Future Vector Enhanced LSTM Language Model for LVCSR

07/31/2020
by   Qi Liu, et al.
0

Language models (LM) play an important role in large vocabulary continuous speech recognition (LVCSR). However, traditional language models only predict next single word with given history, while the consecutive predictions on a sequence of words are usually demanded and useful in LVCSR. The mismatch between the single word prediction modeling in trained and the long term sequence prediction in read demands may lead to the performance degradation. In this paper, a novel enhanced long short-term memory (LSTM) LM using the future vector is proposed. In addition to the given history, the rest of the sequence will be also embedded by future vectors. This future vector can be incorporated with the LSTM LM, so it has the ability to model much longer term sequence level information. Experiments show that, the proposed new LSTM LM gets a better result on BLEU scores for long term sequence prediction. For the speech recognition rescoring, although the proposed LSTM LM obtains very slight gains, the new model seems obtain the great complementary with the conventional LSTM LM. Rescoring using both the new and conventional LSTM LMs can achieve a very large improvement on the word error rate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2017

Lattice Rescoring Strategies for Long Short Term Memory Language Models in Speech Recognition

Recurrent neural network (RNN) language models (LMs) and Long Short Term...
research
06/16/2021

On the long-term learning ability of LSTM LMs

We inspect the long-term learning ability of Long Short-Term Memory lang...
research
04/02/2020

Towards Relevance and Sequence Modeling in Language Recognition

The task of automatic language identification (LID) involving multiple d...
research
05/08/2018

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

Sequence-to-sequence attention-based models on subword units allow simpl...
research
03/10/2016

Personalized Speech recognition on mobile devices

We describe a large vocabulary speech recognition system that is accurat...
research
04/04/2017

A History of Metaheuristics

This chapter describes the history of metaheuristics in five distinct pe...
research
08/19/2020

Cross-Utterance Language Models with Acoustic Error Sampling

The effective exploitation of richer contextual information in language ...

Please sign up or login with your details

Forgot password? Click here to reset