Models, code, and papers for "Xiaodong Cui":

Acoustic Model Optimization Based On Evolutionary Stochastic Gradient Descent with Anchors for Automatic Speech Recognition

Jul 10, 2019
Xiaodong Cui, Michael Picheny

Evolutionary stochastic gradient descent (ESGD) was proposed as a population-based approach that combines the merits of gradient-aware and gradient-free optimization algorithms for superior overall optimization performance. In this paper we investigate a variant of ESGD for optimization of acoustic models for automatic speech recognition (ASR). In this variant, we assume the existence of a well-trained acoustic model and use it as an anchor in the parent population whose good "gene" will propagate in the evolution to the offsprings. We propose an ESGD algorithm leveraging the anchor models such that it guarantees the best fitness of the population will never degrade from the anchor model. Experiments on 50-hour Broadcast News (BN50) and 300-hour Switchboard (SWB300) show that the ESGD with anchors can further improve the loss and ASR performance over the existing well-trained acoustic models.

* Interspeech 2019 

  Click for Model/Code and Paper
Embedding-Based Speaker Adaptive Training of Deep Neural Networks

Oct 17, 2017
Xiaodong Cui, Vaibhava Goel, George Saon

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker, are mapped through a control network to layer-dependent element-wise affine transformations to canonicalize the internal feature representations at the output of hidden layers of a main network. The control network for generating the speaker-dependent mappings is jointly estimated with the main network for the overall speaker adaptive acoustic modeling. Experiments on large vocabulary continuous speech recognition (LVCSR) tasks show that the proposed SAT scheme can yield superior performance over the widely-used speaker-aware training using i-vectors with speaker-adapted input features.

  Click for Model/Code and Paper
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks

Oct 16, 2018
Xiaodong Cui, Wei Zhang, Zoltán Tüske, Michael Picheny

We propose a population-based Evolutionary Stochastic Gradient Descent (ESGD) framework for optimizing deep neural networks. ESGD combines SGD and gradient-free evolutionary algorithms as complementary algorithms in one framework in which the optimization alternates between the SGD step and evolution step to improve the average fitness of the population. With a back-off strategy in the SGD step and an elitist strategy in the evolution step, it guarantees that the best fitness in the population will never degrade. In addition, individuals in the population optimized with various SGD-based optimizers using distinct hyper-parameters in the SGD step are considered as competing species in a coevolution setting such that the complementarity of the optimizers is also taken into account. The effectiveness of ESGD is demonstrated across multiple applications including speech recognition, image recognition and language modeling, using networks with a variety of deep architectures.

  Click for Model/Code and Paper
Task-Based Learning

Nov 19, 2019
Di Chen, Yada Zhu, Xiaodong Cui, Carla P. Gomes

This paper talks about task-based learning.

* This is a draft 

  Click for Model/Code and Paper
Task-Based Learning via Task-Oriented Prediction Network

Oct 17, 2019
Di Chen, Yada Zhu, Xiaodong Cui, Carla P. Gomes

Real-world applications often involve domain-specific and task-based performance objectives that are not captured by the standard machine learning metrics, such as mean squared error, mean absolute error, and cross-entropy loss, but are critical for decision making. A key challenge for direct integration of more meaningful domain and task-based evaluation criteria into an end-to-end gradient-based training process is the fact that often such performance objectives are not necessarily differentiable and may even require additional decision-making optimization processing. We propose Task-Oriented Prediction Network (TOPNet), an end-to-end learning scheme that automatically integrates task-based evaluation criteria into the learning process via a task-oriented estimator and directly learns a model with respect to the task-based goal. A major benefit of the proposed TOPNet learning scheme lies in its capability of automatically integrating non-differentiable evaluation criteria. This makes it particularly suitable for diversified and customized task-based evaluation criteria in real-world prediction tasks. We validate the performance of TOPNet on two real-world financial prediction tasks, revenue surprise forecasting and credit risk modeling. The experimental results on multiple real-world data sets demonstrate that TOPNet significantly outperforms both traditional modeling with standard losses and modeling with differentiable (relaxed) surrogate losses.

