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

Showing 110 of 6433 papers

TitleStatusHype
NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech0
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine0
WhisperKit: On-device Real-time ASR with Billion-Scale Transformers0
VisualSpeaker: Visually-Guided 3D Avatar Lip Synthesis0
A Hybrid Machine Learning Framework for Optimizing Crop Selection via Agronomic and Economic Forecasting0
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 ASR0
Multimodal Representation Learning and Fusion0
Show:102550
← PrevPage 1 of 644Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1HMM-TDNN + pNorm + speed up/down speechPercentage error19.3Unverified
2DNN + DropoutPercentage error19.1Unverified
3HMM-DNN +sMBRPercentage error18.4Unverified
4HMM-TDNN + iVectorsPercentage error17.1Unverified
5CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWBPercentage error16Unverified
6HMM-TDNN trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + Fisher (10% / 15.1% respectively trained on SWBD only)Percentage error13.3Unverified
7HMM-BLSTM trained with MMI + data augmentation (speed) + iVectors + 3 regularizations + FisherPercentage error13Unverified
8RNN + VGG + LSTM acoustic model trained on SWB+Fisher+CH, N-gram + "model M" + NNLM language modelPercentage error12.2Unverified
9VGG/Resnet/LACE/BiLSTM acoustic model trained on SWB+Fisher+CH, N-gram + RNNLM language model trained on Switchboard+Fisher+Gigaword+BroadcastPercentage error11.9Unverified
10ResNet + BiLSTMs acoustic modelPercentage error10.3Unverified