When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech Parsing
We introduce a simpler end-to-end architecture for speech parsing, where we remove these intermediate NN units, reducing the parameters by 12%, while achieving comparable or better performance than prior method on both automatic speech recognition (ASR) and parsing.
ProofPaper ↗
Key points
- End-to-end speech parsing, a task recently proposed, consists in predicting both the transcription and the syntactic tree for a spoken utterance.
- Existing architectures for speech parsing often utilise intermediate neural networks.
- In this work, we examine the effectiveness of intermediate neural networks (NN) for parsing, and, specifically, what role do they play.
- We further investigate the impact of the training data size and intermediate layers of the pretrained speech encoder on speech parsing.
Sources (1)
- [1]When Can You Prune Your Network? A Study of Intermediate Neurons in Multilingual Speech ParsingarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 08:53 AM
We introduce a simpler end-to-end architecture for speech parsing, where we remove these intermediate NN units, reducing the parameters by 12%, while achieving comparable or better performance than prior method on both automatic speech recognition (ASR) and parsing.
End-to-end speech parsing, a task recently proposed, consists in predicting both the transcription and the syntactic tree for a spoken utterance.
Extractive summary: sentences quoted from the sources.
