Deep Speech: Scaling up end-to-end speech recognition

Bryan Catanzaro; Greg Diamos; Erich Elsen; Ryan Prenger; Sanjeev Satheesh; Shubho Sengupta; Adam Coates; Andrew Y. Ng

doi:https://doi.org/10.4230/oasics.slate.2021.16

Deep Speech: Scaling up end-to-end speech recognition

2014 · arXiv (Cornell University) · 1,519 citations · 5 from inside this corpus

Bryan Catanzaro, Greg Diamos, Erich Elsen, Ryan Prenger, Sanjeev Satheesh, Shubho Sengupta, Adam Coates, Andrew Y. Ng

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

16 of 16 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Deep Speech: Scaling up end-to-end speech recognitionLegacy edge — source detail unavailable
Listen, attend and spell: A neural network for large vocabulary conversational speech rec…→Deep Speech: Scaling up end-to-end speech recognitionLegacy edge — source detail unavailable
Privacy-Preserving Deep Learning→Deep Speech: Scaling up end-to-end speech recognitionLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Deep Speech: Scaling up end-to-end speech recognitionLegacy edge — source detail unavailable
Unsupervised Data Augmentation for Consistency Training→Deep Speech: Scaling up end-to-end speech recognitionLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Bidirectional recurrent neural networksLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Improving neural networks by preventing co-adaptation of feature detectorsLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Connectionist temporal classificationLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Deep Sparse Rectifier Neural NetworksLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Kaldi Speech Recognition ToolkitLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→On the importance of initialization and momentum in deep learningLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Sequence to Sequence Learning with Neural NetworksLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Towards End-To-End Speech Recognition with Recurrent Neural NetworksLegacy edge — source detail unavailable
Deep Speech: Scaling up end-to-end speech recognition→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
On the importance of initialization and momentum in deep learning→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
On the importance of initialization and momentum in deep learning→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
On the importance of initialization and momentum in deep learning→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
Improving neural networks by preventing co-adaptation of feature detectors→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
Improving neural networks by preventing co-adaptation of feature detectors→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Acoustic Modeling Using Deep Belief Networks→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Towards End-To-End Speech Recognition with Recurrent Neural Networks→Kaldi Speech Recognition ToolkitLegacy edge — source detail unavailable
Towards End-To-End Speech Recognition with Recurrent Neural Networks→Connectionist temporal classificationLegacy edge — source detail unavailable
Towards End-To-End Speech Recognition with Recurrent Neural Networks→Bidirectional recurrent neural networksLegacy edge — source detail unavailable
Towards End-To-End Speech Recognition with Recurrent Neural Networks→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
Connectionist temporal classification→Bidirectional recurrent neural networksLegacy edge — source detail unavailable
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
Deep Neural Networks for Acoustic Modeling in Speech Recognition→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
Deep Neural Networks for Acoustic Modeling in Speech Recognition→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→On the importance of initialization and momentum in deep learningLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Acoustic Modeling Using Deep Belief NetworksLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Towards End-To-End Speech Recognition with Recurrent Neural NetworksLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Connectionist temporal classificationLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
Listen, attend and spell: A neural network for large vocabulary conversational speech rec…→Kaldi Speech Recognition ToolkitLegacy edge — source detail unavailable
Listen, attend and spell: A neural network for large vocabulary conversational speech rec…→Towards End-To-End Speech Recognition with Recurrent Neural NetworksLegacy edge — source detail unavailable
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Kaldi Speech Recognition ToolkitLegacy edge — source detail unavailable
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Towards End-To-End Speech Recognition with Recurrent Neural NetworksLegacy edge — source detail unavailable
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition→Listen, attend and spell: A neural network for large vocabulary conversational speech rec…Legacy edge — source detail unavailable
Sequence to Sequence Learning with Neural Networks→Connectionist temporal classificationLegacy edge — source detail unavailable
Sequence to Sequence Learning with Neural Networks→Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech RecognitionLegacy edge — source detail unavailable
Sequence to Sequence Learning with Neural Networks→Deep Neural Networks for Acoustic Modeling in Speech RecognitionLegacy edge — source detail unavailable
Unsupervised Data Augmentation for Consistency Training→SpecAugment: A Simple Data Augmentation Method for Automatic Speech RecognitionLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Bidirectional recurrent neural networks	1997	10,294
Improving neural networks by preventing co-adaptation of feature detectors	2012	6,653
Connectionist temporal classification	2006	5,582
Deep Sparse Rectifier Neural Networks	2011	5,428
Kaldi Speech Recognition Toolkit	2024	4,895
On the importance of initialization and momentum in deep learning	2013	3,523
Sequence to Sequence Learning with Neural Networks	2014	3,514
Context-Dependent Pre-Trained Deep Neural Networks for Large-Vocabulary Speech Recognition	2011	3,089
Deep Neural Networks for Acoustic Modeling in Speech Recognition	2012	1,907
Towards End-To-End Speech Recognition with Recurrent Neural Networks	2014	1,855
Acoustic Modeling Using Deep Belief Networks	2011	1,752

What cites it, inside the corpus

Paper	Year	Cited
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition	2019	3,619
Listen, attend and spell: A neural network for large vocabulary conversational speech rec…	2016	2,359
Privacy-Preserving Deep Learning	2015	2,325
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin	2015	2,181
Unsupervised Data Augmentation for Consistency Training	2019	1,624

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Speech Recognition and Synthesis	Computer Science
Speech and Audio Processing	Computer Science
Music and Audio Processing	Computer Science

Is this record sound?

partial

One field of this record is missing or disagrees with another. What is shown below is what the source publishes.

supports8 author record(s) attached.
supports42 reference(s) recorded.
weakensThe DOI names 2021 but the record dates this to 2,014. One of the two is about a different paper.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:58+00:00.

sha256 88a60cdbb94c6a13…