Discriminative Self-training for Punctuation Prediction

by   Qian Chen, et al.

Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications. However, achieving good performance on punctuation prediction often requires large amounts of labeled speech transcripts, which is expensive and laborious. In this paper, we propose a Discriminative Self-Training approach with weighted loss and discriminative label smoothing to exploit unlabeled speech transcripts. Experimental results on the English IWSLT2011 benchmark test set and an internal Chinese spoken language dataset demonstrate that the proposed approach achieves significant improvement on punctuation prediction accuracy over strong baselines including BERT, RoBERTa, and ELECTRA models. The proposed Discriminative Self-Training approach outperforms the vanilla self-training approach. We establish a new state-of-the-art (SOTA) on the IWSLT2011 test set, outperforming the current SOTA model by 1.3


page 1

page 2

page 3

page 4


Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation

Transcripts generated by automatic speech recognition (ASR) systems for ...

RescoreBERT: Discriminative Speech Recognition Rescoring with BERT

Second-pass rescoring is an important component in automatic speech reco...

LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech

Self-Supervised Learning (SSL) using huge unlabeled data has been succes...

Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors

Performance of spoken language understanding (SLU) can be degraded with ...

Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection

With the increased applications of automatic speech recognition (ASR) in...

DNN No-Reference PSTN Speech Quality Prediction

Classic public switched telephone networks (PSTN) are often a black box ...

Please sign up or login with your details

Forgot password? Click here to reset