  Click for Model/Code and Paper
Large-Scale Mixed-Bandwidth Deep Neural Network Acoustic Modeling for Automatic Speech Recognition

Jul 10, 2019
Khoi-Nguyen C. Mac, Xiaodong Cui, Wei Zhang, Michael Picheny

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values for ASR system deployment. In this paper, we extensively investigate large-scale MB deep neural network acoustic modeling for ASR using 1,150 hours of WB data and 2,300 hours of NB data. We study various MB strategies including downsampling, upsampling and bandwidth extension for MB acoustic modeling and evaluate their performance on 8 diverse WB and NB test sets from various application domains. To deal with the large amounts of training data, distributed training is carried out on multiple GPUs using synchronous data parallelism.

* Interspeech 2019 

  Click for Model/Code and Paper
Decentralized Parallel Algorithm for Training Generative Adversarial Nets

Oct 28, 2019
Mingrui Liu, Youssef Mroueh, Wei Zhang, Xiaodong Cui, Tianbao Yang, Payel Das

Generative Adversarial Networks (GANs) are powerful class of generative models in the deep learning community. Current practice on large-scale GAN training~\cite{brock2018large} utilizes large models and distributed large-batch training strategies, and is implemented on deep learning frameworks (e.g., TensorFlow, PyTorch, etc.) designed in a centralized manner. In the centralized network topology, every worker needs to communicate with the central node. However, when the network bandwidth is low or network latency is high, the performance would be significantly degraded. Despite recent progress on decentralized algorithms for training deep neural networks, it remains unclear whether it is possible to train GANs in a decentralized manner. In this paper, we design a decentralized algorithm for solving a class of non-convex non-concave min-max problem with provable guarantee. Experimental results on GANs demonstrate the effectiveness of the proposed algorithm.

* Accepted by NeurIPS Smooth Games Optimization and Machine Learning Workshop: bridging game theory and deep learning, 2019 

  Click for Model/Code and Paper
Challenging the Boundaries of Speech Recognition: The MALACH Corpus

Aug 09, 2019
Michael Picheny, Zóltan Tüske, Brian Kingsbury, Kartik Audhkhasi, Xiaodong Cui, George Saon

There has been huge progress in speech recognition over the last several years. Tasks once thought extremely difficult, such as SWITCHBOARD, now approach levels of human performance. The MALACH corpus (LDC catalog LDC2012S05), a 375-Hour subset of a large archive of Holocaust testimonies collected by the Survivors of the Shoah Visual History Foundation, presents significant challenges to the speech community. The collection consists of unconstrained, natural speech filled with disfluencies, heavy accents, age-related coarticulations, un-cued speaker and language switching, and emotional speech - all still open problems for speech recognition systems. Transcription is challenging even for skilled human annotators. This paper proposes that the community place focus on the MALACH corpus to develop speech recognition systems that are more robust with respect to accents, disfluencies and emotional speech. To reduce the barrier for entry, a lexicon and training and testing setups have been created and baseline results using current deep learning technologies are presented. The metadata has just been released by LDC (LDC2019S11). It is hoped that this resource will enable the community to build on top of these baselines so that the extremely important information in these and related oral histories becomes accessible to a wider audience.

* Accepted for publication at INTERSPEECH 2019 

  Click for Model/Code and Paper
Distributed Deep Learning Strategies For Automatic Speech Recognition

Apr 10, 2019
Wei Zhang, Xiaodong Cui, Ulrich Finkler, Brian Kingsbury, George Saon, David Kung, Michael Picheny

In this paper, we propose and investigate a variety of distributed deep learning strategies for automatic speech recognition (ASR) and evaluate them with a state-of-the-art Long short-term memory (LSTM) acoustic model on the 2000-hour Switchboard (SWB2000), which is one of the most widely used datasets for ASR performance benchmark. We first investigate what are the proper hyper-parameters (e.g., learning rate) to enable the training with sufficiently large batch size without impairing the model accuracy. We then implement various distributed strategies, including Synchronous (SYNC), Asynchronous Decentralized Parallel SGD (ADPSGD) and the hybrid of the two HYBRID, to study their runtime/accuracy trade-off. We show that we can train the LSTM model using ADPSGD in 14 hours with 16 NVIDIA P100 GPUs to reach a 7.6% WER on the Hub5- 2000 Switchboard (SWB) test set and a 13.1% WER on the CallHome (CH) test set. Furthermore, we can train the model using HYBRID in 11.5 hours with 32 NVIDIA V100 GPUs without loss in accuracy.

