The IBM 2016 English Conversational Telephone Speech Recognition System

27 Apr 2016  ·  George Saon, Tom Sercu, Steven Rennie, Hong-Kwang J. Kuo ·

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.

PDF Abstract

Code
Add Remove Mark official

No code implementations yet. Submit your code now

Datasets

  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Speech Recognition swb_hub_500 WER fullSWBCH RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language model Percentage error 12.2 # 5
Compare
Speech Recognition Switchboard + Hub500 RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language model Percentage error 6.6 # 7
Compare
Speech Recognition Switchboard + Hub500 IBM 2016 Percentage error 6.9 # 9
Compare

Methods
Add Remove

Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy