules (23.8 million parameters each), while keeping both the LLM and audio encoders frozen. Despite the minimal training cost and modest data scale, AZeroS achieves state-of-the-art performance on both semantic and paralinguistic benchmarks, including VoiceBench, AIR-Bench Foundation (Speech), and AIR-Bench Chat (Speech).

Hao Zhang, Weiwei Li, Rilin Chen et al.

Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This paper proposes a semantic voice activity detection (VAD) module as a dialogue manager (DM) to efficiently manage turn-taking in full-duplex SDS. Implemented as a lightweight (0.5B) LLM fine-tuned on full-duplex conversation data, the semantic VAD predicts four control tokens to regulate turn-switching and turn-keeping, distinguishing between intentional and unintentional barge-ins while detecting query completion for handling user pauses and hesitations. By processing input speech in short intervals, the semantic VAD enables real-time decision-making, while the core dialogue engine (CDE) is only activated for response generation, reducing computational overhead. This design allows independent DM optimization without retraining the CDE, balancing interaction accuracy and inference efficiency for scalable, next-generation full-duplex SDS.

Shu Wu, Chenxing Li, Wenfu Wang et al.

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards. However, the explicit reasoning process has yet to show significant benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs, with a focus on improving adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity dynamically. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that help the model distinguish between valid and flawed reasoning paths during training. Experimental results demonstrate that our Audio-Thinker model outperforms existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

Yufeng Yue, Meng Yu, Luojie Yang et al.

Image restoration is rather challenging in adverse weather conditions, especially when multiple degradations occur simultaneously. Blind image decomposition was proposed to tackle this issue, however, its effectiveness heavily relies on the accurate estimation of each component. Although diffusion-based models exhibit strong generative abilities in image restoration tasks, they may generate irrelevant contents when the degraded images are severely corrupted. To address these issues, we leverage physical constraints to guide the whole restoration process, where a mixed degradation model based on atmosphere scattering model is constructed. Then we formulate our Joint Conditional Diffusion Model (JCDM) by incorporating the degraded image and degradation mask to provide precise guidance. To achieve better color and detail recovery results, we further integrate a refinement network to reconstruct the restored image, where Uncertainty Estimation Block (UEB) is employed to enhance the features. Extensive experiments performed on both multi-weather and weather-specific datasets demonstrate the superiority of our method over state-of-the-art competing methods.

Xusheng Yang, Long Zhou, Wenfu Wang et al.

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme compression at 5Hz typically leads to severe intelligibility and spectral detail loss, we introduce a Transformer-based inter-frame long-term dependency module and systematically explore residual vector quantization (RVQ) depth and codebook size to identify optimal configurations. Moreover, we apply U-Codec into a large language model (LLM)-based auto-regressive TTS model, which leverages global and local hierarchical architecture to effectively capture dependencies across multi-layer tokens. We extend LLM-based TTS from 3-layer RVQ at 50Hz to 32-layer RVQ at 5Hz. Experimental results demonstrate that U-Codec improves LLM-based TTS inference speed by around 3 $\times$ over high-frame-rate codecs while maintaining similarity and naturalness. These results validate the feasibility of using highly compressed 5Hz discrete tokens for fast and high-fidelity speech synthesis.

Jiliang Hu, Wenfu Wang, Zuchao Li et al.

Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.

Meng Yu, Te Cui, Qitong Chu et al.

Reliable semantic segmentation of open environments is essential for intelligent systems, yet significant problems remain: 1) Existing RGB-T semantic segmentation models mainly rely on low-level visual features and lack high-level textual information, which struggle with accurate segmentation when categories share similar visual characteristics. 2) While SAM excels in instance-level segmentation, integrating it with thermal images and text is hindered by modality heterogeneity and computational inefficiency. To address these, we propose TASeg, a text-aware RGB-T segmentation framework by using Low-Rank Adaptation (LoRA) fine-tuning technology to adapt vision foundation models. Specifically, we propose a Dynamic Feature Fusion Module (DFFM) in the image encoder, which effectively merges features from multiple visual modalities while freezing SAM's original transformer blocks. Additionally, we incorporate CLIP-generated text embeddings in the mask decoder to enable semantic alignment, which further rectifies the classification error and improves the semantic understanding accuracy. Experimental results across diverse datasets demonstrate that our method achieves superior performance in challenging scenarios with fewer trainable parameters.

