Who Cited It

Librispeech: An ASR corpus based on public domain audio books

2015 · 6,095 citations · 5 from inside this corpus

Vassil Panayotov low, Guoguo Chen low, Daniel Povey, Sanjeev Khudanpur

This paper introduces a new corpus of read English speech, suitable for training and evaluating speech recognition systems. The LibriSpeech corpus is derived from audiobooks that are part of the LibriVox project, and contains 1000 hours of speech sampled at 16 kHz. We have made the corpus freely available for download, along with separately prepared language-model training data and pre-built language models. We show that acoustic models trained on LibriSpeech give lower error rate on the Wall Street Journal (WSJ) test sets than models trained on WSJ itself. We are also releasing Kaldi scripts that make it easy to build these systems.

Librispeech: An ASR corpus based on public domain audio books (2015)Librispeech: An ASR corpus ba…Identification of common molecular subsequences (1981)Identification of common mole…Kaldi Speech Recognition Toolkit (2024)Kaldi Speech Recognition Tool…SRILM - an extensible language modeling toolkit (2002)SRILM - an extensible languag…Improved backing-off for M-gram language modeling (2002)Improved backing-off for M-gr…SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition (2019)SpecAugment: A Simple Data Au…Conformer: Convolution-augmented Transformer for Speech Recognition (2020)Conformer: Convolution-augmen…In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication (2020)In-Kernel Aggregation and Bro…Deep Speech 2: End-to-End Speech Recognition in English and Mandarin (2015)Deep Speech 2: End-to-End Spe…WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing (2022)WavLM: Large-Scale Self-Super…
9 of 9 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.

What this paper cites, inside the corpus

PaperYearCited
Identification of common molecular subsequences198110,144
Kaldi Speech Recognition Toolkit20244,895
SRILM - an extensible language modeling toolkit20024,404
Improved backing-off for M-gram language modeling20021,500

What cites it, inside the corpus

PaperYearCited
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition20193,619
Conformer: Convolution-augmented Transformer for Speech Recognition20202,867
In-Kernel Aggregation and Broadcast Acceleration for Distributed Communication20202,452
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin20152,181
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing20221,843

Links

Download BibTeX · Download RIS · DOI · OpenAlex record

Topics

Speech Recognition and SynthesisComputer Science
Music and Audio ProcessingComputer Science
Speech and Audio ProcessingComputer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

  • supports4 author record(s) attached.
  • supports29 reference(s) recorded.
  • supportsThe DOI's year agrees with the publication year.
  • supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:43+00:00.

sha256 5cad55ac5d4d41e1…