Language model integration based on memory control for sequence to sequence speech recognition

by   Jaejin Cho, et al.

In this paper, we explore several new schemes to train a seq2seq model to integrate a pre-trained LM. Our proposed fusion methods focus on the memory cell state and the hidden state in the seq2seq decoder long short-term memory (LSTM), and the memory cell state is updated by the LM unlike the prior studies. This means the memory retained by the main seq2seq would be adjusted by the external LM. These fusion methods have several variants depending on the architecture of this memory cell update and the use of memory cell and hidden states which directly affects the final label inference. We performed the experiments to show the effectiveness of the proposed methods in a mono-lingual ASR setup on the Librispeech corpus and in a transfer learning setup from a multilingual ASR (MLASR) base model to a low-resourced language. In Librispeech, our best model improved WER by 3.7 other relatively to the shallow fusion baseline, with multi-level decoding. In transfer learning from an MLASR base model to the IARPA Babel Swahili model, the best scheme improved the transferred model on eval set by 9.9 CER, WER relatively to the 2-stage transfer baseline.


page 1

page 2

page 3

page 4


Transfer learning of language-independent end-to-end ASR with language model fusion

This work explores better adaptation methods to low-resource languages u...

Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relati...

Improved training of end-to-end attention models for speech recognition

Sequence-to-sequence attention-based models on subword units allow simpl...

Analysis of Multilingual Sequence-to-Sequence speech recognition systems

This paper investigates the applications of various multilingual approac...

Efficient Transfer Learning Schemes for Personalized Language Modeling using Recurrent Neural Network

In this paper, we propose an efficient transfer leaning methods for trai...

Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline

This paper describes a new baseline system for automatic speech recognit...

Please sign up or login with your details

Forgot password? Click here to reset