SOTAVerified

Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR) involves converting spoken language into written text. It is designed to transcribe spoken words into text in real-time, allowing people to communicate with computers, mobile devices, and other technology using their voice. The goal of Automatic Speech Recognition is to accurately transcribe speech, taking into account variations in accent, pronunciation, and speaking style, as well as background noise and other factors that can affect speech quality.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 2251–2300 of 3012 papers

TitleStatusHype
Transfer Learning for Less-Resourced Semitic Languages Speech Recognition: the Case of Amharic—0
Improving the Language Model for Low-Resource ASR with Online Text Corpora—0
Exploring Pre-training with Alignments for RNN Transducer based End-to-End Speech Recognition—0
A convolutional neural-network model of human cochlear mechanics and filter tuning for real-time applicationsCode1
Multiresolution and Multimodal Speech Recognition with Transformers—0
Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on YouTubeCode0
Jointly Trained Transformers models for Spoken Language Translation—0
End-to-end speech-to-dialog-act recognition—0
A Study of Non-autoregressive Model for Sequence Generation—0
ESPnet-ST: All-in-One Speech Translation Toolkit—0
ClovaCall: Korean Goal-Oriented Dialog Speech Corpus for Automatic Speech Recognition of Contact CentersCode1
Transformer based Grapheme-to-Phoneme ConversionCode1
Speaker Diarization with Lexical Information—0
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?—0
Improving Readability for Automatic Speech Recognition Transcription—0
Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech—0
Homophone-based Label Smoothing in End-to-End Automatic Speech Recognition—0
Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement—0
Training for Speech Recognition on Coprocessors—0
Low Latency ASR for Simultaneous Speech Translation—0
High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model—0
Deliberation Model Based Two-Pass End-to-End Speech Recognition—0
Multi-modal Dense Video CaptioningCode1
ASR Error Correction and Domain Adaptation Using Machine Translation—0
Hybrid Autoregressive Transducer (hat)—0
Improving noise robust automatic speech recognition with single-channel time-domain enhancement network—0
Deep Neural Networks for Automatic Speech Processing: A Survey from Large Corpora to Limited Data—0
Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and PruningCode1
Improving Uyghur ASR systems with decoders using morpheme-based language models—0
Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection—0
Natural Language Processing Advancements By Deep Learning: A SurveyCode1
SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech TranslationCode0
A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition—0
Distributed Training of Deep Neural Network Acoustic Models for Automatic Speech Recognition—0
Attention-based ASR with Lightweight and Dynamic Convolutions—0
RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition—0
Gradient-Adjusted Neuron Activation Profiles for Comprehensive Introspection of Convolutional Speech Recognition Models—0
Speech Corpus of Ainu Folklore and End-to-end Speech Recognition for Ainu Language—0
Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR—0
Looking Enhances Listening: Recovering Missing Speech Using Images—0
Attentional Speech Recognition Models Misbehave on Out-of-domain UtterancesCode0
Unsupervised pretraining transfers well across languagesCode1
Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and auto-regressive prosody prior—0
Continuous Silent Speech Recognition using EEG—0
Robust Multi-channel Speech Recognition using Frequency Aligned Network—0
End-to-End Automatic Speech Recognition Integrated With CTC-Based Voice Activity Detection—0
Fully Learnable Front-End for Multi-Channel Acoustic Modeling using Semi-Supervised Learning—0
Dialogue-Based Simulation For Cultural Awareness Training—0
BUT Opensat 2019 Speech Recognition System—0
Continuous speech separation: dataset and analysisCode1
Show:102550
← PrevPage 46 of 61Next →
All datasetsLRS2RealMANSagaleeHUI speech corpusLRS3-TEDM-AILabs speech datasetThe Spoken Wikipedia CorporaVoxforge GermanVoxPopuli

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1TM-CTCTest WER10.1—Unverified
2TM-seq2seqTest WER9.7—Unverified
3CTC/attentionTest WER8.2—Unverified
4LF-MMI TDNNTest WER6.7—Unverified
5Whisper-LLaMATest WER6.6—Unverified
6End2end ConformerTest WER3.9—Unverified
7End2end ConformerTest WER3.7—Unverified
8MoCo + wav2vec (w/o extLM)Test WER2.7—Unverified
9CTC/AttentionTest WER1.5—Unverified
10WhisperTest WER1.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SpatialNetCER14.5—Unverified
2CleanMel-L-maskCER14.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ConformerTest WER15.32—Unverified
2Whisper-largev3-finetunedTest WER10.82—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)1.89—Unverified
#ModelMetricClaimedVerifiedStatus
1DistillAVWER1.4—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)4.28—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)8.04—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer TransducerWER (%)3.36—Unverified
#ModelMetricClaimedVerifiedStatus
1Conformer Transducer (German)WER (%)8.98—Unverified