SOTAVerified

The IBM 2016 English Conversational Telephone Speech Recognition System

2016-04-27Unverified0· sign in to hype

George Saon, Tom Sercu, Steven Rennie, Hong-Kwang J. Kuo

Unverified — Be the first to reproduce this paper.

Reproduce

Abstract

We describe a collection of acoustic and language modeling techniques that lowered the word error rate of our English conversational telephone LVCSR system to a record 6.6% on the Switchboard subset of the Hub5 2000 evaluation testset. On the acoustic side, we use a score fusion of three strong models: recurrent nets with maxout activations, very deep convolutional nets with 3x3 kernels, and bidirectional long short-term memory nets which operate on FMLLR and i-vector features. On the language modeling side, we use an updated model "M" and hierarchical neural network LMs.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
swb_hub_500 WER fullSWBCHRNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language modelPercentage error12.2Unverified
Switchboard + Hub500RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language modelPercentage error6.6Unverified
Switchboard + Hub500IBM 2016Percentage error6.9Unverified

Reproductions