184 citations · 868 across the 60 of their papers we have counts for
63 papers
Massive End-to-end Models for Short Search Queries
Weiran Wang, Rohit Prabhavalkar, Dongseong Hwang +11
In this work, we investigate two popular end-to-end automatic speech recognition (ASR) models, namely Connectionist Temporal Classification (CTC) and RNN-Transducer (RNN-T), for of…
Towards Code Watermarking with Dual-Channel Transformations
Borui Yang, Wei Li, Liyao Xiang +1
The expansion of the open source community and the rise of large language models have raised ethical and security concerns on the distribution of source code, such as misconduct on…
How to Estimate Model Transferability of Pre-Trained Speech Models?
Zih-Ching Chen, Chao-Han Huck Yang, Bo Li +6
In this work, we introduce a "score-based assessment" framework for estimating the transferability of pre-trained speech models (PSMs) for fine-tuning target tasks. We leverage upo…
Modular Domain Adaptation for Conformer-Based Streaming ASR
Qiujia Li, Bo Li, Dongseong Hwang +2
Speech data from different domains has distinct acoustic and linguistic characteristics. It is common to train a single multidomain model such as a Conformer transducer for speech…
UMD: Unsupervised Model Detection for X2X Backdoor Attacks
Zhen Xiang, Zidi Xiong, Bo Li
Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversa…
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
Boyao Li, Alexander J. Thomson, Houssam Nassif +2
Deep neural networks (DNNs) lack the precise semantics and definitive probabilistic interpretation of probabilistic graphical models (PGMs). In this paper, we propose an innovative…