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 19011950 of 6433 papers

TitleStatusHype
A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset0
Regeneration Learning: A Learning Paradigm for Data Generation0
Neural Architecture Search: Insights from 1000 PapersCode0
Language Agnostic Data-Driven Inverse Text Normalization0
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition0
Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining0
Syllable Subword Tokens for Open Vocabulary Speech Recognition in MalayalamCode0
BayesSpeech: A Bayesian Transformer Network for Automatic Speech Recognition0
OLKAVS: An Open Large-Scale Korean Audio-Visual Speech DatasetCode1
Multi-resolution location-based training for multi-channel continuous speech separation0
Using Kaldi for Automatic Speech Recognition of Conversational Austrian German0
Rationalizing Predictions by Adversarial Information Calibration0
Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition0
FullStop:Punctuation and Segmentation Prediction for Dutch with Transformers0
Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group0
Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition0
Audio-Visual Efficient Conformer for Robust Speech RecognitionCode1
Supervised Acoustic Embeddings And Their Transferability Across LanguagesCode0
Towards Voice Reconstruction from EEG during Imagined SpeechCode1
Unsupervised Pre-Training for Vietnamese Automatic Speech Recognition in the HYKIST Project0
ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration0
Sample-Efficient Unsupervised Domain Adaptation of Speech Recognition Systems A case study for Modern Greek0
Memory Augmented Lookup Dictionary based Language Modeling for Automatic Speech Recognition0
Macro-block dropout for improved regularization in training end-to-end speech recognition models0
Learning to Detect Noisy Labels Using Model-Based FeaturesCode1
Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation0
Skit-S2I: An Indian Accented Speech to Intent datasetCode1
Alignment Entropy Regularization0
4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders0
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement0
End-to-End Automatic Speech Recognition model for the Sudanese Dialect0
SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks0
Mu^2SLAM: Multitask, Multilingual Speech and Language Models0
NusaCrowd: Open Source Initiative for Indonesian NLP ResourcesCode2
AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translation0
Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition0
Speech Aware Dialog System Technology Challenge (DSTC11)0
Context-aware Fine-tuning of Self-supervised Speech Models0
BLASER: A Text-Free Speech-to-Speech Translation Evaluation MetricCode2
Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language Understanding tasksCode0
Improving Fast-slow Encoder based Transducer with Streaming Deliberation0
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks0
Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and LanguageCode1
Disentangling Prosody Representations with Unsupervised Speech Reconstruction0
Speech and Natural Language Processing Technologies for Pseudo-Pilot Simulator0
Jointly Learning Visual and Auditory Speech Representations from Raw DataCode1
BASPRO: a balanced script producer for speech corpus collection based on the genetic algorithmCode1
End-to-End Speech Translation of Arabic to English Broadcast News0
Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning0
GPU-accelerated Guided Source Separation for Meeting TranscriptionCode1
Show:102550
← PrevPage 39 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