Scholar
Peter Wu
Google Scholar ID: j9ICsOEAAAAJ
School of Computer Science, Carnegie Mellon University
Citations & Impact
Citations
3,376
H-index
19
i10-index
26
Publications
20
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Deep Speech Synthesis from Articulatory Representations, Interspeech 2022
- ESPnet2-TTS: Extending the Edge of TTS Research, Under submission, 2022
- PACS: A Dataset for Physical Audiovisual CommonSense Reasoning, ECCV 2022
- Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks, APSIPA 2021
- Cross-lingual Transfer for Speech Processing using Acoustic Language Similarity, ASRU 2021
- MultiBench: Multiscale Benchmarks for Multimodal Representation Learning, NeurIPS 2021
- Cross-Modal Generalization: Learning in Low Resource Modalities via Meta-Alignment, ACM Multimedia 2021
- Ordinal Triplet Loss: Investigating Sleepiness Detection from Speech, Interspeech 2019
- LEAF: A Benchmark for Federated Settings, NeurIPs Workshop 2019
- Submission from CMU for Blizzard Challenge 2018, Interspeech Workshop 2018
Research Experience
- Worked at Cresta, Telling.ai, and Kintsugi outside of school.
Education
- Currently a PhD student at Berkeley (BAIR). Previously, a student at Carnegie Mellon (BSCS, MSML) advised by Alan Black, Louis-Philippe Morency, and Shinji Watanabe.
Background
- A CS PhD student, with research interests centering on machine learning and socially impactful applications.
Miscellany
- Outside of school, spent time at Cresta, Telling.ai, and Kintsugi.
