Tian Gao

Joint training of front-end and back-end deep neural networks for robust speech recognition

2015

Based on the recently proposed speech pre-processing front-end with deep neural networks (DNNs), we first investigate different feature mapping directly from noisy speech via DNN for robust speech recognition. Next, we propose to jointly train …

Do Multi-hop Readers Dream of Reasoning Chains?

2019 · arXiv (Cornell University)

General Question Answering (QA) systems over texts require the multi-hop reasoning capability, i.e. the ability to reason with information collected from multiple passages to derive the answer. In this paper we conduct a systematic analysis …

State Variable Effects in Graphical Event Models

2020

Many real-world domains involve co-evolving relationships between events, such as meals and exercise, and time-varying random variables, such as a patient's blood glucose levels. In this paper, we propose a general framework for modeling joint …

Type-augmented Relation Prediction in Knowledge Graphs

2020 · arXiv (Cornell University)

Knowledge graphs (KGs) are of great importance to many real world applications, but they generally suffer from incomplete information in the form of missing relations between entities. Knowledge graph completion (also known as relation prediction) …

Voice spoofing detection with raw waveform based on Dual Path Res2net

2021

The natural-sounding speech produced by recent text-to-speech and voice conversion techniques pose serious threats to automatic speaker verification systems. The majority of existing spoofing detection countermeasures perform well when the nature of the attacks is …

Learning and Retrieval from Prior Data for Skill-based Imitation Learning

2022 · arXiv (Cornell University)

Imitation learning offers a promising path for robots to learn general-purpose behaviors, but traditionally has exhibited limited scalability due to high data supervision requirements and brittle generalization. Inspired by recent advances in multi-task imitation learning, …

Reconstructing Negative Survey with Least Squares Criterion

2022

Inspired by artificial immune system, negative survey is a cost-effective privacy protection method for multiple choice question-answering with the advantage of decentralization. Present reconstruction methods for negative surveys can obtain positive survey without negative values …

DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions

2024 · arXiv (Cornell University)

We propose a single-channel Deep Cascade Fusion of Diarization and Separation (DCF-DS) framework for back-end automatic speech recognition (ASR), combining neural speaker diarization (NSD) and speech separation (SS). First, we sequentially integrate the NSD and …

BEV-TSR: Text-Scene Retrieval in BEV Space for Autonomous Driving

2025 · Proceedings of the AAAI Conference on Artificial Intelligence

The rapid development of the autonomous driving industry has led to a significant accumulation of autonomous driving data. Consequently, there comes a growing demand for retrieving data to provide specialized optimization. However, directly applying previous …