Soroosh Mariooryad

4 papers · 2020–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (2) Interspeech (1) NAACL (1)

Top co-authors

RJ Skerry-Ryan (4) Julian Salazar (3) Daisy Stanton (2) Alon Levkovitch (2) Eric Battenberg (2) Eliya Nachmani (2) Matt Shannon (2) Nadav Bar (1) Raza Habib (1) Tom Bagby (1)

Research topics

Deep Learning (3) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Learning Types (2) Models (2) Natural Language Processing (1) Speech & Audio (1) Applications (1) Architectures (1) Generation (1) Synthesis (1)

Keywords

speech synthesis (3) speech recognition (1) cross-modal learning (1) generative model (1) autoregressive model (1) latent variable (1) controllable generation (1) length generalization (1) spoken language model (1) amplitude scaling (1) zero-shot (1) denoising vocoder (1) geometric time warping (1) semi-supervised learning (1) mono-to-binaural (1)

Papers

Robust and Unbounded Length Generalization in Autoregressive Transformer-Based Text-to-Speech NAACL 2025 Zero-Shot Mono-to-Binaural Speech Synthesis Interspeech 2025 Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM ICLR 2024 Semi-Supervised Generative Modeling for Controllable Speech Synthesis ICLR 2020