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 701–750 of 3012 papers

TitleStatusHype
ASR Rescoring and Confidence Estimation with ELECTRA—0
Confidence Score Based Conformer Speaker Adaptation for Speech Recognition—0
Advocating Character Error Rate for Multilingual ASR Evaluation—0
Configurable Privacy-Preserving Automatic Speech Recognition—0
Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping—0
Conformer-based Hybrid ASR System for Switchboard Dataset—0
Conformer-Based Speech Recognition On Extreme Edge-Computing Devices—0
Chain of Correction for Full-text Speech Recognition with Large Language Models—0
A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition—0
Confusion2Vec: Towards Enriching Vector Space Word Representations with Representational Ambiguities—0
CEASR: A Corpus for Evaluating Automatic Speech Recognition—0
Connecting Speech Encoder and Large Language Model for ASR—0
Consistency Based Unsupervised Self-training For ASR Personalisation—0
A Multitask Training Approach to Enhance Whisper with Contextual Biasing and Open-Vocabulary Keyword Spotting—0
Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data—0
Constrained Variational Autoencoder for improving EEG based Speech Recognition Systems—0
Construction of a Large-scale Japanese ASR Corpus on TV Recordings—0
Content-Aware Speaker Embeddings for Speaker Diarisation—0
Context-aware Fine-tuning of Self-supervised Speech Models—0
Context-aware Neural-based Dialog Act Classification on Automatically Generated Transcriptions—0
Artificial Neural Networks to Recognize Speakers Division from Continuous Bengali Speech—0
Context-based out-of-vocabulary word recovery for ASR systems in Indian languages—0
Context-Dependent Acoustic Modeling without Explicit Phone Clustering—0
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model—0
Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation—0
Contextual Adapters for Personalized Speech Recognition in Neural Transducers—0
A Corpus and Phonetic Dictionary for Tunisian Arabic Speech Recognition—0
Contextual Biasing of Language Models for Speech Recognition in Goal-Oriented Conversational Agents—0
Contextual Biasing of Named-Entities with Large Language Models—0
Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm—0
Causal Structure Discovery for Error Diagnostics of Children's ASR—0
Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation—0
Contextualizing ASR Lattice Rescoring with Hybrid Pointer Network Language Model—0
Contextual Language Model Adaptation for Conversational Agents—0
Contextual RNN-T For Open Domain ASR—0
Contextual Semi-Supervised Learning: An Approach To Leverage Air-Surveillance and Untranscribed ATC Data in ASR Systems—0
Contextual Speech Recognition with Difficult Negative Training Examples—0
Contextual-Utterance Training for Automatic Speech Recognition—0
Causal Analysis of ASR Errors for Children: Quantifying the Impact of Physiological, Cognitive, and Extrinsic Factors—0
Continual Learning for On-Device Speech Recognition using Disentangled Conformers—0
Continual Learning in Machine Speech Chain Using Gradient Episodic Memory—0
Continual learning using lattice-free MMI for speech recognition—0
Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications—0
An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning—0
Articulatory Features for ASR of Pathological Speech—0
Continuous Learning for Children's ASR: Overcoming Catastrophic Forgetting with Elastic Weight Consolidation and Synaptic Intelligence—0
Continuously Learning New Words in Automatic Speech Recognition—0
Continuous Pseudo-Labeling from the Start—0
CASSANDRA: A multipurpose configurable voice-enabled human-computer-interface—0
Adversarial Training for Multilingual Acoustic Modeling—0
Show:102550
← PrevPage 15 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