Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection
This addresses the need for more readable and usable ASR transcripts for applications like machine translation and dialogue systems, though it is incremental as it builds on existing transformer-based methods.
The paper tackles the problem of improving automatic speech recognition transcripts by jointly predicting punctuation and detecting disfluencies in real time, proposing a Controllable Time-delay Transformer model that outperforms previous state-of-the-art models on F-scores and achieves competitive inference speed.
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performance of subsequent applications, such as machine translation, dialogue systems, and so forth. In this paper, we propose a Controllable Time-delay Transformer (CT-Transformer) model that jointly completes the punctuation prediction and disfluency detection tasks in real time. The CT-Transformer model facilitates freezing partial outputs with controllable time delay to fulfill the real-time constraints in partial decoding required by subsequent applications. We further propose a fast decoding strategy to minimize latency while maintaining competitive performance. Experimental results on the IWSLT2011 benchmark dataset and an in-house Chinese annotated dataset demonstrate that the proposed approach outperforms the previous state-of-the-art models on F-scores and achieves a competitive inference speed.