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 951–1000 of 3012 papers

TitleStatusHype
Don't Be So Sure! Boosting ASR Decoding via Confidence Relaxation—0
Don't Stop Self-Supervision: Accent Adaptation of Speech Representations via Residual Adapters—0
Do We Still Need Automatic Speech Recognition for Spoken Language Understanding?—0
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio—0
DRAFT: A Novel Framework to Reduce Domain Shifting in Self-supervised Learning and Its Application to Children's ASR—0
Driving ROVER with Segment-based ASR Quality Estimation—0
An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions—0
Dual Causal/Non-Causal Self-Attention for Streaming End-to-End Speech Recognition—0
On the Effectiveness of Pinyin-Character Dual-Decoding for End-to-End Mandarin Chinese ASR—0
Can You Hear It? Backdoor Attacks via Ultrasonic Triggers—0
Dual Language Models for Code Switched Speech Recognition—0
Can Whisper perform speech-based in-context learning?—0
Dual Script E2E framework for Multilingual and Code-Switching ASR—0
DUAL: Textless Spoken Question Answering with Speech Discrete Unit Adaptive Learning—0
Are disentangled representations all you need to build speaker anonymization systems?—0
DualVC 3: Leveraging Language Model Generated Pseudo Context for End-to-end Low Latency Streaming Voice Conversion—0
DualVoice: Speech Interaction that Discriminates between Normal and Whispered Voice Input—0
DuDe: Dual-Decoder Multilingual ASR for Indian Languages using Common Label Set—0
Emphasizing Unseen Words: New Vocabulary Acquisition for End-to-End Speech Recognition—0
DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting—0
Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition—0
Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model—0
Dynamic Context-Aware Streaming Pretrained Language Model For Inverse Text Normalization—0
Dynamic Data Pruning for Automatic Speech Recognition—0
Dynamic Latency for CTC-Based Streaming Automatic Speech Recognition With Emformer—0
Dynamic Masking for Improved Stability in Spoken Language Translation—0
Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition—0
Dyn-ASR: Compact, Multilingual Speech Recognition via Spoken Language and Accent Identification—0
Early Stage LM Integration Using Local and Global Log-Linear Combination—0
A Recorded Debating Dataset—0
Can We Train a Language Model Inside an End-to-End ASR Model? - Investigating Effective Implicit Language Modeling—0
E-Branchformer: Branchformer with Enhanced merging for speech recognition—0
Echo State Speech Recognition—0
Echotune: A Modular Extractor Leveraging the Variable-Length Nature of Speech in ASR Tasks—0
A Vietnamese Dialog Act Corpus Based on ISO 24617-2 standard—0
EdgeCRNN: an edgecomputing oriented model of acoustic feature enhancement for keyword spotting—0
探討聲學模型的合併技術與半監督鑑別式訓練於會議語音辨識之研究 (Investigating acoustic model combination and semi-supervised discriminative training for meeting speech recognition) [In Chinese]—0
會議語音辨識使用語者資訊之語言模型調適技術 (On the Use of Speaker-Aware Language Model Adaptation Techniques for Meeting Speech Recognition ) [In Chinese]—0
Can Visual Context Improve Automatic Speech Recognition for an Embodied Agent?—0
EEG based Continuous Speech Recognition using Transformers—0
Adversarial Speaker Adaptation—0
Effectively pretraining a speech translation decoder with Machine Translation data—0
AccentDB: A Database of Non-Native English Accents to Assist Neural Speech Recognition—0
Effectiveness of text to speech pseudo labels for forced alignment and cross lingual pretrained models for low resource speech recognition—0
Cantonese Automatic Speech Recognition Using Transfer Learning from Mandarin—0
Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuning—0
Effect of noise suppression losses on speech distortion and ASR performance—0
Effects of Language Relatedness for Cross-lingual Transfer Learning in Character-Based Language Models—0
BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech—0
A Wav2vec2-Based Experimental Study on Self-Supervised Learning Methods to Improve Child Speech Recognition—0
Show:102550
← PrevPage 20 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