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 501550 of 6433 papers

TitleStatusHype
Joint Masked CPC and CTC Training for ASRCode1
Speech SIMCLR: Combining Contrastive and Reconstruction Objective for Self-supervised Speech Representation LearningCode1
Decentralizing Feature Extraction with Quantum Convolutional Neural Network for Automatic Speech RecognitionCode1
Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech RecognitionCode1
Pushing the Limits of Semi-Supervised Learning for Automatic Speech RecognitionCode1
Towards Resistant Audio Adversarial ExamplesCode1
Google Crowdsourced Speech Corpora and Related Open-Source Resources for Low-Resource Languages and Dialects: An OverviewCode1
Non-Attentive Tacotron: Robust and Controllable Neural TTS Synthesis Including Unsupervised Duration ModelingCode1
Representation Learning for Sequence Data with Deep Autoencoding Predictive ComponentsCode1
Online Neural Networks for Change-Point DetectionCode1
Differentiable Weighted Finite-State TransducersCode1
Improving Vietnamese Named Entity Recognition from Speech Using Word Capitalization and Punctuation Recovery ModelsCode1
End-to-End Speech Recognition and Disfluency RemovalCode1
A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition BaselineCode1
Consecutive Decoding for Speech-to-text TranslationCode1
KoSpeech: Open-Source Toolkit for End-to-End Korean Speech RecognitionCode1
Libri-Adapt: A New Speech Dataset for Unsupervised Domain AdaptationCode1
Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence ModelingCode1
Compiling ONNX Neural Network Models Using MLIRCode1
Computer-Generated Music for Tabletop Role-Playing GamesCode1
Sum-Product Networks for Robust Automatic Speaker IdentificationCode1
Investigation of End-To-End Speaker-Attributed ASR for Continuous Multi-Talker RecordingsCode1
Distilling the Knowledge of BERT for Sequence-to-Sequence ASRCode1
Word Error Rate Estimation Without ASR Output: e-WER2Code1
Pretraining Techniques for Sequence-to-Sequence Voice ConversionCode1
Online Spatio-Temporal Learning in Deep Neural NetworksCode1
CoVoST 2 and Massively Multilingual Speech-to-Text TranslationCode1
Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-AttentionCode1
TERA: Self-Supervised Learning of Transformer Encoder Representation for SpeechCode1
DARF: A data-reduced FADE version for simulations of speech recognition thresholds with real hearing aidsCode1
AdaScale SGD: A User-Friendly Algorithm for Distributed TrainingCode1
Unsupervised Cross-lingual Representation Learning for Speech RecognitionCode1
Automatic Speech Recognition Benchmark for Air-Traffic CommunicationsCode1
AVLnet: Learning Audio-Visual Language Representations from Instructional VideosCode1
Emotion Recognition in Audio and Video Using Deep Neural NetworksCode1
Learning to Count Words in Fluent Speech enables Online Speech RecognitionCode1
Improved acoustic word embeddings for zero-resource languages using multilingual transferCode1
PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitivesCode1
Subword RNNLM Approximations for Out-Of-Vocabulary Keyword SearchCode1
On the Comparison of Popular End-to-End Models for Large Scale Speech RecognitionCode1
Adapting End-to-End Speech Recognition for Readable SubtitlesCode1
End-to-end Named Entity Recognition from English SpeechCode1
PyChain: A Fully Parallelized PyTorch Implementation of LF-MMI for End-to-End ASRCode1
A Further Study of Unsupervised Pre-training for Transformer Based Speech RecognitionCode1
Improved Noisy Student Training for Automatic Speech RecognitionCode1
GEV Beamforming Supported by DOA-based Masks Generated on Pairs of MicrophonesCode1
Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech RecognitionCode1
Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech RecognitionCode1
Enhancing Monotonic Multihead Attention for Streaming ASRCode1
Speech Recognition and Multi-Speaker Diarization of Long ConversationsCode1
Show:102550
← PrevPage 11 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
9Gated ConvNetsWord Error Rate (WER)4.8Unverified
10HMM-TDNN + iVectorsWord 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
7HMM-TDNN + pNorm + speed up/down speechPercentage error12.9Unverified
8DNN MPEPercentage error12.9Unverified
9DNN MMIPercentage error12.9Unverified
10CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWBPercentage 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
6TC-DNN-BLSTM-DNNWord Error Rate (WER)3.5Unverified
7Convolutional Speech RecognitionWord 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