Summary of Indonesian-english Code-switching Speech Synthesizer Utilizing Multilingual Sten-tts and Bert Lid, by Ahmad Alfani Handoyo et al.
Indonesian-English Code-Switching Speech Synthesizer Utilizing Multilingual STEN-TTS and Bert LID
by Ahmad Alfani Handoyo, Chung Tran, Dessi Puji Lestari, Sakriani Sakti
First submitted to arxiv on: 26 Dec 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 This research paper presents a multilingual text-to-speech (TTS) system capable of handling code-switching between Indonesian and English, a common phenomenon in Indonesia. The proposed system, named STEN-TTS, incorporates a language identification component based on finetuned BERT for per-word language detection. This allows the model to remove language embedding from the base model and effectively handle code-switched text sentences. Experimental results show that the code-switching model outperforms baseline Indonesian and English TTS models in terms of naturalness and speech intelligibility. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper develops a multilingual text-to-speech system that can convert text into speech across multiple languages, including Indonesian and English. It’s especially important for Indonesia because many people speak both languages. The new system is better at recognizing when words switch from one language to another and improving how well the audio sounds. |
Keywords
» Artificial intelligence » Bert » Embedding
