Yucheng Zhao

Yucheng Zhao, Guangting Wang, Chuanxin Tang et al.

Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Recently, Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and MLP-Mixer, started to lead new trends as they showed promising results in the ImageNet classification task. In this paper, we conduct empirical studies on these DNN structures and try to understand their respective pros and cons. To ensure a fair comparison, we first develop a unified framework called SPACH which adopts separate modules for spatial and channel processing. Our experiments under the SPACH framework reveal that all structures can achieve competitive performance at a moderate scale. However, they demonstrate distinctive behaviors when the network size scales up. Based on our findings, we propose two hybrid models using convolution and Transformer modules. The resulting Hybrid-MS-S+ model achieves 83.9% top-1 accuracy with 63M parameters and 12.3G FLOPS. It is already on par with the SOTA models with sophisticated designs. The code and models are publicly available at https://github.com/microsoft/SPACH.

Haojin Yang, Zhen Shen, Yucheng Zhao

Deep convolutional neural networks (CNN) have achieved astonishing results in a large variety of applications. However, using these models on mobile or embedded devices is difficult due to the limited memory and computation resources. Recently, the inverted residual block becomes the dominating solution for the architecture design of compact CNNs. In this work, we comprehensively investigated the existing design concepts, rethink the functional characteristics of two pointwise convolutions in the inverted residuals. We propose a novel design, called asymmetrical bottlenecks. Precisely, we adjust the first pointwise convolution dimension, enrich the information flow by feature reuse, and migrate saved computations to the second pointwise convolution. By doing so we can further improve the accuracy without increasing the computation overhead. The asymmetrical bottlenecks can be adopted as a drop-in replacement for the existing CNN blocks. We can thus create AsymmNet by easily stack those blocks according to proper depth and width conditions. Extensive experiments demonstrate that our proposed block design is more beneficial than the original inverted residual bottlenecks for mobile networks, especially useful for those ultralight CNNs within the regime of <220M MAdds. Code is available at https://github.com/Spark001/AsymmNet

Chuanxin Tang, Chong Luo, Zhiyuan Zhao et al.

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the input text using a generic text-to-speech (TTS) engine and then transform the voice to the desired voice using voice conversion (VC). A major problem of this framework is that VC is a challenging problem which usually needs a moderate amount of parallel training data to work satisfactorily. In this paper, we propose a one-stage context-aware framework to generate natural and coherent target speech without any training data of the target speaker. In particular, we manage to perform accurate zero-shot duration prediction for the inserted text. The predicted duration is used to regulate both text embedding and speech embedding. Then, based on the aligned cross-modality input, we directly generate the mel-spectrogram of the edited speech with a transformer-based decoder. Subjective listening tests show that despite the lack of training data for the speaker, our method has achieved satisfactory results. It outperforms a recent zero-shot TTS engine by a large margin.

Yucheng Zhao, Guangting Wang, Chong Luo et al.

Advanced self-supervised visual representation learning methods rely on the instance discrimination (ID) pretext task. We point out that the ID task has an implicit semantic consistency (SC) assumption, which may not hold in unconstrained datasets. In this paper, we propose a novel contrastive mask prediction (CMP) task for visual representation learning and design a mask contrast (MaskCo) framework to implement the idea. MaskCo contrasts region-level features instead of view-level features, which makes it possible to identify the positive sample without any assumptions. To solve the domain gap between masked and unmasked features, we design a dedicated mask prediction head in MaskCo. This module is shown to be the key to the success of the CMP. We evaluated MaskCo on training datasets beyond ImageNet and compare its performance with MoCo V2. Results show that MaskCo achieves comparable performance with MoCo V2 using ImageNet training dataset, but demonstrates a stronger performance across a range of downstream tasks when COCO or Conceptual Captions are used for training. MaskCo provides a promising alternative to the ID-based methods for self-supervised learning in the wild.

Yucheng Zhao, Dacheng Yin, Chong Luo et al.

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning approaches to capture fine-grained information at small time scales and use discriminative learning approaches to distill coarse-grained or semantic information at large time scales. For phoneme-scale learning, we borrow idea from the masked language model but tailor it for the continuous speech signal by replacing classification loss with a contrastive loss. We corroborate our design by evaluating MGF representation on various downstream tasks, including phoneme classification, speaker classification, speech recognition, and emotion classification. Experiments verify that training at different time scales needs different training targets and loss functions, which in general complement each other and lead to a better performance.

Xiang Li, Yucheng Zhao, Chong Luo et al.

In this paper, we propose an online speaker diarization system based on Relation Network, named RenoSD. Unlike conventional diariztion systems which consist of several independently-optimized modules, RenoSD implements voice-activity-detection (VAD), embedding extraction, and speaker identity association using a single deep neural network. The most striking feature of RenoSD is that it adopts a meta-learning strategy for speaker identity association. In particular, the relation network learns to learn a deep distance metric in a data-driven way and it can determine through a simple forward pass whether two given segments belong to the same speaker. As such, RenoSD can be performed in an online manner with low latency. Experimental results on AMI and CALLHOME datasets show that the proposed RenoSD system achieves consistent improvements over the state-of-the-art x-vector baseline. Compared with an existing online diarization system named UIS-RNN, RenoSD achieves a better performance using much fewer training data and at a lower time complexity.