2017/10/26 by Yanzhang He, He, Yanzhang, Rohit Prabhavalkar +9 · 3 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Music and Audio Processing #Natural Language Processing Techniques #Speech Recognition and Synthesis #cs.CL
paper · pdf · doi:10.48550/arxiv.1710.09617
To appear in Proceedings of IEEE ASRU 2017
arxiv created 2017/10/26 · openalex publication_date 2017/10/26 · arxiv updated 2017/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We develop streaming keyword spotting systems using a recurrent neural network transducer (RNN-T) model: an all-neural, end-to-end trained, sequence-to-sequence model which jointly learns acoustic and language model components. Our models are trained to predict either phonemes or graphemes as subword units, thus allowing us to detect arbitrary keyword phrases, without any out-of-vocabulary words. In order to adapt the models to the requirements of keyword spotting, we propose a novel technique which biases the RNN-T system towards a specific keyword of interest. Our systems are compared against a strong sequence-trained, connectionist temporal classification (CTC) based "keyword-filler" baseline, which is augmented with a separate phoneme language model. Overall, our RNN-T system with the proposed biasing technique significantly improves performance over the baseline system.