LSTM-Based One-Pass Decoder for Low-Latency Streaming
Javier Jorge, Adrià Giménez, Javier Iranzo-Sánchez, Joan Albert Silvestre-Cerdà, Jorge Civera, Albert Sanchís, Alfons Juan
Abstract
Current state-of-the-art models based on Long-Short Term Memory (LSTM) networks have been extensively used in ASR to improve performance. However, using LSTMs under a streaming setup is not straightforward due to real-time constraints. In this paper we present a novel streaming decoder that includes a bidirectional LSTM acoustic model as well as an unidirectional LSTM language model to perform the decoding efficiently while keeping the performance comparable to that of an off-line setup. We perform a one-pass decoding using a sliding window scheme for a bidirectional LSTM acoustic model and an LSTM language model. This has been implemented and assessed under a pure streaming setup, and deployed into our production systems. We report WER and latency figures for the well-known LibriSpeech and TED-LIUM tasks, obtaining competitive WER results with low-latency responses.
BibTeX
@inproceedings{icassp2020_lstmbasedonepass,
title = {LSTM-Based One-Pass Decoder for Low-Latency Streaming},
author = {Javier Jorge and Adrià Giménez and Javier Iranzo-Sánchez and Joan Albert Silvestre-Cerdà and Jorge Civera and Albert Sanchís and Alfons Juan},
booktitle = {ICASSP 2020},
year = {2020}
}