Summary of Speechcomposer: Unifying Multiple Speech Tasks with Prompt Composition, by Yihan Wu et al.
SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition
by Yihan Wu, Soumi Maiti, Yifan Peng, Wangyou Zhang, Chenda Li, Yuyue Wang, Xihua Wang, Shinji Watanabe, Ruihua Song
First submitted to arxiv on: 31 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); 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 The proposed SpeechComposer model is a novel decoder-only speech language model that unifies common speech tasks by composing fixed prompt tokens. By combining four primary tasks – speech synthesis, recognition, language modeling, and text language modeling – SpeechComposer can extend to more tasks like voice conversion and enhancement. The model’s ability to share knowledge between tasks in a structured manner improves performance on both individual and composite tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary SpeechComposer is a new kind of computer program that helps machines understand and create speech. It combines four different tasks into one, making it easy to add new tasks later. This makes the program better at understanding and creating speech. The results show that this model works well for many tasks. |
Keywords
» Artificial intelligence » Decoder » Language model » Prompt
