1 citations · 2 across the 6 of their papers we have counts for
6 papers
LLM-Driven Heuristic Frame-Level Quantization Parameter Adaptation for VVenC
Liqiang He, Yingwen Zhang, Riyu Lu +2
Optimal frame-level quantization parameter (QP) allocation remains a persistent challenge in modern video encoders. The fixed-QP scheme widely adopted in practical systems is inher…
Generative Pre-trained Speech Language Model with Efficient Hierarchical Transformer
Yongxin Zhu, Dan Su, Liqiang He +2
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio code…
Fuse after Align: Improving Face-Voice Association Learning via Multimodal Encoder
Chong Peng, Liqiang He, Dan Su
Today, there have been many achievements in learning the association between voice and face. However, most previous work models rely on cosine similarity or L2 distance to evaluate…
Latency-Controlled Neural Architecture Search for Streaming Speech Recognition
Liqiang He, Shulin Feng, Dan Su +1
Neural architecture search (NAS) has attracted much attention and has been explored for automatic speech recognition (ASR). In this work, we focus on streaming ASR scenarios and pr…
Learned Transferable Architectures Can Surpass Hand-Designed Architectures for Large Scale Speech Recognition
Liqiang He, Dan Su, Dong Yu
In this paper, we explore the neural architecture search (NAS) for automatic speech recognition (ASR) systems. With reference to the previous works in the computer vision field, th…
Phrase-Level Class based Language Model for Mandarin Smart Speaker Query Recognition
Yiheng Huang, Liqiang He, Lei Han +2
The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and…