pith. sign in

arxiv: 1811.04897 · v1 · pith:NDZSRUR7new · submitted 2018-11-12 · 💻 cs.CL

Multi-encoder multi-resolution framework for end-to-end speech recognition

classification 💻 cs.CL
keywords modelattentionend-to-endjointarchitecturesframeworkinformationmemr
0
0 comments X
read the original abstract

Attention-based methods and Connectionist Temporal Classification (CTC) network have been promising research directions for end-to-end Automatic Speech Recognition (ASR). The joint CTC/Attention model has achieved great success by utilizing both architectures during multi-task training and joint decoding. In this work, we present a novel Multi-Encoder Multi-Resolution (MEMR) framework based on the joint CTC/Attention model. Two heterogeneous encoders with different architectures, temporal resolutions and separate CTC networks work in parallel to extract complimentary acoustic information. A hierarchical attention mechanism is then used to combine the encoder-level information. To demonstrate the effectiveness of the proposed model, experiments are conducted on Wall Street Journal (WSJ) and CHiME-4, resulting in relative Word Error Rate (WER) reduction of 18.0-32.1%. Moreover, the proposed MEMR model achieves 3.6% WER in the WSJ eval92 test set, which is the best WER reported for an end-to-end system on this benchmark.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.