Yisu Liu, Chenxing Li, Wanqian Zhang et al.

Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control over both the content and temporal structure of the generated audio. Despite recent progress, existing methods still face inherent trade-offs among accurate temporal localization, open-vocabulary scalability, and practical efficiency. To address these challenges, we propose DegDiT, a novel dynamic event graph-guided diffusion transformer framework for open-vocabulary controllable audio generation. DegDiT encodes the events in the description as structured dynamic graphs. The nodes in each graph are designed to represent three aspects: semantic features, temporal attributes, and inter-event connections. A graph transformer is employed to integrate these nodes and produce contextualized event embeddings that serve as guidance for the diffusion model. To ensure high-quality and diverse training data, we introduce a quality-balanced data selection pipeline that combines hierarchical event annotation with multi-criteria quality scoring, resulting in a curated dataset with semantic diversity. Furthermore, we present consensus preference optimization, facilitating audio generation through consensus among multiple reward signals. Extensive experiments on AudioCondition, DESED, and AudioTime datasets demonstrate that DegDiT achieves state-of-the-art performances across a variety of objective and subjective evaluation metrics.

Ziang Long, Yunling Zheng, Meng Yu et al.

Variational auto-encoder (VAE) is an effective neural network architecture to disentangle a speech utterance into speaker identity and linguistic content latent embeddings, then generate an utterance for a target speaker from that of a source speaker. This is possible by concatenating the identity embedding of the target speaker and the content embedding of the source speaker uttering a desired sentence. In this work, we propose to improve VAE models with self-attention and structural regularization (RGSM). Specifically, we found a suitable location of VAE's decoder to add a self-attention layer for incorporating non-local information in generating a converted utterance and hiding the source speaker's identity. We applied relaxed group-wise splitting method (RGSM) to regularize network weights and remarkably enhance generalization performance. In experiments of zero-shot many-to-many voice conversion task on VCTK data set, with the self-attention layer and relaxed group-wise splitting method, our model achieves a gain of speaker classification accuracy on unseen speakers by 28.3\% while slightly improved conversion voice quality in terms of MOSNet scores. Our encouraging findings point to future research on integrating more variety of attention structures in VAE framework while controlling model size and overfitting for advancing zero-shot many-to-many voice conversions.

Brian Yan, Chunlei Zhang, Meng Yu et al.

Conversational bilingual speech encompasses three types of utterances: two purely monolingual types and one intra-sententially code-switched type. In this work, we propose a general framework to jointly model the likelihoods of the monolingual and code-switch sub-tasks that comprise bilingual speech recognition. By defining the monolingual sub-tasks with label-to-frame synchronization, our joint modeling framework can be conditionally factorized such that the final bilingual output, which may or may not be code-switched, is obtained given only monolingual information. We show that this conditionally factorized joint framework can be modeled by an end-to-end differentiable neural network. We demonstrate the efficacy of our proposed model on bilingual Mandarin-English speech recognition across both monolingual and code-switched corpora.

Vinay Kothapally, Yong Xu, Meng Yu et al.

Acoustic echo cancellation (AEC) in full-duplex communication systems eliminates acoustic feedback. However, nonlinear distortions induced by audio devices, background noise, reverberation, and double-talk reduce the efficiency of conventional AEC systems. Several hybrid AEC models were proposed to address this, which use deep learning models to suppress residual echo from standard adaptive filtering. This paper proposes deep learning-based joint AEC and beamforming model (JAECBF) building on our previous self-attentive recurrent neural network (RNN) beamformer. The proposed network consists of two modules: (i) multi-channel neural-AEC, and (ii) joint AEC-RNN beamformer with a double-talk detection (DTD) that computes time-frequency (T-F) beamforming weights. We train the proposed model in an end-to-end approach to eliminate background noise and echoes from far-end audio devices, which include nonlinear distortions. From experimental evaluations, we find the proposed network outperforms other multi-channel AEC and denoising systems in terms of speech recognition rate and overall speech quality.

