On the Role of Style in Parsing Speech with Neural Models

2020/10/08 by Trang Tran, Jiahong Yuan, Tran, Trang +6
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL

paper · pdf · doi:10.48550/arxiv.2010.04288

Interspeech 2019

arxiv created 2020/10/08 · openalex publication_date 2020/10/08 · arxiv updated 2020/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Parsing Speech: A Neural Approach to Integrating Lexical and Acoustic-Prosodic Information
• Assessing the Use of Prosody in Constituency Parsing of Imperfect Transcripts
• Controllable neural text-to-speech synthesis using intuitive prosodic features
• STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech
• Neural Constituency Parsing of Speech Transcripts