Tian Yuan - Tianyuan at baidu

Tian Yuan

Tianyuan at baidu

Beijing, China

Join Prog.AI to see contacts

Summary

🤩

Rockstar

Tianyuan is a Beijing-based speech ML engineer with nine years' experience focused on TTS, voice cloning, voice conversion, and speech editing. Currently at Baidu, he contributes to production-grade speech systems and has practical experience integrating tools like Montreal Forced Aligner into open-source projects. As an active contributor to PaddleSpeech—an award-winning, widely used speech toolkit—he has worked on ASR dataset preparation and lexicon tooling for Chinese, reflecting both research-minded and engineering-first instincts. His background blends academic study at BUPT with hands-on model engineering, making him adept at bridging dataset engineering, forced alignment, and end-to-end speech pipelines.

9 years of coding experience

Github Skills (9)

data-preprocessing10

speech-recognition10

automatic-speech-recognition10

python10

asr10

machine-learning9

modeling8

trainings8

code-structure7

Programming languages (9)

C#DockerfileC++JavaScriptLuaHTMLJupyter NotebookMATLAB

Github contributions (5)

PaddlePaddle/PaddleSpeech

Jul 2021 - Jan 2023

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Role in this project:

ML Engineer

Contributions:1 release, 585 reviews, 746 commits in 1 year 6 months

Contributions summary:Tian's commits primarily involve adding a MFA (Montreal Forced Aligner) example for the THCHS30 dataset, showcasing a focus on automatic speech recognition (ASR). The changes include the creation of a new Python script to reorganize the dataset for MFA and modifications to existing scripts for generating Chinese characters to phone lexicons. The commits demonstrate an interest in integrating external tools and techniques like forced alignment into the paddle speech project.

voice-recognitionasrtranslationspeech-recognitionstreaming-tts

yt605155624/PaddleSpeech

Aug 2022 - Dec 2022

A PaddlePaddle Speech to Text toolkit.

Contributions:33 commits, 2 PRs, 578 pushes in 3 months

paddlepaddlespeech-to-textspeech-recognitionspeech-synthesisspeech

Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.

Request Free Trial