# The IBM 2016 English Conversational Telephone Speech Recognition System

arXiv: https://arxiv.org/abs/1604.08242 · HTML: https://mlsanity.com/paper/1604.08242/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Apr 2016.

## Built on by (most cited first, 5 of 5)

- [CitationIE: Leveraging the Citation Graph for Scientific Information Extraction](https://mlsanity.com/paper/2106.01560/) (2021)
- [A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training](https://mlsanity.com/paper/2103.07554/) (2021)
- [A Treatise On FST Lattice Based MMI Training](https://mlsanity.com/paper/2210.08918/) (2022)
- [Lattice Rescoring Based on Large Ensemble of Complementary Neural Language Models](https://mlsanity.com/paper/2312.12764/) (2023)
- [Dialect and Gender Bias in YouTube's Spanish Captioning System](https://mlsanity.com/paper/2602.24002/) (2026)

## Abstract (arXiv)

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.