24 citations · 114 across the 41 of their papers we have counts for
42 papers
Exploring Energy-based Language Models with Different Architectures and Training Methods for Speech Recognition
Hong Liu, Zhaobiao Lv, Zhijian Ou +2
Energy-based language models (ELMs) parameterize an unnormalized distribution for natural sentences and are radically different from popular autoregressive language models (ALMs).…
Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
Yucheng Cai, Hong Liu, Zhijian Ou +2
Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses.…
Persistently Trained, Diffusion-assisted Energy-based Models
Xinwei Zhang, Zhiqiang Tan, Zhijian Ou
Maximum likelihood (ML) learning for energy-based models (EBMs) is challenging, partly due to non-convergence of Markov chain Monte Carlo.Several variations of ML learning have bee…
A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems
Hong Liu, Yucheng Cai, Zhijian Ou +2
Building user simulators (USs) for reinforcement learning (RL) of task-oriented dialog systems (DSs) has gained more and more attention, which, however, still faces several fundame…
Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Dataset
Hong Liu, Hao Peng, Zhijian Ou +3
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games. However, the Wizard-of-Oz data are in fact simulated da…
Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models
Yucheng Cai, Hong Liu, Zhijian Ou +2
Developing semi-supervised task-oriented dialog (TOD) systems by leveraging unlabeled dialog data has attracted increasing interests. For semi-supervised learning of latent state T…
A Challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems
Zhijian Ou, Junlan Feng, Juanzi Li +5
A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop.
Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems
Hong Liu, Yucheng Cai, Zhijian Ou +2
Recently, Transformer based pretrained language models (PLMs), such as GPT2 and T5, have been leveraged to build generative task-oriented dialog (TOD) systems. A drawback of existi…
An Empirical Study of Language Model Integration for Transducer based Speech Recognition
Huahuan Zheng, Keyu An, Zhijian Ou +3
Utilizing text-only data with an external language model (ELM) in end-to-end RNN-Transducer (RNN-T) for speech recognition is challenging. Recently, a class of methods such as dens…
CUSIDE: Chunking, Simulating Future Context and Decoding for Streaming ASR
Keyu An, Huahuan Zheng, Zhijian Ou +3
History and future contextual information are known to be important for accurate acoustic modeling. However, acquiring future context brings latency for streaming ASR. In this pape…
Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study
Keyu An, Ji Xiao, Zhijian Ou
Recently, the end-to-end training approach for multi-channel ASR has shown its effectiveness, which usually consists of a beamforming front-end and a recognition back-end. However,…
Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
Hong Liu, Yucheng Cai, Zhenru Lin +3
Recently, two approaches, fine-tuning large pre-trained language models and variational training, have attracted significant interests, separately, for semi-supervised end-to-end t…
Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers
Huahuan Zheng, Wenjie Peng, Zhijian Ou +1
Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-…
Exploiting Single-Channel Speech For Multi-channel End-to-end Speech Recognition
Keyu An, Zhijian Ou
Recently, the end-to-end training approach for neural beamformer-supported multi-channel ASR has shown its effectiveness in multi-channel speech recognition. However, the integrati…
Multilingual and crosslingual speech recognition using phonological-vector based phone embeddings
Chengrui Zhu, Keyu An, Huahuan Zheng +1
The use of phonological features (PFs) potentially allows language-specific phones to remain linked in training, which is highly desirable for information sharing for multilingual…
Deformable TDNN with adaptive receptive fields for speech recognition
Keyu An, Yi Zhang, Zhijian Ou
Time Delay Neural Networks (TDNNs) are widely used in both DNN-HMM based hybrid speech recognition systems and recent end-to-end systems. Nevertheless, the receptive fields of TDNN…
The SLT 2021 children speech recognition challenge: Open datasets, rules and baselines
Fan Yu, Zhuoyuan Yao, Xiong Wang +6
Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data. However improving robustness, including achieving equally good perfor…
Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients
Huahuan Zheng, Keyu An, Zhijian Ou
Neural Architecture Search (NAS), the process of automating architecture engineering, is an appealing next step to advancing end-to-end Automatic Speech Recognition (ASR), replacin…
An empirical study of domain-agnostic semi-supervised learning via energy-based models: joint-training and pre-training
Yunfu Song, Huahuan Zheng, Zhijian Ou
A class of recent semi-supervised learning (SSL) methods heavily rely on domain-specific data augmentations. In contrast, generative SSL methods involve unsupervised learning based…
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
Yichi Zhang, Zhijian Ou, Huixin Wang +1
Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems. However, training belief trackers often requires expensive turn-leve…
Joint Stochastic Approximation and Its Application to Learning Discrete Latent Variable Models
Zhijian Ou, Yunfu Song
Although with progress in introducing auxiliary amortized inference models, learning discrete latent variable models is still challenging. In this paper, we show that the annoying…
Paraphrase Augmented Task-Oriented Dialog Generation
Silin Gao, Yichi Zhang, Zhijian Ou +1
Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set. However, the lack of high-quality dialog data and the expensive da…
CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
Keyu An, Hongyu Xiang, Zhijian Ou
In this paper, we present a new open source toolkit for speech recognition, named CAT (CTC-CRF based ASR Toolkit). CAT inherits the data-efficiency of the hybrid approach and the s…
Integrating Discrete and Neural Features via Mixed-feature Trans-dimensional Random Field Language Models
Silin Gao, Zhijian Ou, Wei Yang +1
There has been a long recognition that discrete features (n-gram features) and neural network based features have complementary strengths for language models (LMs). Improved perfor…