Papers with Code 아카이브

Speech Recognition

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

하위 태스크
11
평가표
236
보존된 평가 기록
398

Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.

<span style="color:grey; opacity: 0.6">( Image credit: SpecAugment )</span>

평가 결과

데이터셋과 평가 조건을 선택해 성능·논문·코드를 비교하세요. 보존된 Papers with Code 기록으로, 최신 순위는 아닙니다.

DIRHA English WSJ

원본 태스크: Speech Recognition / Distant Speech Recognition

평가 기록 3건

Fongbe audio

원본 태스크: Speech Recognition

평가 기록 3건

LRS3-TED

원본 태스크: Speech Recognition / Visual Speech Recognition

평가 기록 3건

Mandarin Chinese

원본 태스크: Speech Recognition / Accented Speech Recognition / Speech Synthesis

평가 기록 3건

SPGISpeech

원본 태스크: Speech Recognition

평가 기록 3건

VIVOS

원본 태스크: Speech Recognition

평가 기록 3건

WSJ eval93

원본 태스크: Speech Recognition

평가 기록 3건

AISHELL-2

원본 태스크: Speech Recognition

평가 기록 2건

AMI IMH

원본 태스크: Speech Recognition

평가 기록 2건

AMI SDM1

원본 태스크: Speech Recognition

평가 기록 2건

Blizzard Challenge 2013

원본 태스크: Speech Recognition / Accented Speech Recognition / Speech Synthesis

평가 기록 2건

CHiME clean

원본 태스크: Speech Recognition / Noisy Speech Recognition

평가 기록 2건

CHiME-4 real 6ch

원본 태스크: Speech Recognition / Distant Speech Recognition

평가 기록 2건

Common Voice

원본 태스크: Speech Recognition

평가 기록 2건

GRID corpus (mixed-speech)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

LibriCSS

원본 태스크: Speech Recognition

평가 기록 2건

Lip2Wav (Chem)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

Lip2Wav (Chess)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

Lip2Wav (DL)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

Lip2Wav (EH)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

Lip2Wav (HS)

원본 태스크: Speech Recognition / Visual Speech Recognition / Lip to Speech Synthesis / Speaker-Specific Lip to Speech Synthesis

평가 기록 2건

LRS2

원본 태스크: Speech Recognition / Visual Speech Recognition

평가 기록 2건

LRS3-TED

원본 태스크: Speech Recognition / Automatic Speech Recognition (ASR)

평가 기록 2건

RealMAN

원본 태스크: Speech Recognition / Automatic Speech Recognition (ASR)

평가 기록 2건

Sagalee

원본 태스크: Speech Recognition / Automatic Speech Recognition (ASR)

평가 기록 2건

TED-LIUM

원본 태스크: Speech Recognition

평가 기록 2건

VoxForge Commonwealth

원본 태스크: Speech Recognition / Accented Speech Recognition

평가 기록 2건

VoxForge European

원본 태스크: Speech Recognition / Accented Speech Recognition

평가 기록 2건

VoxForge Indian

원본 태스크: Speech Recognition / Accented Speech Recognition

평가 기록 2건

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.