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 1351–1400 of 3012 papers

TitleStatusHype
Memory-Efficient Training of RNN-Transducer with Sampled Softmax—0
Improving Speech Recognition for Indic Languages using Language Model—0
Code Switched and Code Mixed Speech Recognition for Indic languages—0
Is Word Error Rate a good evaluation metric for Speech Recognition in Indic Languages?—0
Federated Domain Adaptation for ASR with Full Self-Supervision—0
Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech RecognitionCode0
Streaming Speaker-Attributed ASR with Token-Level Speaker EmbeddingsCode1
ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversionCode1
Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text NormalizationCode0
4-bit Conformer with Native Quantization Aware Training for Speech RecognitionCode2
Improving Generalization of Deep Neural Network Acoustic Models with Length Perturbation and N-best Based Label Smoothing—0
Earnings-22: A Practical Benchmark for Accents in the WildCode1
Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformer—0
Short-Term Word-Learning in a Dynamically Changing Environment—0
Integrating Lattice-Free MMI into End-to-End Speech RecognitionCode1
LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERTCode1
Analysis of EEG frequency bands for Envisioned Speech RecognitionCode0
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRCode1
Frequency-Directional Attention Model for Multilingual Automatic Speech Recognition—0
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech RecognitionCode1
Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems—0
CMGAN: Conformer-based Metric GAN for Speech EnhancementCode2
Dual-Path Style Learning for End-to-End Noise-Robust Speech RecognitionCode1
Finnish Parliament ASR corpus - Analysis, benchmarks and statisticsCode0
A Dataset for Speech Emotion Recognition in Greek Theatrical PlaysCode0
Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech RecognitionCode1
A Speech Representation Anonymization Framework via Selective Noise PerturbationCode0
Impact of Dataset on Acoustic Models for Automatic Speech Recognition—0
Speech-enhanced and Noise-aware Networks for Robust Speech RecognitionCode0
Automatic Speech Recognition for Speech Assessment of Persian Preschool ChildrenCode1
Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion—0
Lahjoita puhetta -- a large-scale corpus of spoken Finnish with some benchmarks—0
Computing Optimal Location of Microphone for Improved Speech Recognition—0
Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis—0
Pseudo Label Is Better Than Human Label—0
A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis—0
Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition—0
Neural Predictor for Black-Box Adversarial Attacks on Speech RecognitionCode1
Representative Subset Selection for Efficient Fine-Tuning in Self-Supervised Speech Recognition—0
Prediction of speech intelligibility with DNN-based performance measures—0
Whither the Priors for (Vocal) Interactivity?—0
RED-ACE: Robust Error Detection for ASR using Confidence EmbeddingsCode0
Spectral Modification Based Data Augmentation For Improving End-to-End ASR For Children's Speech—0
Transformer-based Streaming ASR with Cumulative Attention—0
Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems—0
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question AnsweringCode1
A practical framework for multi-domain speech recognition and an instance sampling method to neural language modeling—0
Which French speech recognition system for assistant robots?—0
Towards Contextual Spelling Correction for Customization of End-to-end Speech Recognition SystemsCode0
Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training—0
Show:102550
← PrevPage 28 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