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 59516000 of 6433 papers

TitleStatusHype
Biometrics Recognition Using Deep Learning: A SurveyCode0
Predicting Affective Vocal Bursts with Finetuned wav2vec 2.0Code0
Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural NetworksCode0
Conditional independence for pretext task selection in Self-supervised speech representation learningCode0
Complementing Handcrafted Features with Raw Waveform Using a Light-weight Auxiliary ModelCode0
Towards Unsupervised Speech Recognition Without Pronunciation ModelsCode0
Who is Real Bob? Adversarial Attacks on Speaker Recognition SystemsCode0
Augmented Cyclic Adversarial Learning for Low Resource Domain AdaptationCode0
Arabic Speech Recognition by End-to-End, Modular Systems and HumanCode0
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related TasksCode0
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed TrainingCode0
Deep Gradient Compression Reduce the Communication Bandwidth For distributed TraningCode0
VideoBERT: A Joint Model for Video and Language Representation LearningCode0
Use of Deep Learning in Modern Recommendation System: A Summary of Recent WorksCode0
Trace norm regularization and faster inference for embedded speech recognition RNNsCode0
Understanding Adaptive, Multiscale Temporal Integration In Deep Speech Recognition SystemsCode0
Latent Tree Language ModelCode0
Improving RNN Transducer Modeling for End-to-End Speech RecognitionCode0
Adversarial Training For Low-Resource Disfluency CorrectionCode0
Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion TechniquesCode0
Adversarial Example Detection by Classification for Deep Speech RecognitionCode0
Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search DegradationCode0
Pre-Finetuning for Few-Shot Emotional Speech RecognitionCode0
Scheduled Sampling for Sequence Prediction with Recurrent Neural NetworksCode0
Multi-Speaker ASR Combining Non-Autoregressive Conformer CTC and Conditional Speaker ChainCode0
Speech-enhanced and Noise-aware Networks for Robust Speech RecognitionCode0
SCORE: Self-supervised Correspondence Fine-tuning for Improved Content RepresentationsCode0
Improving LSTM-CTC based ASR performance in domains with limited training dataCode0
Preparing Data from Psychotherapy for Natural Language ProcessingCode0
Preserving spoken content in voice anonymisation with character-level vocoder conditioningCode0
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy PreservationCode0
Pretext Tasks selection for multitask self-supervised speech representation learningCode0
Scribosermo: Fast Speech-to-Text models for German and other LanguagesCode0
Whole-Word Segmental Speech Recognition with Acoustic Word EmbeddingsCode0
DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural NetworksCode0
Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech RepresentationsCode0
Deep-FSMN for Large Vocabulary Continuous Speech RecognitionCode0
ed-cec: improving rare word recognition using asr postprocessing based on error detection and context-aware error correctionCode0
An End-to-End Neural Network for Polyphonic Piano Music TranscriptionCode0
Trainable Frontend For Robust and Far-Field Keyword SpottingCode0
Understanding the Tradeoffs in Client-side Privacy for Downstream Speech TasksCode0
Evaluation of End-to-End Continuous Spanish Lipreading in Different Data ConditionsCode0
Learning Alignment for Multimodal Emotion Recognition from SpeechCode0
Pre-training on high-resource speech recognition improves low-resource speech-to-text translationCode0
EBPC: Extended Bit-Plane Compression for Deep Neural Network Inference and Training AcceleratorsCode0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
Improved training for online end-to-end speech recognition systemsCode0
Big model only for hard audios: Sample dependent Whisper model selection for efficient inferencesCode0
Vietnamese Capitalization and Punctuation Recovery ModelsCode0
Show:102550
← PrevPage 120 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