most citedImproving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning

18 citations · 36 across the 5 of their papers we have counts for

collaborators

5 papers

quant-ph2025★ 1 cited

Quantum Direct Steganography Scheme Based on Modified Generator Projection Directions of Steane Code over a Single-Type Pauli Channel

Chaolong Hao, Quangong Ma, Dan Qu +1

In quantum mechanics, measurements of a quantum state in various directions yield distinct outcomes, a principle that forms the foundation of quantum communication theory. This pap…

cs.CL2023★ 2 cited

Tuning Large language model for End-to-end Speech Translation

Hao Zhang, Nianwen Si, Yaqi Chen +4

With the emergence of large language models (LLMs), multimodal models based on LLMs have demonstrated significant potential. Models such as LLaSM, X-LLM, and SpeechGPT exhibit an i…

cs.CL2023★ 15 cited

DropDim: A Regularization Method for Transformer Networks

Hao Zhang, Dan Qu, Keji Shao +1

We introduceDropDim, a structured dropout method designed for regularizing the self-attention mechanism, which is a key component of the transformer. In contrast to the general dro…

cs.CL2023★ 18 cited

Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning

Hao Zhang, Nianwen Si, Yaqi Chen +4

The end-to-end speech translation (E2E-ST) model has gradually become a mainstream paradigm due to its low latency and less error propagation. However, it is non-trivial to train s…

cs.CL2023

Decouple Non-parametric Knowledge Distillation For End-to-end Speech Translation

Hao Zhang, Nianwen Si, Yaqi Chen +4

Existing techniques often attempt to make knowledge transfer from a powerful machine translation (MT) to speech translation (ST) model with some elaborate techniques, which often r…