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 39514000 of 6433 papers

TitleStatusHype
KIT’s IWSLT 2021 Offline Speech Translation System0
KIT's Low-resource Speech Translation Systems for IWSLT2025: System Enhancement with Synthetic Data and Model Regularization0
KIT's Offline Speech Translation and Instruction Following Submission for IWSLT 20250
Fine-grained Early Frequency Attention for Deep Speaker Representation Learning0
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data0
Knowledge Distillation and Data Selection for Semi-Supervised Learning in CTC Acoustic Models0
Knowledge Distillation for Improved Accuracy in Spoken Question Answering0
Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data0
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models0
Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization0
Knowledge Distillation for Small-footprint Highway Networks0
Knowledge distillation from language model to acoustic model: a hierarchical multi-task learning approach0
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition0
Knowledge Distillation from Non-streaming to Streaming ASR Encoder using Auxiliary Non-streaming Layer0
Knowledge-driven Subword Grammar Modeling for Automatic Speech Recognition in Tamil and Kannada0
Knowledge Transfer for Efficient On-device False Trigger Mitigation0
Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers0
Knowledge Transfer Pre-training0
Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance0
Korean Children's Spoken English Corpus and an Analysis of its Pronunciation Variability0
Korean Tokenization for Beam Search Rescoring in Speech Recognition0
Korean Word-Sense Disambiguation Using Parallel Corpus as Additional Resource0
L2 proficiency assessment using self-supervised speech representations0
L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition0
Label Aware Speech Representation Learning For Language Identification0
Label-Looping: Highly Efficient Decoding for Transducers0
Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification0
Label-Synchronous Neural Transducer for Adaptable Online E2E Speech Recognition0
Label-Synchronous Speech-to-Text Alignment for ASR Using Forward and Backward Transformers0
Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks0
La longueur des tours de parole comme crit\`ere de s\'election de conversations dans un centre d'appels (Turn-taking length as criterion to select call center conversations) [in French]0
LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers0
LAMA-UT: Language Agnostic Multilingual ASR through Orthography Unification and Language-Specific Transliteration0
Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks0
Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition0
Language Agnostic Data-Driven Inverse Text Normalization0
Language-agnostic Multilingual Modeling0
Language Bias in Self-Supervised Learning For Automatic Speech Recognition0
Language Dependencies in Adversarial Attacks on Speech Recognition Systems0
Language Identification in Code-Switching Scenario0
Language ID Prediction from Speech Using Self-Attentive Pooling and 1D-Convolutions0
Language ID Prediction from Speech Using Self-Attentive Pooling0
Language Informed Modeling of Code-Switched Text0
Language learning using Speech to Image retrieval0
Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition0
Language model fusion for streaming end to end speech recognition0
Language Modeling at Scale0
Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data0
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction0
Language Modeling for Spoken Dialogue System based on Filtering using Predicate-Argument Structures0
Show:102550
← PrevPage 80 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