SOTAVerified

Speech Recognition

Speech Recognition is the task of converting spoken language into text. It involves recognizing the words spoken in an audio recording and transcribing them into a written format. The goal is to accurately transcribe the speech in real-time or from recorded audio, taking into account factors such as accents, speaking speed, and background noise.

( Image credit: SpecAugment )

Papers

Showing 351400 of 6433 papers

TitleStatusHype
Large-Scale Streaming End-to-End Speech Translation with Neural TransducersCode1
3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognitionCode1
Low-Latency Speech Separation Guided Diarization for Telephone ConversationsCode1
PriMock57: A Dataset Of Primary Care Mock ConsultationsCode1
HiFi-VC: High Quality ASR-Based Voice ConversionCode1
A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker ExtractionCode1
How Does Pre-trained Wav2Vec 2.0 Perform on Domain Shifted ASR? An Extensive Benchmark on Air Traffic Control CommunicationsCode1
indic-punct: An automatic punctuation restoration and inverse text normalization framework for Indic languagesCode1
Streaming Speaker-Attributed ASR with Token-Level Speaker EmbeddingsCode1
Recent improvements of ASR models in the face of adversarial attacksCode1
Shifted Chunk Encoder for Transformer Based Streaming End-to-End ASRCode1
Earnings-22: A Practical Benchmark for Accents in the WildCode1
Integrating Lattice-Free MMI into End-to-End Speech RecognitionCode1
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech RecognitionCode1
ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversionCode1
LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERTCode1
Dual-Path Style Learning for End-to-End Noise-Robust Speech RecognitionCode1
Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech RecognitionCode1
FLUTE: A Scalable, Extensible Framework for High-Performance Federated Learning SimulationsCode1
Automatic Speech Recognition for Speech Assessment of Persian Preschool ChildrenCode1
A^3T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and EditingCode1
Neural Predictor for Black-Box Adversarial Attacks on Speech RecognitionCode1
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question AnsweringCode1
Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR ErrorsCode1
Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech RecognitionCode1
AISHELL-NER: Named Entity Recognition from Chinese SpeechCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech RecognitionCode1
Self-supervised Learning with Random-projection Quantizer for Speech RecognitionCode1
Streaming Multi-Talker ASR with Token-Level Serialized Output TrainingCode1
Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge SelectionCode1
CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command RecognitionCode1
Improving Mandarin End-to-End Speech Recognition with Word N-gram Language ModelCode1
A Discriminative Hierarchical PLDA-based Model for Spoken Language RecognitionCode1
Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-ArtCode1
Regularizing End-to-End Speech Translation with Triangular Decomposition AgreementCode1
Self-Supervised Learning for speech recognition with Intermediate layer supervisionCode1
X-Vector based voice activity detection for multi-genre broadcast speech-to-textCode1
Consistent Training and Decoding For End-to-end Speech Recognition Using Lattice-free MMICode1
Romanian Speech Recognition Experiments from the ROBIN ProjectCode1
SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural SpeechCode1
XLS-R: Self-supervised Cross-lingual Speech Representation Learning at ScaleCode1
MT3: Multi-Task Multitrack Music TranscriptionCode1
A transfer learning based approach for pronunciation scoringCode1
Cross Attention Augmented Transducer Networks for Simultaneous TranslationCode1
