I’m Zirui Li (李孜睿), a doctoral researcher at Aalto University working with Prof. Mikko Kurimo and Dr. Lauri Juvela. My research is primarily about controllable text-to-speech (TTS) at the prosodic and phonetic levels for second-language learning and real-time speech assessment and feedback systems. I’m also interested in developing large-scale speech datasets and open-source models for Nordic TTS.

Before joining Aalto, I obtained an MSc in Embedded Systems at Delft University of Technology, where I was supervised by Prof. Odette Scharenborg and studied regional accent bias in speech recognition. I obtained a BEng in Internet of Things Engineering from Tianjin University.

🔥 News

  • 2026.02:  🎉🎉 Our paper, Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech, has been accepted by ICASSP 2026. See you in Barcelona🇪🇸.
  • 2025.09:  🎉🎉 We release Nord-Parl-TTS, an open-source TTS dataset for Finnish and Swedish. You’re welcomed to check our demo page.
  • 2025.06:  🎉🎉 Our paper Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams is accepted by Speech Synthesis Workshop 2025 (SSW13).
  • 2024.10:  🎉🎉 I started as a PhD student at Speech Recognition Group at Aalto University.

📝 Publications

  • Z. Li, R. Silas, L. Juvela, T. Bäckström and M. Kurimo, “EmphTTS: An Emphasis-Control TTS with Reinforcement Learning”, arXiv:2609.27599, 2026. Under review. Arxiv Demo Code
  • Z. Li, J. Edlund, Y. Gu, N. Phan, L. Juvela and M. Kurimo, “Nord-Parl-TTS: Finnish and Swedish TTS Dataset from Parliament Speech,” in ICASSP 2026. Paper Demo Dataset
  • Z. Li, L. Juvela and M. Kurimo, “Pronunciation Editing for Finnish Speech using Phonetic Posteriorgrams”, in 13th Speech Synthesis Workshop (SSW13), 2025. Arxiv Code ISCA Archive

📖 Educations

  • 2024.10 - now, PhD student, Aalto University, Finland.
  • 2021.09 - 2023.07, M.Sc in Embedded Systems, Delft University of Technology, the Netherlands.
  • 2017.09 - 2021.07, B.Eng in Internet of Things Engineering, Tianjin University, China.

💻 Work Experience

  • Software Engineer (full-time) at Just Eat Takeaway.com
    Aug–Oct 2024 · Enschede, Netherlands
    Developed payment gateway features and added support for new payment methods across markets.
  • Research & Development Intern at AiSpeech Co. Ltd.
    Feb–Jun 2024 · Suzhou, China
    Built a two-stage keyword spotter for in-car speech and implemented streaming rescoring to reduce false alarms.
  • Software Development Engineer Intern at Amazon Web Services
    Jun–Jul 2023 · Amsterdam, Netherlands
    Built CloudShell OpsBot with TypeScript and AWS Lambda to help on-call engineers investigate CloudWatch alarms.
  • Machine Learning Engineer Intern at Cambricon Technologies
    Mar–Jun 2021 · Beijing, China
    Quantized and deployed YOLOv5s for object detection and Tacotron for speech synthesis on Cambricon’s deep learning accelerator.
  • Data Engineering Intern at Bosch China
    Aug–Oct 2020 · Changsha, China
    Built a convolutional network to recognize spare parts and a pipeline to process noisy sensor data.