A Pruned Rnnlm Lattice-Rescoring Algorithm for Automatic Speech Recognition

118 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation (2018, methodology): “We also considered a RNNLM with letter-based features and importance sampling [15], coupled with a pruned approach to lattice-rescoring [14].”
Semi-Orthogonal Low-Rank Matrix Factorization for Deep Neural Networks (2018, methodology): “The ﬁrst-pass decoding uses a 3-gram backoff LM which we rescore with an RNNLM [15, 16], with explicit modeling for silence probabilities [17].”
LSTM Language Models for LVCSR in First-Pass Decoding and Lattice-Rescoring (2019, background): “Examples for this approach are [15, 16, 17, 18, 19, 20] where a variety of heuristics is proposed to speed up the rescoring process.”
The STC System for the CHiME-6 Challenge (2020, background): “The second one is excluding one-third of all microphones with worst Envelope Variance [21] scores from the beamforming.”