This is the authors' abstract. We don't add key points for this paper.
Language models (LM) have been widely deployed in modern ASR systems. The LM is often trained by minimizing its perplexity on speech transcript. However, few studies try to discriminate a "gold" reference against inferior hypotheses. In this work, we propose a large margin language model (LMLM). LMLM is a general framework that enforces an LM to assign a higher score to the "gold" reference, and a lower one to the inferior hypothesis. The general framework is applied to three pretrained LM architectures: left-to-right LSTM, transformer encoder, and transformer decoder. Results show that LMLM can significantly outperform traditional LMs that are trained by minimizing perplexity. Especially for challenging noisy cases. Finally, among the three architectures, transformer encoder achieves the best performance.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2021) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: