Zhijian Ou

CAT. CAT is more than a CRF-based ASR toolkit: it provides a complete workflow for data-efficient end-to-end ASR, supporting CTC, CTC-CRF, RNN-T, and language-model training and inference.

ASR-Benchmarks. An effort to track benchmarking results over widely-used datasets for ASR.

damd-multiwoz. Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context, AAAI 2020.

LABES. Yichi Zhang et al. A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning. EMNLP 2020.

RAG-CoT. Code for "An Empirical Study of Retrieval Augmented Generation with Chain-of-Thought"

ST-NAS. Efficient Neural Architecture Search via Straight-Through Gradients

SPMILM. A SPMI Lab toolkit for language models.

PPT2DST. Python

CTC-TTS. Code for CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment, Interspeech 2026.

PARG. Paraphrase Augmented Task-Oriented Dialog Generation, ACL 2020

GUS. A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems. EMNLP 2022 SereTOD Workshop.

MGA. Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems. SLT 2022.

Awesome-speech-and-language-processing-papers.

semi-EBM. Python

VLS-GPT. Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog System

SPMIArray. Tsinghua University SPMI Lab array processing toolkit

seq2seq-JAE. Semi-supervised Seq2seq Joint-stochastic-approximation Autoencoders with Applications to Semantic Parsing, SPL 2019.

DASI. Python

Entriever. Code for "Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems" (ACL2025 findings)

Inclusive-NRF. Python

JSA-KRTOD. Python

MGA-dev. Markovian Generative Architectures for Efficient Task-Oriented Dialog Systems

JSA. Joint Stochastic Approximation and its Application to Learning Discrete Latent Variable Models, UAI 2020.

VMSep-2010. Combining HMM-based Melody Extraction and NMF-based Soft Masking for Separating Voice and Accompaniment from Monaural Audio, ICASSP 2011.

SPMISeq. A SPMI Lab toolkit for sequence tagging tasks based on Pytorch. Neural CRF Transducers for Sequence Labeling, ICASSP 2019.

IqiyiProject. Iqiyi movie dialog system. Tracking of enriched dialog states for flexible conversational information access, ICASSP 2018.