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 24512500 of 6433 papers

TitleStatusHype
Code-Switching without Switching: Language Agnostic End-to-End Speech Translation0
Articulatory information and Multiview Features for Large Vocabulary Continuous Speech Recognition0
Code-Switching Text Generation and Injection in Mandarin-English ASR0
Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition0
Articulatory Features for ASR of Pathological Speech0
A Framework for Synthetic Audio Conversations Generation using Large Language Models0
Acoustic feature learning using cross-domain articulatory measurements0
Code-Switching Detection with Data-Augmented Acoustic and Language Models0
Codeswitching Detection via Lexical Features in Conditional Random Fields0
Articulatory and bottleneck features for speaker-independent ASR of dysarthric speech0
Code-Switching Detection Using ASR-Generated Language Posteriors0
A Robotic Agent in a Virtual Environment that Performs Situated Incremental Understanding of Navigational Utterances0
Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences0
Code Switched and Code Mixed Speech Recognition for Indic languages0
A Review of Speaker Diarization: Recent Advances with Deep Learning0
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition0
Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations0
A Review of Sparse Expert Models in Deep Learning0
A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding0
Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognition0
Cocktail-Party Audio-Visual Speech Recognition0
A Review of Recent Advances of Binary Neural Networks for Edge Computing0
CoBiLiRo: A Research Platform for Bimodal Corpora0
CobaltF: A Fluent Metric for MT Evaluation0
A review of on-device fully neural end-to-end automatic speech recognition algorithms0
Affect Recognition in Conversations Using Large Language Models0
Coarse-To-Fine And Cross-Lingual ASR Transfer0
CoALT: A Software for Comparing Automatic Labelling Tools0
A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search0
CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge0
CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge0
A Review of Meta-Reinforcement Learning for Deep Neural Networks Architecture Search0
A Fast-Converged Acoustic Modeling for Korean Speech Recognition: A Preliminary Study on Time Delay Neural Network0
Acoustic data-driven lexicon learning based on a greedy pronunciation selection framework0
CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments0
CNN architecture extraction on edge GPU0
A Review of Hybrid and Ensemble in Deep Learning for Natural Language Processing0
CMU’s IWSLT 2022 Dialect Speech Translation System0
A Review of Deep Learning Techniques for Speech Processing0
Community Detection Clustering via Gumbel Softmax0
Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study0
A Dynamic Programming Algorithm for Computing N-gram Posteriors from Lattices0
Acoustic-aware Non-autoregressive Spell Correction with Mask Sample Decoding0
AccentFold: A Journey through African Accents for Zero-Shot ASR Adaptation to Target Accents0
3-D Feature and Acoustic Modeling for Far-Field Speech Recognition0
Listening while Speaking and Visualizing: Improving ASR through Multimodal Chain0
Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition0
Cloud-Based Face and Speech Recognition for Access Control Applications0
A Research Platform for Multi-Robot Dialogue with Humans0
Cloud-based Automatic Speech Recognition Systems for Southeast Asian Languages0
Show:102550
← PrevPage 50 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