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 60516100 of 6433 papers

TitleStatusHype
A Toolkit for Efficient Learning of Lexical Units for Speech RecognitionCode0
When Is TTS Augmentation Through a Pivot Language Useful?Code0
NeMo Inverse Text Normalization: From Development To ProductionCode0
I3D: Transformer architectures with input-dependent dynamic depth for speech recognitionCode0
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech ToolkitCode0
DSD: Dense-Sparse-Dense Training for Deep Neural NetworksCode0
HydraFormer: One Encoder For All Subsampling RatesCode0
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech RecognitionCode0
Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition NetworksCode0
Whose Emotion Matters? Speaking Activity Localisation without Prior KnowledgeCode0
Neural Architecture Search: A SurveyCode0
Neural Architecture Search For LF-MMI Trained Time Delay Neural NetworksCode0
Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech RecognitionCode0
Neural Architecture Search: Insights from 1000 PapersCode0
Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional TrainingCode0
Teaching Wav2Vec2 the Language of the BrainCode0
Hybrid phonetic-neural model for correction in speech recognition systemsCode0
A Theory of Unsupervised Speech RecognitionCode0
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer LearningCode0
A Comprehensive Evaluation of Incremental Speech Recognition and Diarization for Conversational AICode0
Speech Recognition with Deep Recurrent Neural NetworksCode0
Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free CommunicationCode0
Self-supervised Speech Representations Still Struggle with African American Vernacular EnglishCode0
Decoding P300 Variability using Convolutional Neural NetworksCode0
A Dataset for Speech Emotion Recognition in Greek Theatrical PlaysCode0
Self-Train Before You TranscribeCode0
Self-training and Pre-training are Complementary for Speech RecognitionCode0
A Survey of Recent DNN Architectures on the TIMIT Phone Recognition TaskCode0
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
Let SSMs be ConvNets: State-space Modeling with Optimal Tensor ContractionsCode0
Letter-Based Speech Recognition with Gated ConvNetsCode0
Pseudo-Labeling for Domain-Agnostic Bangla Automatic Speech RecognitionCode0
Bigger is not Always Better: The Effect of Context Size on Speech Pre-TrainingCode0
Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and SubtitlingCode0
Speech Understanding on Tiny Devices with A Learning CacheCode0
DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distributionCode0
TinyML for Speech RecognitionCode0
Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech RecognitionCode0
Semantically Corrected Amharic Automatic Speech RecognitionCode0
Semantically Meaningful Metrics for Norwegian ASR SystemsCode0
TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASRCode0
Transcription free filler word detection with Neural semi-CRFsCode0
Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short TextsCode0
Neural network based spectral mask estimation for acoustic beamformingCode0
Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of WhisperCode0
Collecting Resources in Sub-Saharan African Languages for Automatic Speech Recognition: a Case Study of WolofCode0
Semantic Mask for Transformer based End-to-End Speech RecognitionCode0
Code-Switched Urdu ASR for Noisy Telephonic Environment using Data Centric Approach with Hybrid HMM and CNN-TDNNCode0
Neural NILM: Deep Neural Networks Applied to Energy DisaggregationCode0
Show:102550
← PrevPage 122 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