Heming Wang

Muqiao Yang, Chunlei Zhang, Yong Xu et al. · cmu

Speech enhancement aims to improve the quality of speech signals in terms of quality and intelligibility, and speech editing refers to the process of editing the speech according to specific user needs. In this paper, we propose a Unified Speech Enhancement and Editing (uSee) model with conditional diffusion models to handle various tasks at the same time in a generative manner. Specifically, by providing multiple types of conditions including self-supervised learning embeddings and proper text prompts to the score-based diffusion model, we can enable controllable generation of the unified speech enhancement and editing model to perform corresponding actions on the source speech. Our experiments show that our proposed uSee model can achieve superior performance in both speech denoising and dereverberation compared to other related generative speech enhancement models, and can perform speech editing given desired environmental sound text description, signal-to-noise ratios (SNR), and room impulse responses (RIR). Demos of the generated speech are available at https://muqiaoy.github.io/usee.

Leying Zhang, Yao Qian, Linfeng Yu et al.

Diffusion models have gained attention in speech enhancement tasks, providing an alternative to conventional discriminative methods. However, research on target speech extraction under multi-speaker noisy conditions remains relatively unexplored. Moreover, the superior quality of diffusion methods typically comes at the cost of slower inference speed. In this paper, we introduce the Discriminative Diffusion model for Target Speech Extraction (DDTSE). We apply the same forward process as diffusion models and utilize the reconstruction loss similar to discriminative methods. Furthermore, we devise a two-stage training strategy to emulate the inference process during model training. DDTSE not only works as a standalone system, but also can further improve the performance of discriminative models without additional retraining. Experimental results demonstrate that DDTSE not only achieves higher perceptual quality but also accelerates the inference process by 3 times compared to the conventional diffusion model.

Manuel Ballester, Heming Wang, Jiren Li et al.

We present a novel single-shot interferometric ToF camera targeted for precise 3D measurements of dynamic objects. The camera concept is based on Synthetic Wavelength Interferometry, a technique that allows retrieval of depth maps of objects with optically rough surfaces at submillimeter depth precision. In contrast to conventional ToF cameras, our device uses only off-the-shelf CCD/CMOS detectors and works at their native chip resolution (as of today, theoretically up to 20 Mp and beyond). Moreover, we can obtain a full 3D model of the object in single-shot, meaning that no temporal sequence of exposures or temporal illumination modulation (such as amplitude or frequency modulation) is necessary, which makes our camera robust against object motion. In this paper, we introduce the novel camera concept and show first measurements that demonstrate the capabilities of our system. We present 3D measurements of small (cm-sized) objects with > 2 Mp point cloud resolution (the resolution of our used detector) and up to sub-mm depth precision. We also report a "single-shot 3D video" acquisition and a first single-shot "Non-Line-of-Sight" measurement. Our technique has great potential for high-precision applications with dynamic object movement, e.g., in AR/VR, industrial inspection, medical imaging, and imaging through scattering media like fog or human tissue.

Jiarui Cao, Zhiyang Zhang, Heming Wang et al.

Nowadays, the nanostructure inverse problem is an attractive problem that helps researchers to understand the relationship between the properties and the structure of nanomaterials. This article focuses on the problem of using PDF to recover the nanostructure, which this article views as a conditional generation problem. This article propose a deep learning model CbLDM, Condition-based Latent Diffusion Model. Based on the original latent diffusion model, the sampling steps of the diffusion model are reduced and the sample generation efficiency is improved by using the conditional prior to estimate conditional posterior distribution, which is the approximated distribution of p(z|x). In addition, this article uses the Laplacian matrix instead of the distance matrix to recover the nanostructure, which can reduce the reconstruction error. Finally, this article compares CbLDM with existing models which were used to solve the nanostructure inverse problem, and find that CbLDM demonstrates significantly higher prediction accuracy than these models, which reflects the ability of CbLDM to solve the nanostructure inverse problem and the potential to cope with other continuous conditional generation tasks.

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.

Yiming Wang, Jinyu Li, Heming Wang et al.

The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider noise robustness which is crucial for real-world applications. In this paper we propose wav2vec-Switch, a method to encode noise robustness into contextualized representations of speech via contrastive learning. Specifically, we feed original-noisy speech pairs simultaneously into the wav2vec 2.0 network. In addition to the existing contrastive learning task, we switch the quantized representations of the original and noisy speech as additional prediction targets of each other. By doing this, it enforces the network to have consistent predictions for the original and noisy speech, thus allows to learn contextualized representation with noise robustness. Our experiments on synthesized and real noisy data show the effectiveness of our method: it achieves 2.9--4.9% relative word error rate (WER) reduction on the synthesized noisy LibriSpeech data without deterioration on the original data, and 5.7% on CHiME-4 real 1-channel noisy data compared to a data augmentation baseline even with a strong language model for decoding. Our results on CHiME-4 can match or even surpass those with well-designed speech enhancement components.