Anton Ratnarajah, Shi-Xiong Zhang, Meng Yu et al.

We present a neural-network-based fast diffuse room impulse response generator (FAST-RIR) for generating room impulse responses (RIRs) for a given acoustic environment. Our FAST-RIR takes rectangular room dimensions, listener and speaker positions, and reverberation time as inputs and generates specular and diffuse reflections for a given acoustic environment. Our FAST-RIR is capable of generating RIRs for a given input reverberation time with an average error of 0.02s. We evaluate our generated RIRs in automatic speech recognition (ASR) applications using Google Speech API, Microsoft Speech API, and Kaldi tools. We show that our proposed FAST-RIR with batch size 1 is 400 times faster than a state-of-the-art diffuse acoustic simulator (DAS) on a CPU and gives similar performance to DAS in ASR experiments. Our FAST-RIR is 12 times faster than an existing GPU-based RIR generator (gpuRIR). We show that our FAST-RIR outperforms gpuRIR by 2.5% in an AMI far-field ASR benchmark.

Xiyun Li, Yong Xu, Meng Yu et al.

Recently, our proposed recurrent neural network (RNN) based all deep learning minimum variance distortionless response (ADL-MVDR) beamformer method yielded superior performance over the conventional MVDR by replacing the matrix inversion and eigenvalue decomposition with two recurrent neural networks. In this work, we present a self-attentive RNN beamformer to further improve our previous RNN-based beamformer by leveraging on the powerful modeling capability of self-attention. Temporal-spatial self-attention module is proposed to better learn the beamforming weights from the speech and noise spatial covariance matrices. The temporal self-attention module could help RNN to learn global statistics of covariance matrices. The spatial self-attention module is designed to attend on the cross-channel correlation in the covariance matrices. Furthermore, a multi-channel input with multi-speaker directional features and multi-speaker speech separation outputs (MIMO) model is developed to improve the inference efficiency. The evaluations demonstrate that our proposed MIMO self-attentive RNN beamformer improves both the automatic speech recognition (ASR) accuracy and the perceptual estimation of speech quality (PESQ) against prior arts.

Meng Yu, Chunlei Zhang, Yong Xu et al.

The objective speech quality assessment is usually conducted by comparing received speech signal with its clean reference, while human beings are capable of evaluating the speech quality without any reference, such as in the mean opinion score (MOS) tests. Non-intrusive speech quality assessment has attracted much attention recently due to the lack of access to clean reference signals for objective evaluations in real scenarios. In this paper, we propose a novel non-intrusive speech quality measurement model, MetricNet, which leverages label distribution learning and joint speech reconstruction learning to achieve significantly improved performance compared to the existing non-intrusive speech quality measurement models. We demonstrate that the proposed approach yields promisingly high correlation to the intrusive objective evaluation of speech quality on clean, noisy and processed speech data.

Helin Wang, Bo Wu, Lianwu Chen et al.

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 frequency bands and low frequency bands (high frequency bands attenuate faster than low frequency bands) in the room impulse response (RIR), we also propose a SubBand based Temporal Attention approach (STA). In order to guide the network to be more aware of the reverberant environments, we jointly optimize the dereverberation network and the reverberation time (RT60) estimator in a multi-task manner. Our experimental results indicate that the proposed method outperforms our previously proposed reverberation-time-aware DNN and the learned attention weights are fully physical consistent. We also report a preliminary yet promising dereverberation and recognition experiment on real test data.

Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe et al.

