The IBM 2016 English Conversational Telephone Speech Recognition System
This work addresses speech recognition for telephone conversations, representing an incremental improvement in a specific domain.
The paper tackled the problem of English conversational telephone speech recognition by developing a system that achieved a record 6.6% word error rate on the Switchboard subset of the Hub5 2000 evaluation testset.
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.