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 2351–2400 of 3012 papers

TitleStatusHype
Audio-attention discriminative language model for ASR rescoring—0
Semantic Mask for Transformer based End-to-End Speech RecognitionCode0
Kurdish (Sorani) Speech to Text: Presenting an Experimental DatasetCode0
Improving Voice Separation by Incorporating End-to-end Speech RecognitionCode0
Designing the Next Generation of Intelligent Personal Robotic Assistants for the Physically Impaired—0
ASR is all you need: cross-modal distillation for lip reading—0
ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment—0
Independent language modeling architecture for end-to-end ASR—0
Improving EEG based Continuous Speech Recognition—0
Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin—0
On using 2D sequence-to-sequence models for speech recognition—0
CAT: CRF-based ASR ToolkitCode0
Deep Spiking Neural Networks for Large Vocabulary Automatic Speech RecognitionCode0
3-D Feature and Acoustic Modeling for Far-Field Speech Recognition—0
Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?—0
Data Efficient Direct Speech-to-Text Translation with Modality Agnostic Meta-Learning—0
Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition—0
Evaluating Voice Conversion-based Privacy Protection against Informed Attackers—0
Speaker Adaptation for Attention-Based End-to-End Speech Recognition—0
A Simplified Fully Quantized Transformer for End-to-end Speech RecognitionCode0
Investigation of Error Simulation Techniques for Learning Dialog Policies for Conversational Error Recovery—0
Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates—0
A comparison of end-to-end models for long-form speech recognition—0
RNN-T For Latency Controlled ASR With Improved Beam Search—0
SHARP: An Adaptable, Energy-Efficient Accelerator for Recurrent Neural Network—0
Data Augmentation for End-to-End Speech Translation: FBK@IWSLT ‘19—0
Entity resolution for noisy ASR transcripts—0
Chameleon: A Language Model Adaptation Toolkit for Automatic Speech Recognition of Conversational Speech—0
Transformer-based Cascaded Multimodal Speech Translation—0
Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?—0
Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation—0
DFSMN-SAN with Persistent Memory Model for Automatic Speech Recognition—0
Unsupervised pre-training for sequence to sequence speech recognition—0
Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding—0
Meta Learning for End-to-End Low-Resource Speech Recognition—0
Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural NetworksCode0
Towards Online End-to-end Transformer Automatic Speech Recognition—0
L2RS: A Learning-to-Rescore Mechanism for Automatic Speech Recognition—0
Recognizing long-form speech using streaming end-to-end models—0
Analyzing the impact of speaker localization errors on speech separation for automatic speech recognitionCode0
Pre-training in Deep Reinforcement Learning for Automatic Speech Recognition—0
ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech ToolkitCode0
A practical two-stage training strategy for multi-stream end-to-end speech recognition—0
Analyzing ASR pretraining for low-resource speech-to-text translation—0
RNN based Incremental Online Spoken Language Understanding—0
Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model—0
Robust Neural Machine Translation for Clean and Noisy Speech Transcripts—0
Word-level Embeddings for Cross-Task Transfer Learning in Speech ProcessingCode0
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR—0
AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks—0
Show:102550
← PrevPage 48 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