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 48014850 of 6433 papers

TitleStatusHype
Introspection for convolutional automatic speech recognition0
`Indicatements' that character language models learn English morpho-syntactic units and regularities0
Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition0
PizzaPal: Conversational Pizza Ordering using a High-Density Conversational AI Platform0
Visualizing Group Dynamics based on Multiparty Meeting Understanding0
Unauthorized AI cannot Recognize Me: Reversible Adversarial Example0
On the End-to-End Solution to Mandarin-English Code-switching Speech RecognitionCode0
How2: A Large-scale Dataset for Multimodal Language UnderstandingCode1
Tropical Modeling of Weighted Transducer Algorithms on Graphs0
Low-Dimensional Bottleneck Features for On-Device Continuous Speech Recognition0
End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimator0
Attention-based sequence-to-sequence model for speech recognition: development of state-of-the-art system on LibriSpeech and its application to non-native English0
Towards End-to-End Code-Switching Speech Recognition0
Towards End-to-end Automatic Code-Switching Speech Recognition0
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired SpeechCode0
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data0
Bi-Directional Lattice Recurrent Neural Networks for Confidence EstimationCode0
Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition0
Contextual Speech Recognition with Difficult Negative Training Examples0
Language Modeling for Code-Switching: Evaluation, Integration of Monolingual Data, and Discriminative TrainingCode0
Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach0
Robust Audio Adversarial Example for a Physical AttackCode0
Neuron Activation Profiles for Interpreting Convolutional Speech Recognition Models0
Scaling Speech Enhancement in Unseen Environments with Noise Embeddings0
Speaker Selective Beamformer with Keyword Mask Estimation0
Tackling Sequence to Sequence Mapping Problems with Neural Networks0
The MeMAD Submission to the IWSLT 2018 Speech Translation Task0
A Deep Generative Acoustic Model for Compositional Automatic Speech Recognition0
Language Modeling at Scale0
Semi-supervised acoustic model training for speech with code-switching0
Learned in Speech Recognition: Contextual Acoustic Word Embeddings0
Targeted Adversarial Examples for Black Box Audio Systems0
ROBUST SPEECH COMMAND RECOGNITION USING LABEL-DRIVEN TIME-FREQUENCY MASKING0
How transferable are features in convolutional neural network acoustic models across languages?0
A comprehensive analysis on attention models0
Cycle-Consistent GAN Front-End to Improve ASR Robustness to Perturbed Speech0
Training Neural Speech Recognition Systems with Synthetic Speech Augmentation0
Improved Speech Enhancement with the Wave-U-Net0
Transferable and Configurable Audio Adversarial Attack from Low-Level Features0
On the Inductive Bias of Word-Character-Level Multi-Task Learning for Speech Recognition0
Robust Domain Adaptation By Augmented Cyclic Adversarial Learning0
Proactive Security: Embedded AI Solution for Violent and Abusive Speech Recognition0
Interpretable Convolutional Filters with SincNet0
Hierarchical Text Generation using an OutlineCode0
EdgeSpeechNets: Highly Efficient Deep Neural Networks for Speech Recognition on the Edge0
Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation0
LRW-1000: A Naturally-Distributed Large-Scale Benchmark for Lip Reading in the WildCode0
Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural NetworksCode0
Speech Recognition with Quaternion Neural Networks0
3D Feature Pyramid Attention Module for Robust Visual Speech Recognition0
Show:102550
← PrevPage 97 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