Scholar
Pooneh Mousavi
Google Scholar ID: QkuComwAAAAJ
Mila and Concordia University
Citations & Impact
Citations
214
H-index
7
i10-index
6
Publications
12
Co-authors
30
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including:
- - "Discrete Audio Tokens: More Than a Survey!" accepted at TMLR 2025
- - "ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs" accepted at ICML 2025 Workshop on Machine Learning for Audio
- - "LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs" accepted at Interspeech 2025
- - "What Are They Doing? Joint Audio-Speech Co-Reasoning" published at ICASSP 2025
- - "How Should We Extract Discrete Audio Tokens from Self-Supervised Models?" published at Interspeech 2024, Oral Session
- - "DASB - Discrete Audio and Speech Benchmark" published at Interspeech 2024
- - "CL-MASR: A Continual Learning Benchmark for Multilingual ASR" submitted to Transactions on Audio, Speech and Language Processing
- - "WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series" published at relevant conferences or journals.
Research Experience
- Involved in multiple research projects and has extensive experience in the field of Conversational AI. She also organizes a weekly Conversational AI Reading Group, inviting researchers to present their papers.
Education
- PhD in Computer Science at Mila/Concordia University (Gina Cody School of Engineering and Computer Science) since Sep. 2022, supervised by Professor Mirco Ravanelli; M.S. in Computer Science at University of Texas at Dallas (UTD) from 2018 to 2021.
Background
- PhD student in Computer Science with a broad interest in deep learning for Conversational AI. Her research focuses on discrete self-supervised learning for speech and audio, exploring its potential to bridge audio and language models. She is also one of the main contributors to the SpeechBrain project, a popular open-source conversational AI toolkit.
Miscellany
- Join her weekly Conversational AI Reading Group, where leading scientists share insights on the latest advancements every Thursday. Open to collaboration on exciting projects, feel free to reach out via mousavi (dot) pooneh (at) gmail.com.
