SOTAVerified

Speech Recognition

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.

( Image credit: SpecAugment )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 6433 papers

TitleStatusHype
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech—0
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine—0
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers—0
VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis—0
A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting—0
First Steps Towards Voice Anonymization for Code-Switching SpeechCode0
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech EnhancementCode2
VOICE CONTROL ROBOT USING ARDUINO MANAGEMENT SYSTEM PROJECT.—0
Lightweight Target-Speaker-Based Overlap Transcription for Practical Streaming ASR—0
Multimodal Representation Learning and Fusion—0
Show:102550
← PrevPage 1 of 644Next →
All datasetsLibriSpeech test-cleanLibriSpeech test-otherSwitchboard + Hub500TIMITAISHELL-1WSJ eval92Common Voice Germanswb_hub_500 WER fullSWBCHTUDACommon Voice FrenchCommon Voice SpanishMediaSpeech

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1wav2vecWER for Arabic0.96—Unverified
2DeepspeechWER for French0.47—Unverified
3GoogleWER for Arabic0.45—Unverified
4VOSKWER for Arabic0.31—Unverified
5SileroWER for Spanish0.31—Unverified
6AzureWER for Arabic0.3—Unverified
7WitWER for Arabic0.23—Unverified
8QuartznetWER for Arabic0.13—Unverified