Multi-source localization is an important and challenging technique for multi-talker conversation analysis. This paper proposes a novel supervised learning method using deep neural networks to estimate the direction of arrival (DOA) of all the speakers simultaneously from the audio mixture. At the heart of the proposal is a source splitting mechanism that creates source-specific intermediate representations inside the network. This allows our model to give source-specific posteriors as the output unlike the traditional multi-label classification approach. Existing deep learning methods perform a frame level prediction, whereas our approach performs an utterance level prediction by incorporating temporal selection and averaging inside the network to avoid post-processing. We also experiment with various loss functions and show that a variant of earth mover distance (EMD) is very effective in classifying DOA at a very high resolution by modeling inter-class relationships. In addition to using the prediction error as a metric for evaluating our localization model, we also establish its potency as a frontend with automatic speech recognition (ASR) as the downstream task. We convert the estimated DOAs into a feature suitable for ASR and pass it as an additional input feature to a strong multi-channel and multi-talker speech recognition baseline. This added input feature drastically improves the ASR performance and gives a word error rate (WER) of 6.3% on the evaluation data of our simulated noisy two speaker mixtures, while the baseline which doesn't use explicit localization input has a WER of 11.5%. We also perform ASR evaluation on real recordings with the overlapped set of the MC-WSJ-AV corpus in addition to simulated mixtures.

Yong Xu, Zhuohuang Zhang, Meng Yu et al.

Although the conventional mask-based minimum variance distortionless response (MVDR) could reduce the non-linear distortion, the residual noise level of the MVDR separated speech is still high. In this paper, we propose a spatio-temporal recurrent neural network based beamformer (RNN-BF) for target speech separation. This new beamforming framework directly learns the beamforming weights from the estimated speech and noise spatial covariance matrices. Leveraging on the temporal modeling capability of RNNs, the RNN-BF could automatically accumulate the statistics of the speech and noise covariance matrices to learn the frame-level beamforming weights in a recursive way. An RNN-based generalized eigenvalue (RNN-GEV) beamformer and a more generalized RNN beamformer (GRNN-BF) are proposed. We further improve the RNN-GEV and the GRNN-BF by using layer normalization to replace the commonly used mask normalization on the covariance matrices. The proposed GRNN-BF obtains better performance against prior arts in terms of speech quality (PESQ), speech-to-noise ratio (SNR) and word error rate (WER).

Zhuohuang Zhang, Yong Xu, Meng Yu et al.

Many purely neural network based speech separation approaches have been proposed to improve objective assessment scores, but they often introduce nonlinear distortions that are harmful to modern automatic speech recognition (ASR) systems. Minimum variance distortionless response (MVDR) filters are often adopted to remove nonlinear distortions, however, conventional neural mask-based MVDR systems still result in relatively high levels of residual noise. Moreover, the matrix inverse involved in the MVDR solution is sometimes numerically unstable during joint training with neural networks. In this study, we propose a multi-channel multi-frame (MCMF) all deep learning (ADL)-MVDR approach for target speech separation, which extends our preliminary multi-channel ADL-MVDR approach. The proposed MCMF ADL-MVDR system addresses linear and nonlinear distortions. Spatio-temporal cross correlations are also fully utilized in the proposed approach. The proposed systems are evaluated using a Mandarin audio-visual corpus and are compared with several state-of-the-art approaches. Experimental results demonstrate the superiority of our proposed systems under different scenarios and across several objective evaluation metrics, including ASR performance.

Wei Xia, Chunlei Zhang, Chao Weng et al.

