Edresson Casanova
Scholar

Edresson Casanova

Google Scholar ID: QvS6LVwAAAAJ
Senior Research Scientist at NVIDIA
Text-to-SpeechSpeech SynthesisSpeech processingDuplex S2S
Google Scholar↗
Citations & Impact
All-time
Citations
1,378
 
H-index
13
 
i10-index
15
 
Publications
20
 
Co-authors
4
list available
Contact
No contact links provided.
Publications
9 items
Tagarela - A Portuguese speech dataset from podcasts
2026
Cited
0
The Impact of Prosodic Segmentation on Speech Synthesis of Spontaneous Speech
2025
Cited
0
Align2Speak: Improving TTS for Low Resource Languages via ASR-Guided Online Preference Optimization
2025
Cited
0
Frame-Stacked Local Transformers For Efficient Multi-Codebook Speech Generation
2025
Cited
0
NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference
2025
Cited
0
Efficient and Direct Duplex Modeling for Speech-to-Speech Language Model
2025
Cited
0
Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance
2025
Cited
0
FreeSVC: Towards Zero-shot Multilingual Singing Voice Conversion
2025
Cited
0
Resume (English only)
Co-authors
4 total
Arnaldo Candido Junior
Arnaldo Candido Junior
Computer Cience Professor, São Paulo State University
Co-author 2
Co-author 2
Moacir Antonelli Ponti
Moacir Antonelli Ponti
Universidade de São Paulo | Mercado Libre Inc.
Co-author 4
Co-author 4