# The IBM 2015 English Conversational Telephone Speech Recognition System

arXiv: https://arxiv.org/abs/1505.05899 · HTML: https://mlsanity.com/paper/1505.05899/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2015.

## Built on by (most cited first, 6 of 6)

- [Large Language Models in Law: A Survey](https://mlsanity.com/paper/2312.03718/) (2023)
- [Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey](https://mlsanity.com/paper/2307.00309/) (2023)
- [A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect](https://mlsanity.com/paper/2105.03409/) (2021)
- [CrossedWires: A Dataset of Syntactically Equivalent but Semantically Disparate Deep Learning Models](https://mlsanity.com/paper/2108.12768/) (2021)
- [A Neural Rejection System Against Universal Adversarial Perturbations in Radio Signal Classification](https://mlsanity.com/paper/2506.11901/) (2025)
- [EmoAugNet: A Signal-Augmented Hybrid CNN-LSTM Framework for Speech Emotion Recognition](https://mlsanity.com/paper/2508.06321/) (2025)

## Abstract (arXiv)

We describe the latest improvements to the IBM English conversational telephone speech recognition system. Some of the techniques that were found beneficial are: maxout networks with annealed dropout rates; networks with a very large number of outputs trained on 2000 hours of data; joint modeling of partially unfolded recurrent neural networks and convolutional nets by combining the bottleneck and output layers and retraining the resulting model; and lastly, sophisticated language model rescoring with exponential and neural network LMs. These techniques result in an 8.0% word error rate on the Switchboard part of the Hub5-2000 evaluation test set which is 23% relative better than our previous best published result.