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 20512100 of 6433 papers

TitleStatusHype
End-to-End Monaural Multi-speaker ASR System without Pretraining0
End-to-End Multi-Channel Transformer for Speech Recognition0
End-to-End Multimodal Speech Recognition0
Chipmunk: A Systolically Scalable 0.9 mm^2, 3.08 Gop/s/mW @ 1.2 mW Accelerator for Near-Sensor Recurrent Neural Network Inference0
Chinese Medical Speech Recognition with Punctuated Hypothesis0
Arabic Diacritization with Recurrent Neural Networks0
Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides0
CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings0
Arabic Code-Switching Speech Recognition using Monolingual Data0
Adversarial Speaker Adaptation0
Child Speech Recognition in Human-Robot Interaction: Problem Solved?0
Children's Speech Recognition through Discrete Token Enhancement0
A Quantitative Study of Data in the NLP community0
Adversarial Meta Sampling for Multilingual Low-Resource Speech Recognition0
A Quantitative Insight into the Impact of Translation on Readability0
A Corpus of Spontaneous Speech in Lectures: The KIT Lecture Corpus for Spoken Language Processing and Translation0
End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data0
End-to-End Joint Target and Non-Target Speakers ASR0
Adversarial Machine Learning in Network Intrusion Detection Systems0
Character-Level Language Modeling with Hierarchical Recurrent Neural Networks0
End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec20
A Purely End-to-end System for Multi-speaker Speech Recognition0
Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition0
Accented Speech Recognition: Benchmarking, Pre-training, and Diverse Data0
End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation0
Characterizing the Weight Space for Different Learning Models0
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement0
A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations0
Characterizing Audio Adversarial Examples Using Temporal Dependency0
Character-aware audio-visual subtitling in context0
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition0
A Corpus of Read and Spontaneous Upper Saxon German Speech for ASR Evaluation0
End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations0
End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition0
Character-Aware Attention-Based End-to-End Speech Recognition0
Character and Subword-Based Word Representation for Neural Language Modeling Prediction0
A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution0
Chaotic Variational Auto encoder-based Adversarial Machine Learning0
CHAOS: A Parallelization Scheme for Training Convolutional Neural Networks on Intel Xeon Phi0
A Probabilistic Approach for Confidence Scoring in Speech Recognition0
Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise0
A privacy-preserving method using secret key for convolutional neural network-based speech classification0
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech0
A Corpus for Modeling Word Importance in Spoken Dialogue Transcripts0
Challenging the Boundaries of Speech Recognition: The MALACH Corpus0
Challenges of Computational Processing of Code-Switching0
A Preliminary Study on Leveraging Meta Learning Technique for Code-switching Speech Recognition0
2D-CTC for Scene Text Recognition0
100,000 Podcasts: A Spoken English Document Corpus0
Challenges of Applying Automatic Speech Recognition for Transcribing EU Parliament Committee Meetings: A Pilot Study0
Show:102550
← PrevPage 42 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