Summary of A Comparative Study Of Llm-based Asr and Whisper in Low Resource and Code Switching Scenario, by Zheshu Song and Ziyang Ma and Yifan Yang and Jianheng Zhuo and Xie Chen
A Comparative Study of LLM-based ASR and Whisper in Low Resource and Code Switching Scenario
by Zheshu Song, Ziyang Ma, Yifan Yang, Jianheng Zhuo, Xie Chen
First submitted to arxiv on: 1 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper investigates the potential of Large Language Models (LLMs) in Automatic Speech Recognition (ASR) tasks, particularly in low-resource settings and Mandarin-English code switching scenarios. Building upon previous works that leveraged LLMs for speech recognition in English and Chinese, this study aims to explore their capabilities in addressing these challenges. The authors evaluate and compare the performance of LLM-based ASR systems against the Whisper model, demonstrating a relative gain of 12.8% in low-resource ASR while the Whisper model performs better in Mandarin-English code switching ASR. This research sheds light on ASR for low-resource scenarios. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well computers can recognize what people are saying, especially when there’s not much data to learn from. It also explores how computers can understand when people switch between two languages. The researchers tested a special kind of computer model called Large Language Models and compared it to another model called Whisper. They found that the Large Language Model was better at recognizing speech in situations with limited data, but the Whisper model did better when understanding conversations that mixed two languages. |
Keywords
» Artificial intelligence » Large language model
