EUVIMEDEUVIMED entdecken
Crossref

CONDITIONAL FASTSPEECH 2 FOR LOW-RESOURCE INDIAN ACCENT SYNTHESIS: A PHONETIC ADAPTATION APPROACH

Ritesh Kumar Yadav, Divyanshi Srivastava, Sweacha Verma, Chaudhary Surya Prakash

Adroid Conference Series: Engineering and Technology · 24.11.2025 · 230-235

DOI: 10.63503/c.acset.2025.25 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Adroid Conference Series: Engineering and Technology, online erschienen am 24.11.2025. Verfasst von Ritesh Kumar Yadav und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In essence, text-to-speech (TTS) applications that read aloud text are becoming more and more crucial for digital accessibility in order to access digital content. The issue is that they struggle to understand Indian languages and our regional accents (when peaks English with Indian accent features). This paper discusses the FastSpeech2 system. To it, we applied an accent embedding layer. It can speak in three different languages thanks to this layer: standard Hindi, Indian English, and Bhojpuri, a low-resource language. In order to identify accent-appropriate pronunciations for a particular accent, particularly the less common Bhojpuri ones, we employed a transformer-based LLM-adapted tool for speech and phonetic mapping. Graphemes to phonemes (G2P) mapping is accomplished by this adaptive phonetic mapping module! We tested it, and the findings show notable advancements. Enhancement of 27.5 Essential Points in Plain English for the Bhojpuri Accent The primary issue is that low-resource languages and a variety of Indian accents perform poorly on current text-to-speech (TTS) systems. Our Method: By incorporating an Accent Embedding Layer, we enhanced a TTS system (FastSpeech2). What it can do: It can now communicate in Standard Hindi, Bhojpuri, and Indian English. Method: To modify pronunciations for those distinct accents, we employed a large language model (LLM). As a result, human listeners judged the voices as natural, and it speaks Bhojpuri much more accurately.

Zitieren

APA

Yadav, R. K., Srivastava, D., Verma, S., & Prakash, C. S. (2025). CONDITIONAL FASTSPEECH 2 FOR LOW-RESOURCE INDIAN ACCENT SYNTHESIS: A PHONETIC ADAPTATION APPROACH. Adroid Conference Series: Engineering and Technology, 230-235. https://doi.org/10.63503/c.acset.2025.25

Vancouver

Yadav RK, Srivastava D, Verma S, Prakash CS. CONDITIONAL FASTSPEECH 2 FOR LOW-RESOURCE INDIAN ACCENT SYNTHESIS: A PHONETIC ADAPTATION APPROACH. Adroid Conference Series: Engineering and Technology. 2025:230-235. doi:10.63503/c.acset.2025.25

BibTeX
@article{Yadav2025,
  author = {Yadav, Ritesh Kumar and Srivastava, Divyanshi and Verma, Sweacha and Prakash, Chaudhary Surya},
  title = {CONDITIONAL FASTSPEECH 2 FOR LOW-RESOURCE INDIAN ACCENT SYNTHESIS: A PHONETIC ADAPTATION APPROACH},
  journal = {Adroid Conference Series: Engineering and Technology},
  year = {2025},
  pages = {230--235},
  doi = {10.63503/c.acset.2025.25}
}
Kostenlos starten →