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 751800 of 6433 papers

TitleStatusHype
Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelsCode0
Improved Speech Enhancement with the Wave-U-NetCode0
Improved training for online end-to-end speech recognition systemsCode0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
Active Learning with Task Adaptation Pre-training for Speech Emotion RecognitionCode0
A Toolkit for Efficient Learning of Lexical Units for Speech RecognitionCode0
Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech RecognitionCode0
Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language ModelsCode0
ImportantAug: a data augmentation agent for speechCode0
A Theory of Unsupervised Speech RecognitionCode0
Improved acoustic-to-articulatory inversion using representations from pretrained self-supervised learning modelsCode0
Intrinsic evaluation of language models for code-switchingCode0
DistriBlock: Identifying adversarial audio samples by leveraging characteristics of the output distributionCode0
Human Transcription Quality ImprovementCode0
Hybrid ASR for Resource-Constrained Robots: HMM - Deep Learning FusionCode0
How You Say It Matters: Measuring the Impact of Verbal Disfluency Tags on Automated Dementia DetectionCode0
Active Learning for Classifying 2D Grid-Based Level CompletabilityCode0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
How Phonotactics Affect Multilingual and Zero-shot ASR PerformanceCode0
A Target-Agnostic Attack on Deep Models: Exploiting Security Vulnerabilities of Transfer LearningCode0
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksCode0
Homophone Disambiguation Reveals Patterns of Context Mixing in Speech TransformersCode0
HK-LegiCoST: Leveraging Non-Verbatim Transcripts for Speech TranslationCode0
Honk: A PyTorch Reimplementation of Convolutional Neural Networks for Keyword SpottingCode0
A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic ModelsCode0
High-order Graph-based Neural Dependency ParsingCode0
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech RecognitionCode0
Harnessing Evolution of Multi-Turn Conversations for Effective Answer RetrievalCode0
Attentional Speech Recognition Models Misbehave on Out-of-domain UtterancesCode0
Action Recognition in Video Sequences using Deep Bi-Directional LSTM With CNN FeaturesCode0
Harnessing GANs for Zero-shot Learning of New Classes in Visual Speech RecognitionCode0
Hierarchical Text Generation using an OutlineCode0
Hybrid phonetic-neural model for correction in speech recognition systemsCode0
Improving Slot Filling in Spoken Language Understanding with Joint Pointer and AttentionCode0
Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of SpeechCode0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
Attention-based Multi-hypothesis Fusion for Speech SummarizationCode0
Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASRCode0
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer GeneratorCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
A Survey of Recent DNN Architectures on the TIMIT Phone Recognition TaskCode0
A Survey of Deep Active LearningCode0
Incremental Training of a Recurrent Neural Network Exploiting a Multi-Scale Dynamic MemoryCode0
Geometric deep learning on graphs and manifolds using mixture model CNNsCode0
Generating gender-ambiguous voices for privacy-preserving speech recognitionCode0
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired SpeechCode0
Integrated Semantic and Phonetic Post-correction for Chinese Speech RecognitionCode0
Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech RecognitionCode0
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionCode0
Show:102550
← PrevPage 16 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