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 451500 of 6433 papers

TitleStatusHype
CLSRIL-23: Cross Lingual Speech Representations for Indic LanguagesCode1
Nanopore Base Calling on the EdgeCode1
A Toolbox for Construction and Analysis of Speech DatasetsCode1
Neural Predictor for Black-Box Adversarial Attacks on Speech RecognitionCode1
Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMICode1
Non-autoregressive Error Correction for CTC-based ASR with Phone-conditioned Masked LMCode1
Deep Sparse Conformer for Speech RecognitionCode1
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech DatasetCode1
Brazilian Portuguese Speech Recognition Using Wav2vec 2.0Code1
On the Comparison of Popular End-to-End Models for Large Scale Speech RecognitionCode1
Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural NetworksCode1
OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality AlignmentCode1
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation WritingCode1
BrainBERT: Self-supervised representation learning for intracranial recordingsCode1
Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language ModelsCode1
Bridging the Gaps of Both Modality and Language: Synchronous Bilingual CTC for Speech Translation and Speech RecognitionCode1
Beyond Performance Plateaus: A Comprehensive Study on Scalability in Speech EnhancementCode1
PriMock57: A Dataset Of Primary Care Mock ConsultationsCode1
Prompting Large Language Models with Audio for General-Purpose Speech SummarizationCode1
Prompting the Hidden Talent of Web-Scale Speech Models for Zero-Shot Task GeneralizationCode1
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASRCode1
Integer-only Zero-shot Quantization for Efficient Speech RecognitionCode1
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsCode1
BIG-C: a Multimodal Multi-Purpose Dataset for BembaCode1
A Comparison of Methods for OOV-word Recognition on a New Public DatasetCode1
BembaSpeech: A Speech Recognition Corpus for the Bemba LanguageCode1
Regularizing End-to-End Speech Translation with Triangular Decomposition AgreementCode1
Relaxed Attention: A Simple Method to Boost Performance of End-to-End Automatic Speech RecognitionCode1
BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmCode1
BENDR: using transformers and a contrastive self-supervised learning task to learn from massive amounts of EEG dataCode1
Bridging the Granularity Gap for Acoustic ModelingCode1
Romanian Speech Recognition Experiments from the ROBIN ProjectCode1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
RyanSpeech: A Corpus for Conversational Text-to-Speech SynthesisCode1
AVLnet: Learning Audio-Visual Language Representations from Instructional VideosCode1
Deep Discriminative Feature Learning for Accent RecognitionCode1
AVATAR: Unconstrained Audiovisual Speech RecognitionCode1
Consecutive Decoding for Speech-to-text TranslationCode1
AV Taris: Online Audio-Visual Speech RecognitionCode1
Self-supervised Learning with Random-projection Quantizer for Speech RecognitionCode1
Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling InsightsCode1
SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion RecognitionCode1
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRCode1
A Comprehensive Survey on Graph Neural NetworksCode1
A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and RecognitionCode1
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense EvaluationCode1
SoccerNet-Echoes: A Soccer Game Audio Commentary DatasetCode1
SoftCTC -- Semi-Supervised Learning for Text Recognition using Soft Pseudo-LabelsCode1
Speaker Recognition in the WildCode1
Automatic Speech Recognition Benchmark for Air-Traffic CommunicationsCode1
Show:102550
← PrevPage 10 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