TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Speech/Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR)

16 benchmarks3012 papers

Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.

Benchmarks

Automatic Speech Recognition (ASR) on LRS2

Test WER

Automatic Speech Recognition (ASR) on RealMAN

CER

Automatic Speech Recognition (ASR) on Sagalee

Test WER

Automatic Speech Recognition (ASR) on LRS3-TED

WERWord Error Rate (WER)

Automatic Speech Recognition (ASR) on VibraVox (forehead accelerometer)

Test PER

Automatic Speech Recognition (ASR) on VibraVox (headset microphone)

Test PER

Automatic Speech Recognition (ASR) on VibraVox (rigid in-ear microphone)

Test PER

Automatic Speech Recognition (ASR) on VibraVox (soft in-ear microphone)

Test PER

Automatic Speech Recognition (ASR) on VibraVox (temple vibration pickup)

Test PER

Automatic Speech Recognition (ASR) on VibraVox (throat microphone)

Test PER

Automatic Speech Recognition (ASR) on HUI speech corpus

WER (%)

Automatic Speech Recognition (ASR) on M-AILabs speech dataset

WER (%)

Automatic Speech Recognition (ASR) on The Spoken Wikipedia Corpora

WER (%)

Automatic Speech Recognition (ASR) on VoxPopuli

WER (%)

Automatic Speech Recognition (ASR) on Voxforge German

WER (%)