SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.07263 · 2020

Single headed attention based sequence-to-sequence model for state-of-the-art results on Switchboard

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.

Abstract

It is generally believed that direct sequence-to-sequence (seq2seq) speech recognition models are competitive with hybrid models only when a large amount of data, at least a thousand hours, is available for training. In this paper, we show that state-of-the-art recognition performance can be achieved on the Switchboard-300 database using a single headed attention, LSTM based model. Using a cross-utterance language model, our single-pass speaker independent system reaches 6.4% and 12.5% word error rate (WER) on the Switchboard and CallHome subsets of Hub5'00, without a pronunciation lexicon. While careful regularization and data augmentation are crucial in achieving this level of performance, experiments on Switchboard-2000 show that nothing is more useful than more data. Overall, the combination of various regularizations and a simple but fairly large model results in a new state of the art, 4.7% and 7.8% WER on the Switchboard and CallHome sets, using SWB-2000 without any external data resources.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2001.07263")
get_code_for_paper("2001.07263")
have("2001.07263")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2001.07263.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2001.07263.svg)](https://syntology.ai/paper/2001.07263)

Connect an agent — have() is free.