In this study, we investigate self-supervised representation learning for speaker verification (SV). First, we examine a simple contrastive learning approach (SimCLR) with a momentum contrastive (MoCo) learning framework, where the MoCo speaker embedding system utilizes a queue to maintain a large set of negative examples. We show that better speaker embeddings can be learned by momentum contrastive learning. Next, alternative augmentation strategies are explored to normalize extrinsic speaker variabilities of two random segments from the same speech utterance. Specifically, augmentation in the waveform largely improves the speaker representations for SV tasks. The proposed MoCo speaker embedding is further improved when a prototypical memory bank is introduced, which encourages the speaker embeddings to be closer to their assigned prototypes with an intermediate clustering step. In addition, we generalize the self-supervised framework to a semi-supervised scenario where only a small portion of the data is labeled. Comprehensive experiments on the Voxceleb dataset demonstrate that our proposed self-supervised approach achieves competitive performance compared with existing techniques, and can approach fully supervised results with partially labeled data.

Jiatong Shi, Chunlei Zhang, Chao Weng et al.

Target-speaker speech recognition aims to recognize target-speaker speech from noisy environments with background noise and interfering speakers. This work presents a joint framework that combines time-domain target-speaker speech extraction and Recurrent Neural Network Transducer (RNN-T). To stabilize the joint-training, we propose a multi-stage training strategy that pre-trains and fine-tunes each module in the system before joint-training. Meanwhile, speaker identity and speech enhancement uncertainty measures are proposed to compensate for residual noise and artifacts from the target speech extraction module. Compared to a recognizer fine-tuned with a target speech extraction model, our experiments show that adding the neural uncertainty module significantly reduces 17% relative Character Error Rate (CER) on multi-speaker signals with background noise. The multi-condition experiments indicate that our method can achieve 9% relative performance gain in the noisy condition while maintaining the performance in the clean condition.

Zhaoheng Ni, Yong Xu, Meng Yu et al.

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 training. The beamforming module is improved by utilizing the spatio-temporal correlation. A multi-objective loss, including the complex spectra domain scale-invariant signal-to-noise ratio (C-Si-SNR) and the magnitude domain mean square error (Mag-MSE), is properly designed to make multiple constraints on the enhanced speech and the desired power of the dry clean signal. Joint training is conducted to optimize the complex-valued mask estimator and the WPD++ beamformer in an end-to-end way. The results show that the proposed WPD++ outperforms several state-of-the-art beamformers on the enhanced speech quality and word error rate (WER) of ASR.

Aswin Shanmugam Subramanian, Chao Weng, Shinji Watanabe et al.

This paper proposes a new paradigm for handling far-field multi-speaker data in an end-to-end neural network manner, called directional automatic speech recognition (D-ASR), which explicitly models source speaker locations. In D-ASR, the azimuth angle of the sources with respect to the microphone array is defined as a latent variable. This angle controls the quality of separation, which in turn determines the ASR performance. All three functionalities of D-ASR: localization, separation, and recognition are connected as a single differentiable neural network and trained solely based on ASR error minimization objectives. The advantages of D-ASR over existing methods are threefold: (1) it provides explicit speaker locations, (2) it improves the explainability factor, and (3) it achieves better ASR performance as the process is more streamlined. In addition, D-ASR does not require explicit direction of arrival (DOA) supervision like existing data-driven localization models, which makes it more appropriate for realistic data. For the case of two source mixtures, D-ASR achieves an average DOA prediction error of less than three degrees. It also outperforms a strong far-field multi-speaker end-to-end system in both separation quality and ASR performance.

Daniel Michelsanti, Zheng-Hua Tan, Shi-Xiong Zhang et al.

Speech enhancement and speech separation are two related tasks, whose purpose is to extract either one or more target speech signals, respectively, from a mixture of sounds generated by several sources. Traditionally, these tasks have been tackled using signal processing and machine learning techniques applied to the available acoustic signals. Since the visual aspect of speech is essentially unaffected by the acoustic environment, visual information from the target speakers, such as lip movements and facial expressions, has also been used for speech enhancement and speech separation systems. In order to efficiently fuse acoustic and visual information, researchers have exploited the flexibility of data-driven approaches, specifically deep learning, achieving strong performance. The ceaseless proposal of a large number of techniques to extract features and fuse multimodal information has highlighted the need for an overview that comprehensively describes and discusses audio-visual speech enhancement and separation based on deep learning. In this paper, we provide a systematic survey of this research topic, focusing on the main elements that characterise the systems in the literature: acoustic features; visual features; deep learning methods; fusion techniques; training targets and objective functions. In addition, we review deep-learning-based methods for speech reconstruction from silent videos and audio-visual sound source separation for non-speech signals, since these methods can be more or less directly applied to audio-visual speech enhancement and separation. Finally, we survey commonly employed audio-visual speech datasets, given their central role in the development of data-driven approaches, and evaluation methods, because they are generally used to compare different systems and determine their performance.