Efficiently Modeling Long Sequences with Structured State SpacesCode1
Revisiting joint decoding based multi-talker speech recognition with DNN acoustic modelCode1
SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language ProcessingCode1
CORAA: a large corpus of spontaneous and prepared speech manually validated for speech recognition in Brazilian PortugueseCode1
BERTraffic: BERT-based Joint Speaker Role and Speaker Change Detection for Air Traffic Control CommunicationsCode1
Show:102550
← PrevPage 8 of 129Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1AmNetWord Error Rate (WER)8.6Unverified
2HMM-(SAT)GMMWord Error Rate (WER)8Unverified
3Local Prior Matching (Large Model)Word Error Rate (WER)7.19Unverified
4SnipsWord Error Rate (WER)6.4Unverified
5Li-GRUWord Error Rate (WER)6.2Unverified
6HMM-DNN + pNorm*Word Error Rate (WER)5.5Unverified
7CTC + policy learningWord Error Rate (WER)5.42Unverified
8Deep Speech 2Word Error Rate (WER)5.33Unverified
9HMM-TDNN + iVectorsWord Error Rate (WER)4.8Unverified
10Gated ConvNetsWord Error Rate (WER)4.8Unverified
#ModelMetricClaimedVerifiedStatus
1Local Prior Matching (Large Model)Word Error Rate (WER)20.84Unverified
2SnipsWord Error Rate (WER)16.5Unverified
3Local Prior Matching (Large Model, ConvLM LM)Word Error Rate (WER)15.28Unverified
4Deep Speech 2Word Error Rate (WER)13.25Unverified
5TDNN + pNorm + speed up/down speechWord Error Rate (WER)12.5Unverified
6CTC-CRF 4gram-LMWord Error Rate (WER)10.65Unverified
7Convolutional Speech RecognitionWord Error Rate (WER)10.47Unverified
8MT4SSLWord Error Rate (WER)9.6Unverified
9Jasper DR 10x5Word Error Rate (WER)8.79Unverified
10EspressoWord Error Rate (WER)8.7Unverified
#ModelMetricClaimedVerifiedStatus
1Deep SpeechPercentage error20Unverified
2DNN-HMMPercentage error18.5Unverified
3CD-DNNPercentage error16.1Unverified
4DNNPercentage error16Unverified
5DNN + DropoutPercentage error15Unverified
6DNN BMMIPercentage error12.9Unverified
7DNN MPEPercentage error12.9Unverified
8DNN MMIPercentage error12.9Unverified
9HMM-TDNN + pNorm + speed up/down speechPercentage error12.9Unverified
10HMM-DNN +sMBRPercentage error12.6Unverified
#ModelMetricClaimedVerifiedStatus
1LSNNPercentage error33.2Unverified
2LAS multitask with indicators samplingPercentage error20.4Unverified
3Soft Monotonic Attention (ours, offline)Percentage error20.1Unverified
4QCNN-10L-256FMPercentage error19.64Unverified
5Bi-LSTM + skip connections w/ CTCPercentage error17.7Unverified
6Bi-RNN + AttentionPercentage error17.6Unverified
7RNN-CRF on 24(x3) MFSCPercentage error17.3Unverified
8CNN in time and frequency + dropout, 17.6% w/o dropoutPercentage error16.7Unverified
9Light Gated Recurrent UnitsPercentage error16.7Unverified
10GRUPercentage error16.6Unverified
#ModelMetricClaimedVerifiedStatus
1AttWord Error Rate (WER)18.7Unverified
2CTC/AttWord Error Rate (WER)6.7Unverified
3BRA-EWord Error Rate (WER)6.63Unverified
4CTC-CRF 4gram-LMWord Error Rate (WER)6.34Unverified
5BATWord Error Rate (WER)4.97Unverified
6ParaformerWord Error Rate (WER)4.95Unverified
7U2Word Error Rate (WER)4.72Unverified
8UMAWord Error Rate (WER)4.7Unverified
9Lightweight TransducerWord Error Rate (WER)4.31Unverified
10CIF-HKD With LMWord Error Rate (WER)4.1Unverified
#ModelMetricClaimedVerifiedStatus
1Jasper 10x3Word Error Rate (WER)6.9Unverified
2CNN over RAW speech (wav)Word Error Rate (WER)5.6Unverified
3CTC-CRF 4gram-LMWord Error Rate (WER)3.79Unverified
4Deep Speech 2Word Error Rate (WER)3.6Unverified
5test-set on open vocabulary (i.e. harder), model = HMM-DNN + pNorm*Word Error Rate (WER)3.6Unverified
6Convolutional Speech RecognitionWord Error Rate (WER)3.5Unverified
7TC-DNN-BLSTM-DNNWord Error Rate (WER)3.5Unverified
8EspressoWord Error Rate (WER)3.4Unverified
9CTC-CRF VGG-BLSTMWord Error Rate (WER)3.2Unverified
10Transformer with Relaxed AttentionWord Error Rate (WER)3.19Unverified