Mohammad Javad Ranjbar

محمدجواد رنجبر

I'm a researcher at the EPFL NLP Lab in Lausanne, working with Antoine Bosselut on multilingual audio understanding for Apertus 2, Switzerland's fully open multilingual LLM. I'm also a research assistant at the BIIC Lab at National Tsing Hua University, working with Chi-Chun Lee on affective speech foundation models across cultures.

My research is on multilingual and low-resource NLP, mostly around speech: how far synthetic speech can stand in for real data, and the corpora and benchmarks that Persian NLP has been missing. These include ParsVoice, the largest open Persian speech corpus, which I built for my M.Sc. thesis at the University of Tehran with Azadeh Shakery and Heshaam Faili.

Outside research, I love movies and games, and I like karaoke, long walks, exploring random places and visiting museums. You can see what I've been reading on Goodreads. A few of my favorite films and games are hidden around this site as easter eggs; see how many you can find.

I'm looking for PhD positions starting in 2027.

mohammadjavadranjbark@gmail.com/ CV/ Google Scholar/ GitHub/ Hugging Face/ LinkedIn

Portrait of Mohammad Javad Ranjbar

Hear my work

My thesis model clones a voice it has never heard from a few seconds of audio. Nobody ever recorded this sentence; press the waveform to hear it.

صدای خنده بچه‌ها در تمام کوچه پیچیده بود ▶ press to listen

"The sound of children's laughter echoed throughout the alley."

Selected publications full list

How Far Can Synthetic Speech Take Us? Synthetic Data Recipes for Pretraining Multilingual Speech Language Models
M. J. Ranjbar Kalahroodi*, A. K. Tarun*, C. I. Meister, A. Bosselut
Under review at ICLR 2027. *Equal contribution.

How far synthetic (TTS) speech can stand in for real speech when pretraining multilingual speech-language models, across six languages.

ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis
M. J. Ranjbar Kalahroodi, H. Faili, A. Shakery
EMNLP 2026, main conference

The largest open Persian speech corpus: 4,000+ hours of audiobooks turned into multi-speaker TTS data by an automated pipeline, with a zero-shot voice-cloning model.

PARSA-Bench: A Comprehensive Persian Audio-Language Model Benchmark
M. J. Ranjbar Kalahroodi*, M. Amini*, P. Bathayan, H. Faili, A. Shakery
Findings of EACL 2027. *Equal contribution.

The first Persian audio-language benchmark: 16 tasks and 7,645 samples, from speech recognition to the metre of classical poetry.

PersianMedQA: Evaluating Large Language Models on a Persian-English Bilingual Medical Question Answering Benchmark
M. J. Ranjbar Kalahroodi, A. Sheikholselami, S. Karimi Arpanahi, S. Ranjbar Kalahroodi, H. Faili, A. Shakery
LREC 2026

20,785 expert-validated questions from 14 years of Iranian medical board exams, in Persian and English, for testing LLMs.

PersianPunc: A Large-Scale Dataset and BERT-Based Approach for Persian Punctuation Restoration
M. J. Ranjbar Kalahroodi, H. Faili, A. Shakery
SilkRoadNLP workshop at EACL 2026

A 17M-sample dataset and a lightweight ParsBERT model for restoring punctuation in Persian text, such as speech-recognition output.

Experience

2026 – now
EPFL NLP Lab, researcher

Swiss AI Initiative: adding multilingual audio understanding to Apertus 2, and studying how far synthetic speech can replace real speech in pretraining.

2026 – now
National Tsing Hua University, BIIC Lab, research assistant

With Chi-Chun Lee, on a Taiwan–Germany project on affective speech foundation models across cultures.

2023 – 2026
University of Tehran, IIS Lab, research and teaching assistant

Led research on Persian speech synthesis and medical LLMs; chief TA for ML Methods in NLP and Digital Speech Processing, and TA for five more courses.

2023 – 2024
Sofia, co-founder and NLP engineer

A multi-platform RAG customer-service chatbot with 20,000+ active users on the University of Tehran website.

2024 – 2026
Neuromatch Summer School, teaching assistant

Mentored international students across the NLP, neuroscience and computer vision courses, each summer.

2020 – 2022
Amirkabir University of Technology and FIRA Academy, instructor, TA and RA

Taught image processing and ML; developed the SWIMBot platform for Diginext; research on facial emotion recognition.

Education

2022 – 2025
University of Tehran, M.Sc. in Computer Engineering

GPA 4.0/4.0. Thesis: Zero-Shot Text-to-Speech for the Persian Language, advised by Azadeh Shakery and Heshaam Faili.

2016 – 2021
Amirkabir University of Technology, B.Sc. in Electrical Engineering

Thesis: Facial Expression Recognition with Robotic Implementation, advised by M. B. Menhaj and H. Taheri.

Invited talks

Aug 2026

Audio and Text Understanding for Low-Resource Languages

Jul 2026

Audio and Text Understanding for Low-Resource Languages

Academic service

Oct 2026
Volunteer virtual session chair, EMNLP 2026
2019, 2021
Student committee, International Conference on Robotics and Mechatronics (ICRoM)

Honors

2022
Ranked 76th of ~15,000 (top 0.5%), National M.Sc. Entrance Exam, Computer Engineering
2022
Ranked 35th of ~2,000 (top 2%), National M.Sc. Entrance Exam, Computer Science
2016
Ranked 411th of ~163,000 (top 0.25%), National University Entrance Exam, Math and Physics