Meng Yu, Xuan Ji, Bo Wu et al.

The performance of keyword spotting (KWS), measured in false alarms and false rejects, degrades significantly under the far field and noisy conditions. In this paper, we propose a multi-look neural network modeling for speech enhancement which simultaneously steers to listen to multiple sampled look directions. The multi-look enhancement is then jointly trained with KWS to form an end-to-end KWS model which integrates the enhanced signals from multiple look directions and leverages an attention mechanism to dynamically tune the model's attention to the reliable sources. We demonstrate, on our large noisy and far-field evaluation sets, that the proposed approach significantly improves the KWS performance against the baseline KWS system and a recent beamformer based multi-beam KWS system.

Yong Xu, Meng Yu, Shi-Xiong Zhang et al.

Purely neural network (NN) based speech separation and enhancement methods, although can achieve good objective scores, inevitably cause nonlinear speech distortions that are harmful for the automatic speech recognition (ASR). On the other hand, the minimum variance distortionless response (MVDR) beamformer with NN-predicted masks, although can significantly reduce speech distortions, has limited noise reduction capability. In this paper, we propose a multi-tap MVDR beamformer with complex-valued masks for speech separation and enhancement. Compared to the state-of-the-art NN-mask based MVDR beamformer, the multi-tap MVDR beamformer exploits the inter-frame correlation in addition to the inter-microphone correlation that is already utilized in prior arts. Further improvements include the replacement of the real-valued masks with the complex-valued masks and the joint training of the complex-mask NN. The evaluation on our multi-modal multi-channel target speech separation and enhancement platform demonstrates that our proposed multi-tap MVDR beamformer improves both the ASR accuracy and the perceptual speech quality against prior arts.

Rongzhi Gu, Shi-Xiong Zhang, Lianwu Chen et al.

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 filters are implemented by a 2d convolution (conv2d) layer and their parameters are optimized using a speech separation objective function in a purely data-driven fashion. Furthermore, inspired by the IPD formulation, we design a conv2d kernel to compute the inter-channel convolution differences (ICDs), which are expected to provide the spatial cues that help to distinguish the directional sources. Evaluation results on simulated multi-channel reverberant WSJ0 2-mix dataset demonstrate that our proposed ICD based MCSS model improves the overall signal-to-distortion ratio by 10.4% over the IPD based MCSS model.

Fahimeh Bahmaninezhad, Shi-Xiong Zhang, Yong Xu et al.

Speech separation refers to extracting each individual speech source in a given mixed signal. Recent advancements in speech separation and ongoing research in this area, have made these approaches as promising techniques for pre-processing of naturalistic audio streams. After incorporating deep learning techniques into speech separation, performance on these systems is improving faster. The initial solutions introduced for deep learning based speech separation analyzed the speech signals into time-frequency domain with STFT; and then encoded mixed signals were fed into a deep neural network based separator. Most recently, new methods are introduced to separate waveform of the mixed signal directly without analyzing them using STFT. Here, we introduce a unified framework to include both spectrogram and waveform separations into a single structure, while being only different in the kernel function used to encode and decode the data; where, both can achieve competitive performance. This new framework provides flexibility; in addition, depending on the characteristics of the data, or limitations of the memory and latency can set the hyper-parameters to flow in a pipeline of the framework which fits the task properly. We extend single-channel speech separation into multi-channel framework with end-to-end training of the network while optimizing the speech separation criterion (i.e., Si-SNR) directly. We emphasize on how tied kernel functions for calculating spatial features, encoder, and decoder in multi-channel framework can be effective. We simulate spatialized reverberate data for both WSJ0 and LibriSpeech corpora here, and while these two sets of data are different in the matter of size and duration, the effect of capturing shorter and longer dependencies of previous/+future samples are studied in detail. We report SDR, Si-SNR and PESQ to evaluate the performance of developed solutions.

