🧑‍🔬 David Harwath

🏛️ Affiliations

🎓The University of Texas at AustinAustin · United States2021–2026 · 81 paperscurrent🎓Massachusetts Institute of TechnologyCambridge · United States2013–2021 · 22 papers🔬MIT Computer Science and Artificial Intelligence LaboratoryCambridge · United States2013–2021 · 12 papers🔬MIT Lincoln LaboratoryLexington · United States2012–2013 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation (2026 · 4 citations)
   Autoregressive neural codec language model (NCLM) TTS systems usually concatenate text and speech tokens and leave alignment to ordinary positional encodings.
2. Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration (2026)
   Multilingual ASR systems such as Whisper learn from web data in which one language may be transcribed in several writing systems.

All works

13 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Learning Word-Like Units from Joint Audio-Visual Analysis ↗Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetDavid Harwath, James Glass2017 · 122 citations
2. Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetBrian Chen et al.2021 · 78 citations
3. Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality ↗Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · no summary yetAnuj Diwan et al.2022 · 52 citations
4. Scaling Rich Style-Prompted Text-to-Speech Datasets ↗Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · no summary yetAnuj Diwan et al.2025 · 10 citations
5. BAT: Learning to Reason about Spatial Sounds with Large Language Models ↗arXiv (Cornell University) · no summary yetZhisheng Zheng et al.2024 · 7 citations
6. Continual Learning for On-Device Speech Recognition Using Disentangled Conformers ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetAnuj Diwan et al.2023 · 7 citations
7. Audio-Visual Neural Syntax Acquisition ↗IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · no summary yetCheng-I Lai et al.2023 · 5 citations
8. VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and ExtrapolationFindings of the Association for Computational LinguisticsPuyuan Peng, Zhisheng Zheng, Shang-Wen Li, et al.2026 · 4 citations
9. Textless Speech-to-Speech Translation With Limited Parallel Data ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetAnuj Diwan et al.2024 · 3 citations
10. When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · no summary yetAnuj Diwan, Eunsol Choi, David Harwath2023 · 2 citations
11. Linear Script Representations in Speech Foundation Models Enable Zero-Shot TransliterationFindings of the Association for Computational LinguisticsRyan Soh-Eun Shim, Kwanghee Choi, Kalvin Chang, et al.2026
12. ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining ↗arXiv (Cornell University) · no summary yetAnuj Diwan, Eunsol Choi, David F. Harwath2026
13. Rhapsody: A Dataset for Highlight Detection in Podcasts ↗arXiv (Cornell University) · no summary yetY.T. Park et al.2025

🤝 Co-authors here

9 co-authors with a page, the most papers together first.

• Abdelrahman Mohamed
• Alane Suhr
• Barbara Plank
• David R. Mortensen
• Kalvin Chang
• Kwanghee Choi
• Michael A. Hedderich
• Shang-Wen Li
• Zhizheng Wu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing ×2
• Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) ×2
• Findings of the Association for Computational Linguistics: EMNLP 2024
• IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)
• IEEE International Conference on Acoustics Speech and Signal Processing
• IEEE/CVF International Conference on Computer Vision (ICCV)

🔗 Cited by

Papers of our library cite their works 78 times (of the 149,439 papers whose bibliographies we read); 10 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/david-harwath/