CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition
This addresses the need for efficient and accurate end-to-end speech recognition systems, suitable for various ASR scenarios, though it appears incremental as it builds on existing encoder-decoder frameworks.
The paper tackles the problem of sequence transduction in automatic speech recognition (ASR) by proposing a Continuous Integrate-and-Fire (CIF) mechanism, achieving a word error rate of 2.86% on Librispeech test-clean and setting a new state-of-the-art on a Mandarin telephone ASR benchmark.
In this paper, we propose a novel soft and monotonic alignment mechanism used for sequence transduction. It is inspired by the integrate-and-fire model in spiking neural networks and employed in the encoder-decoder framework consists of continuous functions, thus being named as: Continuous Integrate-and-Fire (CIF). Applied to the ASR task, CIF not only shows a concise calculation, but also supports online recognition and acoustic boundary positioning, thus suitable for various ASR scenarios. Several support strategies are also proposed to alleviate the unique problems of CIF-based model. With the joint action of these methods, the CIF-based model shows competitive performance. Notably, it achieves a word error rate (WER) of 2.86% on the test-clean of Librispeech and creates new state-of-the-art result on Mandarin telephone ASR benchmark.