Ke Tan, Yong Xu, Shi-Xiong Zhang et al.

Background noise, interfering speech and room reverberation frequently distort target speech in real listening environments. In this study, we address joint speech separation and dereverberation, which aims to separate target speech from background noise, interfering speech and room reverberation. In order to tackle this fundamentally difficult problem, we propose a novel multimodal network that exploits both audio and visual signals. The proposed network architecture adopts a two-stage strategy, where a separation module is employed to attenuate background noise and interfering speech in the first stage and a dereverberation module to suppress room reverberation in the second stage. The two modules are first trained separately, and then integrated for joint training, which is based on a new multi-objective loss function. Our experimental results show that the proposed multimodal network yields consistently better objective intelligibility and perceptual quality than several one-stage and two-stage baselines. We find that our network achieves a 21.10% improvement in ESTOI and a 0.79 improvement in PESQ over the unprocessed mixtures. Moreover, our network architecture does not require the knowledge of the number of speakers.

Chengzhu Yu, Heng Lu, Na Hu et al.

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 high quality facial expression which can be synchronized with generated speech with/without parallel speech and face data. To improve the efficiency of speech generation, we also propose a multi-band parallel generation strategy on top of the WaveRNN model. The proposed Multi-band WaveRNN effectively reduces the total computational complexity from 9.8 to 5.5 GFLOPS, and is able to generate audio that is 6 times faster than real time on a single CPU core. We show that DurIAN could generate highly natural speech that is on par with current state of the art end-to-end systems, while at the same time avoid word skipping/repeating errors in those systems. Finally, a simple yet effective approach for fine-grained control of expressiveness of speech and facial expression is introduced.

Fahimeh Bahmaninezhad, Jian Wu, Rongzhi Gu et al.

Speech separation has been studied widely for single-channel close-talk microphone recordings over the past few years; developed solutions are mostly in frequency-domain. Recently, a raw audio waveform separation network (TasNet) is introduced for single-channel data, with achieving high Si-SNR (scale-invariant source-to-noise ratio) and SDR (source-to-distortion ratio) comparing against the state-of-the-art solution in frequency-domain. In this study, we incorporate effective components of the TasNet into a frequency-domain separation method. We compare both for alternative scenarios. We introduce a solution for directly optimizing the separation criterion in frequency-domain networks. In addition to speech separation objective and subjective measurements, we evaluate the separation performance on a speech recognition task as well. We study the speech separation problem for far-field data (more similar to naturalistic audio streams) and develop multi-channel solutions for both frequency and time-domain separators with utilizing spectral, spatial and speaker location information. For our experiments, we simulated multi-channel spatialized reverberate WSJ0-2mix dataset. Our experimental results show that spectrogram separation can achieve competitive performance with better network design. Multi-channel framework as well is shown to improve the single-channel performance relatively up to +35.5% and +46% in terms of WER and SDR, respectively.

Rongzhi Gu, Jian Wu, Shi-Xiong Zhang et al.

The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The primary contributions of this work include 1) an integrated waveform-in waveform-out separation system in a single neural network architecture. 2) We reformulate the traditional short time Fourier transform (STFT) and inter-channel phase difference (IPD) as a function of time-domain convolution with a special kernel. 3) We further relaxed those fixed kernels to be learnable, so that the entire architecture becomes purely data-driven and can be trained from end-to-end. We demonstrate on the WSJ0 far-field speech separation task that, with the benefit of learnable spatial features, our proposed end-to-end multi-channel model significantly improved the performance of previous end-to-end single-channel method and traditional multi-channel methods.

