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 851–900 of 3012 papers

TitleStatusHype
Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition—0
Deep Recurrent Neural Networks for Acoustic Modelling—0
Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends—0
Deep Shallow Fusion for RNN-T Personalization—0
Cascaded Cross-Modal Transformer for Request and Complaint Detection—0
Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study—0
Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion—0
Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization—0
Deep versus Wide: An Analysis of Student Architectures for Task-Agnostic Knowledge Distillation of Self-Supervised Speech Models—0
Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video—0
Deep Xi as a Front-End for Robust Automatic Speech Recognition—0
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser—0
Cascaded CNN-resBiLSTM-CTC: An End-to-End Acoustic Model For Speech Recognition—0
Deliberation Model Based Two-Pass End-to-End Speech Recognition—0
Deliberation Model for On-Device Spoken Language Understanding—0
Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems—0
DENOASR: Debiasing ASRs through Selective Denoising—0
Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition—0
Densely Connected Convolutional Networks for Speech Recognition—0
CarneliNet: Neural Mixture Model for Automatic Speech Recognition—0
Deploying self-supervised learning in the wild for hybrid automatic speech recognition—0
Deploying Technology to Save Endangered Languages—0
Design and Development of Speech Corpora for Air Traffic Control Training—0
Designing a Speech Corpus for the Development and Evaluation of Dictation Systems in Latvian—0
Adversarial synthesis based data-augmentation for code-switched spoken language identification—0
Designing the Next Generation of Intelligent Personal Robotic Assistants for the Physically Impaired—0
Detecting Audio Attacks on ASR Systems with Dropout Uncertainty—0
Detecting Mild Cognitive Impairment by Exploiting Linguistic Information from Transcripts—0
Disentangling Prosody Representations with Unsupervised Speech Reconstruction—0
Developing ASR for Indonesian-English Bilingual Language Teaching—0
Developing Automatic Speech Recognition for Scottish Gaelic—0
Developing language technology tools and resources for a resource-poor language: Sindhi—0
Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability—0
Development of Automatic Speech Recognition for the Documentation of Cook Islands Māori—0
D\'eveloppement de ressources en swahili pour un syt\`eme de reconnaisance automatique de la parole (Developments of Swahili resources for an automatic speech recognition system) [in French]—0
Device Directedness with Contextual Cues for Spoken Dialog Systems—0
Device-directed Utterance Detection—0
DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition—0
Automatic recognition of child speech for robotic applications in noisy environments—0
Diacritic Recognition Performance in Arabic ASR—0
Capturing Multi-Resolution Context by Dilated Self-Attention—0
Dialectal Speech Recognition and Translation of Swiss German Speech to Standard German Text: Microsoft's Submission to SwissText 2021—0
Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT—0
Dialect-Specific Models for Automatic Speech Recognition of African American Vernacular English—0
Capitalization and Punctuation Restoration: a Survey—0
Dialogue Act Segmentation for Vietnamese Human-Human Conversational Texts—0
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers—0
Can Whisper perform speech-based in-context learning?—0
Are disentangled representations all you need to build speaker anonymization systems?—0
Disfluency Detection with Unlabeled Data and Small BERT Models—0
Show:102550
← PrevPage 18 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