Joint Endpointing And Decoding With End-To-End Models

The tradeoff between word error rate (WWER)and latency is very aimportant for streaming automatic speech recognition (ASR) applications. We want the system to endpoint and close the microphone as quickly as possible, without degrading WER. Conventional ASR systems rely on a separately trained endpointing module, which interacts with the acoustic, pronunciation and language model (AM, PM, and LM) components, and can result in a higher W I iR or a larger latency. In going with the all -neural spirit of end -to -end (11,211) models, which fold the AM, PM and LM into a single neural network, in this work we look at folding the endpointer into this E2E model to assist with the endpointing task. We refer to this jointly optimized model which performs both recognition and endpointing as an E2E enpointer. On a large vocabulary Voice Search task, we show that the combination of such an Ii2E endpoiner with a conventional endpointer results in no quality degradation, while reducing latency by more than a factor of 2 compared to using a separate endpointer with the E2E, model.