Textless Dependency Parsing by Labeled Sequence Prediction

TL;DR

This paper introduces a novel textless dependency parsing method that directly predicts dependency trees from speech signals, bypassing transcription, and explores its effectiveness and limitations compared to cascading approaches.

Contribution

It proposes a new textless dependency parsing approach using labeled sequence prediction directly from speech, highlighting the importance of combining acoustic and lexical features.

Findings

Textless parsing can effectively capture acoustic features.

Cascading methods outperform in overall accuracy.

Fusion of word-level and prosody features improves performance.

Abstract

Traditional spoken language processing involves cascading an automatic speech recognition (ASR) system into text processing models. In contrast, "textless" methods process speech representations without ASR systems, enabling the direct use of acoustic speech features. Although their effectiveness is shown in capturing acoustic features, it is unclear in capturing lexical knowledge. This paper proposes a textless method for dependency parsing, examining its effectiveness and limitations. Our proposed method predicts a dependency tree from a speech signal without transcribing, representing the tree as a labeled sequence. scading method outperforms the textless method in overall parsing accuracy, the latter excels in instances with important acoustic features. Our findings highlight the importance of fusing word-level representations and sentence-level prosody for enhanced parsing performance. The code and models are made publicly available: https://github.com/mynlp/SpeechParser.