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 36013650 of 6433 papers

TitleStatusHype
Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery DetectionCode1
Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging0
Exploring wav2vec 2.0 on speaker verification and language identification0
Improved Robustness to Disfluencies in RNN-Transducer Based Speech Recognition0
DeCoAR 2.0: Deep Contextualized Acoustic Representations with Vector QuantizationCode1
Next Wave Artificial Intelligence: Robust, Explainable, Adaptable, Ethical, and Accountable0
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech RecognitionCode1
Multi-Classifier Interactive Learning for Ambiguous Speech Emotion Recognition0
Speech Recognition for Endangered and Extinct Samoyedic languages0
On Knowledge Distillation for Direct Speech Translation0
Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for Speech Recognition0
Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy PreservationCode0
Using multiple ASR hypotheses to boost i18n NLU performance0
MLS: A Large-Scale Multilingual Dataset for Speech ResearchCode0
SpeakingFaces: A Large-Scale Multimodal Dataset of Voice Commands with Visual and Thermal Video StreamsCode1
Parallel Blockwise Knowledge Distillation for Deep Neural Network CompressionCode0
Adapt-and-Adjust: Overcoming the Long-Tail Problem of Multilingual Speech Recognition0
End to End ASR System with Automatic Punctuation InsertionCode0
ASR for Non-standardised Languages with Dialectal Variation: the case of Swiss German0
Sparse Transcription0
German-Arabic Speech-to-Speech Translation for Psychiatric Diagnosis0
End-to-End Automatic Speech Recognition for GujaratiCode1
Development of Hybrid Algorithm for Automatic Extraction of Multiword Expressions from Monolingual and Parallel Corpus of English and Punjabi0
On-Device detection of sentence completion for voice assistants with low-memory footprint0
Supervised Adaptation of Sequence-to-Sequence Speech Recognition Systems using Batch-Weighting0
100,000 Podcasts: A Spoken English Document Corpus0
The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software0
A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AICode0
Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention0
Attentively Embracing Noise for Robust Latent Representation in BERTCode0
metaCAT: A Metadata-based Task-oriented Chatbot Annotation ToolCode1
Federated Marginal Personalization for ASR Rescoring0
Multi-Modal Detection of Alzheimer's Disease from Speech and Text0
Transformer-Transducers for Code-Switched Speech Recognition0
Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion0
Streaming end-to-end multi-talker speech recognition0
Unsupervised Domain Adaptation for Speech Recognition via Uncertainty Driven Self-Training0
A Panoramic Survey of Natural Language Processing in the Arab World0
Bootstrap an end-to-end ASR system by multilingual training, transfer learning, text-to-text mapping and synthetic audio0
Deep Discriminative Feature Learning for Accent RecognitionCode1
A Review of Recent Advances of Binary Neural Networks for Edge Computing0
Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech0
Adam^+: A Stochastic Method with Adaptive Variance Reduction0
Using Synthetic Audio to Improve The Recognition of Out-Of-Vocabulary Words in End-To-End ASR Systems0
Multi-task Language Modeling for Improving Speech Recognition of Rare Words0
Streaming Multi-speaker ASR with RNN-T0
An Online Multilingual Hate speech Recognition SystemCode0
Deep Learning in EEG: Advance of the Last Ten-Year Critical Period0
Improving RNN-T ASR Accuracy Using Context Audio0
TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos0
Show:102550
← PrevPage 73 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