SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1506.07503 · 2015

Attention-Based Models for Speech Recognition

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. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We show that while an adaptation of the model used for machine translation in reaches a competitive 18.7% phoneme error rate (PER) on the TIMIT phoneme recognition task, it can only be applied to utterances which are roughly as long as the ones it was trained on. We offer a qualitative explanation of this failure and propose a novel and generic method of adding location-awareness to the attention mechanism to alleviate this issue. The new method yields a model that is robust to long inputs and achieves 18% PER in single utterances and 20% in 10-times longer (repeated) utterances. Finally, we propose a change to the at- tention mechanism that prevents it from concentrating too much on single frames, which further reduces PER to 17.6% level.

For agents

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

get_harvested_code_for_paper("1506.07503")
get_code_for_paper("1506.07503")
have("1506.07503")

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

curl https://syntology.ai/api/ran/1506.07503.json

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

[![Syntology run record](https://syntology.ai/api/ran/1506.07503.svg)](https://syntology.ai/paper/1506.07503)

Connect an agent — have() is free.