Jiachen Lian

Jiachen Lian (连甲琛)

I am a PhD at Berkeley EECS and I am affiliated at Berkeley Artificial Intelligence Research (BAIR) where I am advised by Prof. Gopala Krishna Anumanchipalli.

Research

Generally, my interest is the things that are still interesting 5 years from now.

Specifically, I am currently working on two directions.

(1) Boosting conversational/healthy/educational system with rich spoken language understanding .

With a clear sense of mission, I also work with UCSF to deploy my research outcome into hospitals and K-5 schools across the California!

(2) Real time multi-agents human-robot interaction around multi-modal world.

I am also interested in general AI science/health topics.

Startup Activity

I am co-founding an AI-powered spoken language learning startup, together with my advisor and another genius labmate. Demo will be available shortly.

Please pin me and have a coffee at any time to discuss educational (US, Chinese K12, etc) business collaboration.

Essay

Why do so few scientists make significant contributions and so many are forgotten in the long run [1]?
[1] https://www.cs.virginia.edu/~robins/YouAndYourResearch.pdf

Industrial

Meta AI, CA, USA
FAIR-BAIR Student Researcher • Oct 2023 to now
With: Wei-Ning Hsu

Meta AI, CA, USA
Research Intern • May 2022 to Dec. 2022
With: Alexei Baevski, Wei-Ning Hsu, Michael Auli

Speech and NLP Group, Tencent AI Lab(American) , WA, USA
Research Intern • Dec 2021 to Feb. 2022
With: Chunlei Zhang, Dong Yu

Speech and NLP Group, Tencent AI Lab(American) , WA, USA
Research Intern • April 2021 to Aug. 2021
With: Chunlei Zhang, Dong Yu

Teaching

Audio Signal Processing in Humans and Machines, Berkeley EECS , CA, USA Reader • Aug 2022 to Dec. 2022 Designed ASR Lab. Advisor: Prof. Gopala Krishna Anumanchipalli
Introduction to Deep Learning, CMU LTI , PA, USA Teaching Assistant • May 2021 to Dec. 2021 Independently designed face recognition assignment from scratch (one of the heaviest assignments). [Write-up] [Kaggle] Advisor: Prof. Bhiksha Raj

Selected Publications

	Towards Hierarchical Spoken Language Dysfluency Modeling Jiachen Lian, and Gopala Krishna Anumanchipalli, 2024 EACL (Main Conf/Oral, Long). Hierarchical extension of UDM with monotonicity injection. .
	Unconstrained Dysfluency Modeling for Dysfluent Speech Transcription and Detection Jiachen Lian, Carly Feng, Naasir Farooqi, Steve Li, Anshul Kashyap, Cheol Jun Cho, Peter Wu, Robbie Netzorg, Tingle Li, and Gopala Krishna Anumanchipalli, 2023 ASRU (Best Paper Candidate). To be deployed in hospitals and K-5 schools across the California! . 2024 Sevin Rosen Funds Award
	Deep Speech Synthesis from MRI-Based Articulatory Representations Peter Wu, Tingle Li, Yijing Lu, Yubin Zhang, Jiachen Lian, Alan Black, Louis Goldstein, Shinji Watanabe, and Gopala Krishna Anumanchipalli, 2023 Interspeech.
	AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations Jiachen Lian, Alexei Baevski, Wei-Ning Hsu, and Michael Auli, 2023 ASRU.
	Articulatory Representation Learning Via Joint Factor Analysis and Neural Matrix Factorization Jiachen Lian, Alan W Black, Yijing Lu, Louis Goldstein, Shinji Watanabe, and Gopala Krishna Anumanchipalli, 2023 ICASSP.
	UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli, and Dong Yu. IEEE/ACM Transactions on Audio, Speech, and Language Processing . [Demo]
	Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition Jiachen Lian, Alan W Black, Louis Goldstein, and Gopala Krishna Anumanchipalli. 2022 Interspeech. [code]
	Towards Improved Voice Conversion with Conditional DSVAE Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli, and Dong Yu. 2022 Interspeech. [Demo]
	Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion Jiachen Lian, Chunlei Zhang, and Dong Yu. 2022 ICASSP. [Demo]
	Masked Proxy Loss For Text-Independent Speaker Verification Jiachen Lian, Aiswarya Vinod Kumar, Hira Dhamyal, Bhiksha Raj, and Rita Singh. 2021 Interspeech (ISCA Student Travel Grant) . [Code]
	Detection and Evaluation of Human and Machine Generated Speech in Spoofing Attacks on Automatic Speaker Verification Systems Yang Gao, Jiachen Lian, Bhiksha Raj, and Rita Singh. 2021 SLT.