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 28012850 of 6433 papers

TitleStatusHype
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides0
How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyena0
How Might We Create Better Benchmarks for Speech Recognition?0
Fast Labeling and Transcription with the Speechalyzer Toolkit0
FastInject: Injecting Unpaired Text Data into CTC-based ASR training0
CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings0
Arabic Code-Switching Speech Recognition using Monolingual Data0
Adversarial Speaker Adaptation0
How to Learn a New Language? An Efficient Solution for Self-Supervised Learning Models Unseen Languages Adaption in Low-Resource Scenario0
How to Reach Real-Time AI on Consumer Devices? Solutions for Programmable and Custom Architectures0
How to Scale Up Kernel Methods to Be As Good As Deep Neural Nets0
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network0
Child Speech Recognition in Human-Robot Interaction: Problem Solved?0
How transferable are features in convolutional neural network acoustic models across languages?0
Fast frequency modulation is encoded according to the listener expectations in the human subcortical auditory pathway0
Faster Speech-LLaMA Inference with Multi-token Prediction0
HTEC: Human Transcription Error Correction0
Children's Speech Recognition through Discrete Token Enhancement0
HuBERTopic: Enhancing Semantic Representation of HuBERT through Self-supervision Utilizing Topic Model0
A Quantitative Study of Data in the NLP community0
Experiments on Turkish ASR with Self-Supervised Speech Representation Learning0
Human and Automatic Speech Recognition Performance on German Oral History Interviews0
Fast Entropy-Based Methods of Word-Level Confidence Estimation for End-To-End Automatic Speech Recognition0
Human Evaluation of Conceptual Route Graphs for Interpreting Spoken Route Descriptions0
Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT0
Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement0
Human-Machine Dialogue as a Stochastic Game0
A Quantitative Insight into the Impact of Translation on Readability0
Huqariq: A Multilingual Speech Corpus of Native Languages of Peru for Speech Recognition0
Huqariq: A Multilingual Speech Corpus of Native Languages of Peru forSpeech Recognition0
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition0
A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation0
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition0
Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units0
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition0
Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition0
Hybridized Feature Extraction and Acoustic Modelling Approach for Dysarthric Speech Recognition0
Fast Context-Biasing for CTC and Transducer ASR models with CTC-based Word Spotter0
Hybrid Orthogonal Projection and Estimation (HOPE): A New Framework to Probe and Learn Neural Networks0
Character-Level Language Modeling with Hierarchical Recurrent Neural Networks0
H_eval: A new hybrid evaluation metric for automatic speech recognition tasks0
Hybrid Selection of Language Model Training Data Using Linguistic Information and Perplexity0
Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks0
Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition0
HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition0
Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach0
Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers0
Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition0
Fast Bootstrapping of Grapheme to Phoneme System for Under-resourced Languages - Application to the Iban Language0
Fast and Scalable Decoding with Language Model Look-Ahead for Phrase-based Statistical Machine Translation0
Show:102550
← PrevPage 57 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