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 31513200 of 6433 papers

TitleStatusHype
Interactive spatial speech recognition maps based on simulated speech recognition experiments0
Interactive Spoken Content Retrieval by Deep Reinforcement Learning0
InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASR0
InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions0
Enhanced CORILGA: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech0
Inter-KD: Intermediate Knowledge Distillation for CTC-Based Automatic Speech Recognition0
Inter-linguistic Phonetic Composition (IPC): A Theoretical and Computational Approach to Enhance Second Language Pronunciation0
Intermediate-layer output Regularization for Attention-based Speech Recognition with Shared Decoder0
Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding0
InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss0
Brain Signals to Rescue Aphasia, Apraxia and Dysarthria Speech Recognition0
Internal Language Model Estimation based Language Model Fusion for Cross-Domain Code-Switching Speech Recognition0
Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognition0
Internal Language Model Estimation Through Explicit Context Vector Learning for Attention-based Encoder-decoder ASR0
Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition0
CTC-Assisted LLM-Based Contextual ASR0
Interpolated Dirichlet Class Language Model for Speech Recognition Incorporating Long-distance N-grams0
Interpretable Convolutional Filters with SincNet0
Interpretable Convolutional Filters with SincNet0
Interpretable Dysarthric Speaker Adaptation based on Optimal-Transport0
English Conversational Telephone Speech Recognition by Humans and Machines0
Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation0
Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding0
Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network0
Intra-Speaker Topic Modeling for Improved Multi-Party Meeting Summarization with Integrated Random Walk0
Cumulative Adaptation for BLSTM Acoustic Models0
Introducing Semantics into Speech Encoders0
Introduction d'informations s\'emantiques dans un syst\`eme de reconnaissance de la parole (Despite spectacular advances in recent years, the Automatic Speech Recognition (ASR) systems still make mistakes, especially in noisy environments)0
Introduction to speech recognition0
Introspection for convolutional automatic speech recognition0
Invariant Representations for Noisy Speech Recognition0
Investigating Confidence Estimation Measures for Speaker Diarization0
Investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation0
Investigating End-to-End ASR Architectures for Long Form Audio Transcription0
Curvature: A signature for Action Recognition in Video Sequences0
Investigating Lexical Replacements for Arabic-English Code-Switched Data Augmentation0
English Broadcast News Speech Recognition by Humans and Machines0
探究新穎語句模型化技術於節錄式語音摘要 (Investigating Novel Sentence Modeling Techniques for Extractive Speech Summarization) [In Chinese]0
Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution0
Investigating Speech Recognition for Improving Predictive AAC0
Investigating Target Set Reduction for End-to-End Speech Recognition of Hindi-English Code-Switching Data0
Investigating the 'Autoencoder Behavior' in Speech Self-Supervised Models: a focus on HuBERT's Pretraining0
Investigating the effect of auxiliary objectives for the automated grading of learner English speech transcriptions0
Investigating self-supervised, weakly supervised and fully supervised training approaches for multi-domain automatic speech recognition: a study on Bangladeshi Bangla0
Cycle-Consistent GAN Front-End to Improve ASR Robustness to Perturbed Speech0
Attentive Adversarial Learning for Domain-Invariant Training0
A non-expert Kaldi recipe for Vietnamese Speech Recognition System0
Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition0
Accelerating Minibatch Stochastic Gradient Descent using Typicality Sampling0
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation0
Show:102550
← PrevPage 64 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