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 551600 of 6433 papers

TitleStatusHype
Discriminative Multi-modality Speech RecognitionCode1
CTC-synchronous Training for Monotonic Attention ModelCode1
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global ContextCode1
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applicationsCode1
Meta-Transfer Learning for Code-Switched Speech RecognitionCode1
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact CentersCode1
How to Teach DNNs to Pay Attention to the Visual Modality in Speech RecognitionCode1
Transformer based Grapheme-to-Phoneme ConversionCode1
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and PruningCode1
Can We Read Speech Beyond the Lips? Rethinking RoI Selection for Deep Visual Speech RecognitionCode1
Untangling in Invariant Speech RecognitionCode1
Natural Language Processing Advancements By Deep Learning: A SurveyCode1
Universal Phone Recognition with a Multilingual Allophone SystemCode1
Multilingual Twitter Corpus and Baselines for Evaluating Demographic Bias in Hate Speech RecognitionCode1
Imputer: Sequence Modelling via Imputation and Dynamic ProgrammingCode1
Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T LossCode1
Unsupervised pretraining transfers well across languagesCode1
Continuous speech separation: dataset and analysisCode1
Multi-task self-supervised learning for Robust Speech RecognitionCode1
FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural NetworksCode1
Libri-Light: A Benchmark for ASR with Limited or No SupervisionCode1
Common Voice: A Massively-Multilingual Speech CorpusCode1
A Resource for Computational Experiments on MapudungunCode1
Deep Contextualized Acoustic Representations For Semi-Supervised Speech RecognitionCode1
Effectiveness of self-supervised pre-training for speech recognitionCode1
Generative Pre-Training for Speech with Autoregressive Predictive CodingCode1
GPU-Accelerated Viterbi Exact Lattice Decoder for Batched Online and Offline Speech RecognitionCode1
Improving Transformer-based Speech Recognition Using Unsupervised Pre-trainingCode1
vq-wav2vec: Self-Supervised Learning of Discrete Speech RepresentationsCode1
FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio ProcessingCode1
Espresso: A Fast End-to-end Neural Speech Recognition ToolkitCode1
DOVER: A Method for Combining Diarization OutputsCode1
Emotionless: Privacy-Preserving Speech Analysis for Voice AssistantsCode1
Attention model for articulatory features detectionCode1
BERTphone: Phonetically-Aware Encoder Representations for Utterance-Level Speaker and Language RecognitionCode1
When Does Label Smoothing Help?Code1
CIF: Continuous Integrate-and-Fire for End-to-End Speech RecognitionCode1
RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data AugmentationCode1
Transformers with convolutional context for ASRCode1
SpecAugment: A Simple Data Augmentation Method for Automatic Speech RecognitionCode1
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain AdaptationCode1
wav2vec: Unsupervised Pre-training for Speech RecognitionCode1
STFNets: Learning Sensing Signals from the Time-Frequency Perspective with Short-Time Fourier Neural NetworksCode1
A Fully Differentiable Beam Search DecoderCode1
A Comprehensive Survey on Graph Neural NetworksCode1
Speech and Speaker Recognition from Raw Waveform with SincNetCode1
The PyTorch-Kaldi Speech Recognition ToolkitCode1
How2: A Large-scale Dataset for Multimodal Language UnderstandingCode1
