Scaling Up Online Speech Recognition Using ConvNets
INTERSPEECH(2020)
摘要
We design an online end-to-end speech recognition system based on Time-Depth Separable (TDS) convolutions and Connectionist Temporal Classification (CTC). We improve the core TDS architecture in order to limit the future context and hence reduce latency while maintaining accuracy. The system has almost three times the throughput of a well tuned hybrid ASR baseline while also having lower latency and a better word error rate. Also important to the efficiency of the recognizer is our highly optimized beam search decoder. To show the impact of our design choices, we analyze throughput, latency, accuracy, and discuss how these metrics can be tuned based on the user requirements.
更多查看译文
关键词
online speech recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络