* Published in ICASSP'19 

  Click for Model/Code and Paper
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition

Jul 10, 2019
Wei Zhang, Xiaodong Cui, Ulrich Finkler, George Saon, Abdullah Kayi, Alper Buyuktosunoglu, Brian Kingsbury, David Kung, Michael Picheny

Modern Automatic Speech Recognition (ASR) systems rely on distributed deep learning to for quick training completion. To enable efficient distributed training, it is imperative that the training algorithms can converge with a large mini-batch size. In this work, we discovered that Asynchronous Decentralized Parallel Stochastic Gradient Descent (ADPSGD) can work with much larger batch size than commonly used Synchronous SGD (SSGD) algorithm. On commonly used public SWB-300 and SWB-2000 ASR datasets, ADPSGD can converge with a batch size 3X as large as the one used in SSGD, thus enable training at a much larger scale. Further, we proposed a Hierarchical-ADPSGD (H-ADPSGD) system in which learners on the same computing node construct a super learner via a fast allreduce implementation, and super learners deploy ADPSGD algorithm among themselves. On a 64 Nvidia V100 GPU cluster connected via a 100Gb/s Ethernet network, our system is able to train SWB-2000 to reach a 7.6% WER on the Hub5-2000 Switchboard (SWB) test-set and a 13.2% WER on the Call-home (CH) test-set in 5.2 hours. To the best of our knowledge, this is the fastest ASR training system that attains this level of model accuracy for SWB-2000 task to be ever reported in the literature.


  Click for Model/Code and Paper
Dilated Recurrent Neural Networks

Nov 02, 2017
Shiyu Chang, Yang Zhang, Wei Han, Mo Yu, Xiaoxiao Guo, Wei Tan, Xiaodong Cui, Michael Witbrock, Mark Hasegawa-Johnson, Thomas S. Huang

Learning with recurrent neural networks (RNNs) on long sequences is a notoriously difficult task. There are three major challenges: 1) complex dependencies, 2) vanishing and exploding gradients, and 3) efficient parallelization. In this paper, we introduce a simple yet effective RNN connection structure, the DilatedRNN, which simultaneously tackles all of these challenges. The proposed architecture is characterized by multi-resolution dilated recurrent skip connections and can be combined flexibly with diverse RNN cells. Moreover, the DilatedRNN reduces the number of parameters needed and enhances training efficiency significantly, while matching state-of-the-art performance (even with standard RNN cells) in tasks involving very long-term dependencies. To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures. We rigorously prove the advantages of the DilatedRNN over other recurrent neural architectures. The code for our method is publicly available at

* Accepted by NIPS 2017 

  Click for Model/Code and Paper
English Conversational Telephone Speech Recognition by Humans and Machines

Mar 06, 2017
George Saon, Gakuto Kurata, Tom Sercu, Kartik Audhkhasi, Samuel Thomas, Dimitrios Dimitriadis, Xiaodong Cui, Bhuvana Ramabhadran, Michael Picheny, Lynn-Li Lim, Bergul Roomi, Phil Hall

One of the most difficult speech recognition tasks is accurate recognition of human to human communication. Advances in deep learning over the last few years have produced major speech recognition improvements on the representative Switchboard conversational corpus. Word error rates that just a few years ago were 14% have dropped to 8.0%, then 6.6% and most recently 5.8%, and are now believed to be within striking range of human performance. This then raises two issues - what IS human performance, and how far down can we still drive speech recognition error rates? A recent paper by Microsoft suggests that we have already achieved human performance. In trying to verify this statement, we performed an independent set of human performance measurements on two conversational tasks and found that human performance may be considerably better than what was earlier reported, giving the community a significantly harder goal to achieve. We also report on our own efforts in this area, presenting a set of acoustic and language modeling techniques that lowered the word error rate of our own English conversational telephone LVCSR system to the level of 5.5%/10.3% on the Switchboard/CallHome subsets of the Hub5 2000 evaluation, which - at least at the writing of this paper - is a new performance milestone (albeit not at what we measure to be human performance!). On the acoustic side, we use a score fusion of three models: one LSTM with multiple feature inputs, a second LSTM trained with speaker-adversarial multi-task learning and a third residual net (ResNet) with 25 convolutional layers and time-dilated convolutions. On the language modeling side, we use word and character LSTMs and convolutional WaveNet-style language models.

  Click for Model/Code and Paper