Jian Wu, Yong Xu, Shi-Xiong Zhang et al.

This paper summarizes several follow-up contributions for improving our submitted NWPU speaker-dependent system for CHiME-5 challenge, which aims to solve the problem of multi-channel, highly-overlapped conversational speech recognition in a dinner party scenario with reverberations and non-stationary noises. We adopt a speaker-aware training method by using i-vector as the target speaker information for multi-talker speech separation. With only one unified separation model for all speakers, we achieve a 10\% absolute improvement in terms of word error rate (WER) over the previous baseline of 80.28\% on the development set by leveraging our newly proposed data processing techniques and beamforming approach. With our improved back-end acoustic model, we further reduce WER to 60.15\% which surpasses the result of our submitted CHiME-5 challenge system without applying any fusion techniques.

Jian Wu, Yong Xu, Shi-Xiong Zhang et al.

Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker extraction from monaural mixtures. The architecture generalizes the previous TasNet (time-domain speech separation network) to enable multi-modal learning and at meanwhile it extends the classical audio-visual speech separation from frequency-domain to time-domain. The main components of proposed architecture include an audio encoder, a video encoder that extracts lip embedding from video streams, a multi-modal separation network and an audio decoder. Experiments on simulated mixtures based on recently released LRS2 dataset show that our method can bring 3dB+ and 4dB+ Si-SNR improvements on two- and three-speaker cases respectively, compared to audio-only TasNet and frequency-domain audio-visual networks

Jun Wang, Jie Chen, Dan Su et al.

Speaker-aware source separation methods are promising workarounds for major difficulties such as arbitrary source permutation and unknown number of sources. However, it remains challenging to achieve satisfying performance provided a very short available target speaker utterance (anchor). Here we present a novel "deep extractor network" which creates an extractor point for the target speaker in a canonical high dimensional embedding space, and pulls together the time-frequency bins corresponding to the target speaker. The proposed model is different from prior works in that the canonical embedding space encodes knowledges of both the anchor and the mixture during an end-to-end training phase: First, embeddings for the anchor and mixture speech are separately constructed in a primary embedding space, and then combined as an input to feed-forward layers to transform to a canonical embedding space which we discover more stable than the primary one. Experimental results show that given a very short utterance, the proposed model can efficiently recover high quality target speech from a mixture, which outperforms various baseline models, with 5.2% and 6.6% relative improvements in SDR and PESQ respectively compared with a baseline oracle deep attracor model. Meanwhile, we show it can be generalized well to more than one interfering speaker.

Le Guan, Peng Liu, Xinyu Xing et al.

The rapid evolution of Internet-of-Things (IoT) technologies has led to an emerging need to make it smarter. A variety of applications now run simultaneously on an ARM-based processor. For example, devices on the edge of the Internet are provided with higher horsepower to be entrusted with storing, processing and analyzing data collected from IoT devices. This significantly improves efficiency and reduces the amount of data that needs to be transported to the cloud for data processing, analysis and storage. However, commodity OSes are prone to compromise. Once they are exploited, attackers can access the data on these devices. Since the data stored and processed on the devices can be sensitive, left untackled, this is particularly disconcerting. In this paper, we propose a new system, TrustShadow that shields legacy applications from untrusted OSes. TrustShadow takes advantage of ARM TrustZone technology and partitions resources into the secure and normal worlds. In the secure world, TrustShadow constructs a trusted execution environment for security-critical applications. This trusted environment is maintained by a lightweight runtime system that coordinates the communication between applications and the ordinary OS running in the normal world. The runtime system does not provide system services itself. Rather, it forwards requests for system services to the ordinary OS, and verifies the correctness of the responses. To demonstrate the efficiency of this design, we prototyped TrustShadow on a real chip board with ARM TrustZone support, and evaluated its performance using both microbenchmarks and real-world applications. We showed TrustShadow introduces only negligible overhead to real-world applications.