Thilo Koehler
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- The Llama 3 Herd of ModelsSaved credit: Contributor · 2024Explore people connected to this work →
- Ultra-lightweight Neural Differential DSP Vocoder For High Quality Speech SynthesisSaved credit: Contributor · 2024Explore people connected to this work →
- Transformer-Based Acoustic Modeling for Streaming Speech SynthesisSaved credit: Contributor · 2021Explore people connected to this work →
- Interactive Text-to-Speech System via Joint Style AnalysisSaved credit: Contributor · 2020Explore people connected to this work →
- G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASRSaved credit: Contributor · 2019Explore people connected to this work →