Matt Sharifi
Matt Sharifi has 2 papers in our library, in 2022–2023, most of them on Speech & spoken language, Language models & pretraining; often with Damien Vincent, Eugene Kharitonov, Marco Tagliasacchi.
OpenAlex · ORCID · h-index 8 · 11 works · 863 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 313 citations in our library · ⭐ Paper Star rank #2723
Affiliations
Concepts, shelves and topics
📚 Shelves 5 Arts and Humanities · 2 works Computer Science · 2 works Artificial Intelligence · 2 works Language and Linguistics · 2 works Signal Processing · 2 works
🧭 Topics 2 Speech & spoken language · 2 works Language models & pretraining · 1 work
Works by year
2020s
Papers
- AudioLM: a Language Modeling Approach to Audio Generation (2022 · 570 citations)
AudioLM tackles a long-standing tension in audio synthesis: models that produce realistic-sounding waveforms tend to drift into incoherent output (such as babbling speech) without strong conditioning, while earlier "textless" spoken language models stay coherent but offer limited quality and only one clean-speech… - Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision (2023 · 143 citations)
SPEAR-TTS addresses the fact that text-to-speech systems usually need hundreds of hours of transcribed audio, which leaves most of the world's languages without high-quality TTS.
Co-authors here
- Damien Vincent ×2
- Eugene Kharitonov ×2
- Marco Tagliasacchi ×2
- Neil Zeghidour ×2
- Olivier Pietquin ×2
- Raphael Marinier ×2
- Zalan Borsos ×2
- David Grangier
Venues
- IEEE/ACM Transactions on Audio Speech and Language…: 2022
- Transactions of the Association for Computational…: 2023
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/matt-sharifi/