167 citations · 453 across the 29 of their papers we have counts for
30 papers
Adaptive Perturbation Selection for Contrastive Audio Decoding
Aaron Isidore Grace, Zhouyuan Huo, Weiran Wang
Large audio-language models (LALMs) frequently hallucinate by overriding acoustic evidence with language priors. While contrastive decoding (CD) offers training-free mitigation, ex…
Improving Speech Recognition for African American English With Audio Classification
Shefali Garg, Zhouyuan Huo, Khe Chai Sim +11
Automatic speech recognition (ASR) systems have been shown to have large quality disparities between the language varieties they are intended or expected to recognize. One way to m…
Efficient Domain Adaptation for Speech Foundation Models
Bo Li, Dongseong Hwang, Zhouyuan Huo +8
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benef…
Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion
Zhouyuan Huo, Khe Chai Sim, Bo Li +3
Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks…
JOIST: A Joint Speech and Text Streaming Model For ASR
Tara N. Sainath, Rohit Prabhavalkar, Ankur Bapna +6
We present JOIST, an algorithm to train a streaming, cascaded, encoder end-to-end (E2E) model with both speech-text paired inputs, and text-only unpaired inputs. Unlike previous wo…
Pseudo Label Is Better Than Human Label
Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo +1
State-of-the-art automatic speech recognition (ASR) systems are trained with tens of thousands of hours of labeled speech data. Human transcription is expensive and time consuming.…
Large-scale ASR Domain Adaptation using Self- and Semi-supervised Learning
Dongseong Hwang, Ananya Misra, Zhouyuan Huo +7
Self- and semi-supervised learning methods have been actively investigated to reduce labeled training data or enhance the model performance. However, the approach mostly focus on i…
Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim +5
Streaming end-to-end speech recognition models have been widely applied to mobile devices and show significant improvement in efficiency. These models are typically trained on the…
A Field Guide to Federated Optimization
Jianyu Wang, Zachary Charles, Zheng Xu +50
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy prote…
On Large-Cohort Training for Federated Learning
Zachary Charles, Zachary Garrett, Zhouyuan Huo +2
Federated learning methods typically learn a model by iteratively sampling updates from a population of clients. In this work, we explore how the number of clients sampled at each…
Privacy-Preserving Asynchronous Federated Learning Algorithms for Multi-Party Vertically Collaborative Learning
Bin Gu, An Xu, Zhouyuan Huo +2
The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in whi…
Step-Ahead Error Feedback for Distributed Training with Compressed Gradient
An Xu, Zhouyuan Huo, Heng Huang
Although the distributed machine learning methods can speed up the training of large deep neural networks, the communication cost has become the non-negligible bottleneck to constr…
Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training
An Xu, Zhouyuan Huo, Heng Huang
The communication of gradients is costly for training deep neural networks with multiple devices in computer vision applications. In particular, the growing size of deep learning m…
Faster On-Device Training Using New Federated Momentum Algorithm
Zhouyuan Huo, Qian Yang, Bin Gu +1
Mobile crowdsensing has gained significant attention in recent years and has become a critical paradigm for emerging Internet of Things applications. The sensing devices continuous…
Large Batch Training Does Not Need Warmup
Zhouyuan Huo, Bin Gu, Heng Huang
Training deep neural networks using a large batch size has shown promising results and benefits many real-world applications. However, the optimizer converges slowly at early epoch…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…
Straggler-Agnostic and Communication-Efficient Distributed Primal-Dual Algorithm for High-Dimensional Data Mining
Zhouyuan Huo, Heng Huang
Recently, reducing communication time between machines becomes the main focus of distributed data mining. Previous methods propose to make workers do more computation locally befor…
Ouroboros: On Accelerating Training of Transformer-Based Language Models
Qian Yang, Zhouyuan Huo, Wenlin Wang +2
Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently…
On the Acceleration of Deep Learning Model Parallelism with Staleness
An Xu, Zhouyuan Huo, Heng Huang
Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The ineffi…
Faster Gradient-Free Proximal Stochastic Methods for Nonconvex Nonsmooth Optimization
Feihu Huang, Bin Gu, Zhouyuan Huo +2
Proximal gradient method has been playing an important role to solve many machine learning tasks, especially for the nonsmooth problems. However, in some machine learning problems…
Ego-Downward and Ambient Video based Person Location Association
Liang Yang, Hao Jiang, Jizhong Xiao +1
Using an ego-centric camera to do localization and tracking is highly needed for urban navigation and indoor assistive system when GPS is not available or not accurate enough. The…
Training Neural Networks Using Features Replay
Zhouyuan Huo, Bin Gu, Heng Huang
Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network…
Decoupled Parallel Backpropagation with Convergence Guarantee
Zhouyuan Huo, Bin Gu, Qian Yang +1
Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way b…
Accelerated Method for Stochastic Composition Optimization with Nonsmooth Regularization
Zhouyuan Huo, Bin Gu, Ji Liu +1
Stochastic composition optimization draws much attention recently and has been successful in many emerging applications of machine learning, statistical analysis, and reinforcement…