NICE: Noise Injection and Clamping Estimation for Neural Network QuantizationCode1
Deep Audio-Visual Speech RecognitionCode1
Show:102550
← PrevPage 12 of 129Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AmNetWord Error Rate (WER)8.6Unverified
2HMM-(SAT)GMMWord Error Rate (WER)8Unverified
3Local Prior Matching (Large Model)Word Error Rate (WER)7.19Unverified
4SnipsWord Error Rate (WER)6.4Unverified
5Li-GRUWord Error Rate (WER)6.2Unverified
6HMM-DNN + pNorm*Word Error Rate (WER)5.5Unverified
7CTC + policy learningWord Error Rate (WER)5.42Unverified
8Deep Speech 2Word Error Rate (WER)5.33Unverified
9HMM-TDNN + iVectorsWord Error Rate (WER)4.8Unverified
10Gated ConvNetsWord Error Rate (WER)4.8Unverified
#ModelMetricClaimedVerifiedStatus
1Local Prior Matching (Large Model)Word Error Rate (WER)20.84Unverified
2SnipsWord Error Rate (WER)16.5Unverified
3Local Prior Matching (Large Model, ConvLM LM)Word Error Rate (WER)15.28Unverified
4Deep Speech 2Word Error Rate (WER)13.25Unverified
5TDNN + pNorm + speed up/down speechWord Error Rate (WER)12.5Unverified
6CTC-CRF 4gram-LMWord Error Rate (WER)10.65Unverified
7Convolutional Speech RecognitionWord Error Rate (WER)10.47Unverified
8MT4SSLWord Error Rate (WER)9.6Unverified
9Jasper DR 10x5Word Error Rate (WER)8.79Unverified
10EspressoWord Error Rate (WER)8.7Unverified
#ModelMetricClaimedVerifiedStatus
1Deep SpeechPercentage error20Unverified
2DNN-HMMPercentage error18.5Unverified
3CD-DNNPercentage error16.1Unverified
4DNNPercentage error16Unverified
5DNN + DropoutPercentage error15Unverified
6DNN BMMIPercentage error12.9Unverified
7DNN MPEPercentage error12.9Unverified
8DNN MMIPercentage error12.9Unverified
9HMM-TDNN + pNorm + speed up/down speechPercentage error12.9Unverified
10HMM-DNN +sMBRPercentage error12.6Unverified
#ModelMetricClaimedVerifiedStatus
1LSNNPercentage error33.2Unverified
2LAS multitask with indicators samplingPercentage error20.4Unverified
3Soft Monotonic Attention (ours, offline)Percentage error20.1Unverified
4QCNN-10L-256FMPercentage error19.64Unverified
5Bi-LSTM + skip connections w/ CTCPercentage error17.7Unverified
6Bi-RNN + AttentionPercentage error17.6Unverified
7RNN-CRF on 24(x3) MFSCPercentage error17.3Unverified
8CNN in time and frequency + dropout, 17.6% w/o dropoutPercentage error16.7Unverified
9Light Gated Recurrent UnitsPercentage error16.7Unverified
10GRUPercentage error16.6Unverified
#ModelMetricClaimedVerifiedStatus
1AttWord Error Rate (WER)18.7Unverified
2CTC/AttWord Error Rate (WER)6.7Unverified
3BRA-EWord Error Rate (WER)6.63Unverified
4CTC-CRF 4gram-LMWord Error Rate (WER)6.34Unverified
5BATWord Error Rate (WER)4.97Unverified
6ParaformerWord Error Rate (WER)4.95Unverified
7U2Word Error Rate (WER)4.72Unverified
8UMAWord Error Rate (WER)4.7Unverified
9Lightweight TransducerWord Error Rate (WER)4.31Unverified
10CIF-HKD With LMWord Error Rate (WER)4.1Unverified
#ModelMetricClaimedVerifiedStatus
1Jasper 10x3Word Error Rate (WER)6.9Unverified
2CNN over RAW speech (wav)Word Error Rate (WER)5.6Unverified
3CTC-CRF 4gram-LMWord Error Rate (WER)3.79Unverified
4Deep Speech 2Word Error Rate (WER)3.6Unverified
5test-set on open vocabulary (i.e. harder), model = HMM-DNN + pNorm*Word Error Rate (WER)3.6Unverified
6Convolutional Speech RecognitionWord Error Rate (WER)3.5Unverified
7TC-DNN-BLSTM-DNNWord Error Rate (WER)3.5Unverified
8EspressoWord Error Rate (WER)3.4Unverified
9CTC-CRF VGG-BLSTMWord Error Rate (WER)3.2Unverified
10Transformer with Relaxed AttentionWord Error Rate (WER)3.19Unverified