Author

Tiantian Feng

Observed name: Feng, Tiantian

Institutions: University of Southern California, University of Michigan

Observed institutions: University of Southern California, University of Michigan

ORCID: 0000-0002-2053-9068

Observed ORCID: 0000-0002-2053-9068

OpenAlex ID: A5128663831

Understanding Everyday Communication Patterns, Stress, and Productivity in Hybrid Work through Egocentric Wearable Audio Sensing

2026 · Feng, Tiantian, Kommineni, Aditya, et al. · arXiv (Cornell University)

PDF

Uni-Stream: A Unified Streaming Speech Language Model for Speech Synthesis and Recognition

2026 · Shi, Xuan, Zeng, Chang, et al. · arXiv (Cornell University)

PDF

SPARC: Spoken Profile Authorship Recognition Corpus

2026 · Tsaprazlis, Efthymios, Yi, Bowen, et al. · arXiv (Cornell University)

PDF

Probing Neural Audio Codecs with Speaker Traits and Speech Characteristics

2026 · Lee, Jihwan, Feng, Tiantian, et al. · arXiv (Cornell University)

PDF

PEDBench: Can Speech Models Detect Phonetic Errors?

2026 · Shi, Zhonghao, Rackauckas, Zackary, et al. · arXiv (Cornell University)

PDF

Smiling Regulates Emotion During Traumatic Recollection

2026 · Marcus Ma, Emily Zhou, et al. · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION

Speaker Role and Language Diarization for Analyzing Multilingual Interviews for Language Proficiency of Older Adults

2026 · Xu, Anfeng, Feng, Tiantian, et al. · arXiv (Cornell University)

PDF

RespiraMFM: A Multimodal Foundation Model with Contrastive Audio-Language Alignment for Respiratory Disease Identification

2026 · Association for Computational Linguistics 2026, Feng, Tiantian, et al. · Underline Science Inc.

A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models

2026 · Kommineni, Aditya, Zhou, Emily, et al. · arXiv (Cornell University)

PDF

Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models

2026 · Kommineni, Aditya, Zhou, Emily, et al. · arXiv (Cornell University)

PDF

Encoding Emotion Through Self-Supervised Eye Movement Reconstruction

2026 · Marcus Ma, Jordan Prescott, et al. · IEEE International Conference on Acoustics Speech and Signal Processing

Exploring Speech Foundation Models for Speaker Diarization Across Lifespan

2026 · Xu, Anfeng, Feng, Tiantian, et al. · arXiv (Cornell University)

PDF

Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

2026 · Wang, Shih-Heng, Feng, Tiantian, et al. · arXiv (Cornell University)

PDF

Affect Decoding in Phonated and Silent Speech Production from Surface EMG

2026 · Pistrosch, Simon, Avramidis, Kleanthis, et al. · arXiv (Cornell University)

PDF

Speech Codec Probing from Semantic and Phonetic Perspectives

2026 · Shi, Xuan, Zeng, Chang, et al. · arXiv (Cornell University)

PDF

VoxCare: Studying Natural Communication Behaviors of Hospital Caregivers through Wearable Sensing of Egocentric Audio

2026 · Feng, Tiantian, Avramidis, Kleanthis, et al. · arXiv (Cornell University)

PDF

Learning-free L2-Accented Speech Generation using Phonological Rules

2026 · Lertpetchpun, Thanathai, Lee, Yoonjeong, et al. · arXiv (Cornell University)

PDF

Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data

2026 · Lertpetchpun, Thanathai, Trachu, Thanapat, et al. · arXiv (Cornell University)

PDF

Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis

2026 · Lertpetchpun, Thanathai, Lee, Yoonjeong, et al. · arXiv (Cornell University)

PDF

Encoding Emotion Through Self-Supervised Eye Movement Reconstruction

2026 · Ma, Marcus, Prescott, Jordan, et al. · arXiv (Cornell University)

PDF

VoxCog: Towards End-to-End Multilingual Cognitive Impairment Classification through Dialectal Knowledge

2026 · Feng, Tiantian, Xu, Anfeng, et al. · arXiv (Cornell University)

PDF

Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs

2026 · Efthymios Tsaprazlis, Tiantian Feng, et al. · Lecture notes in computer science

PDF

ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across Childhood

2026 · Tiantian Feng, Anfeng Xu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

PDF

Works count: 23

Citation count:

H-index:

I10-index: