# On the Role of Style in Parsing Speech with Neural Models

arXiv: https://arxiv.org/abs/2010.04288 · HTML: https://mlsanity.com/paper/2010.04288/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2020.

## Built on by (most cited first, 7 of 7)

- [The Role of Prosody in Spoken Question Answering](https://mlsanity.com/paper/2502.05389/) (2025)
- [Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives](https://mlsanity.com/paper/2301.10761/) (2023)
- [Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts](https://mlsanity.com/paper/2106.07794/) (2021)
- [Audio-Visual Neural Syntax Acquisition](https://mlsanity.com/paper/2310.07654/) (2023)
- [Artificial Disfluency Detection, Uh No, Disfluency Generation for the Masses](https://mlsanity.com/paper/2211.09235/) (2022)
- [Prosodic segmentation for parsing spoken dialogue](https://mlsanity.com/paper/2105.12667/) (2021)
- [Prosodic features improve sentence segmentation and parsing](https://mlsanity.com/paper/2302.12165/) (2023)

## Abstract (arXiv)

The differences in written text and conversational speech are substantial; previous parsers trained on treebanked text have given very poor results on spontaneous speech. For spoken language, the mismatch in style also extends to prosodic cues, though it is less well understood. This paper re-examines the use of written text in parsing speech in the context of recent advances in neural language processing. We show that neural approaches facilitate using written text to improve parsing of spontaneous speech, and that prosody further improves over this state-of-the-art result. Further, we find an asymmetric degradation from read vs. spontaneous mismatch, with spontaneous speech more generally useful for training parsers.