# Exploiting Nontrivial Connectivity for Automatic Speech Recognition

Source: [Exploiting Nontrivial Connectivity for Automatic Speech Recognition](<https://www.sota2.com/research/paper/68fa63d81e209131cea01404>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T20:51:10.308Z

Authors: Marius Paraschiv, Lasse Borgholt, Tycho Max Sylvester Tax, Marco Singh, Lars Maal{\\o}e

Published: 2017-11-28T13:13:41.000Z

## Abstract

Nontrivial connectivity has allowed the training of very deep networks by addressing the problem of vanishing gradients and offering a more efficient method of reusing parameters. In this paper we make a comparison between residual networks, densely-connected networks and highway networks on an image classification task. Next, we show that these methodologies can easily be deployed into automatic speech recognition and provide significant improvements to existing models.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1711.10271>)

[PDF](<https://arxiv.org/pdf/1711.10271.pdf>)