Hang Lv

An Asynchronous WFST-Based Decoder For Automatic Speech Recognition

2021 · arXiv (Cornell University)

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which …

TELEVAL: A Dynamic Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios

2025 · arXiv (Cornell University)

Spoken language models (SLMs) have advanced rapidly in recent years, accompanied by a growing number of evaluation benchmarks. However, most existing benchmarks emphasize task completion and capability scaling, while remaining poorly aligned with how users …