2019/09/26 by Qingyun Dou, Yiting Lu, Dou, Qingyun +5 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #Computation and Language (cs.CL) #FOS: Computer and information sciences #FOS: Electrical engineering #I.2 #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1909.12289
openalex publication_date 2019/09/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach, teacher forcing, guides a model with reference output history during training. The problem is that the model is unlikely to recover from its mistakes during inference, where the reference output is replaced by generated output. Several approaches deal with this problem, largely by guiding the model with generated output history. To make training stable, these approaches often require a heuristic schedule or an auxiliary classifier. This paper introduces attention forcing, which guides the model with generated output history and reference attention. This approach can train the model to recover from its mistakes, in a stable fashion, without the need for a schedule or a classifier. In addition, it allows the model to generate output sequences aligned with the references, which can be important for cascaded systems like many speech synthesis systems. Experiments on speech synthesis show that attention forcing yields significant performance gain. Experiments on machine translation show that for tasks where various re-orderings of the output are valid, guiding the model with generated output history is challenging, while guiding the model with reference attention is beneficial.