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 20512100 of 6433 papers

TitleStatusHype
Cross-document Event Coreference Resolution based on Cross-media Features0
Cross-Attribute Matrix Factorization Model with Shared User Embedding0
Cross-Attention Fusion of Visual and Geometric Features for Large Vocabulary Arabic Lipreading0
Cross-Attention End-to-End ASR for Two-Party Conversations0
A Transfer Learning Method for Speech Emotion Recognition from Automatic Speech Recognition0
Aligning Speech to Languages to Enhance Code-switching Speech Recognition0
Activity focused Speech Recognition of Preschool Children in Early Childhood Classrooms0
A collaborative filtering model with heterogeneous neural networks for recommender systems0
Cross-attention conformer for context modeling in speech enhancement for ASR0
Critical Appraisal of Artificial Intelligence-Mediated Communication0
A Tour of TensorFlow0
Aligning Pre-trained Models for Spoken Language Translation0
CRF-based Single-stage Acoustic Modeling with CTC Topology0
Creating Spoken Dialog Systems in Ultra-Low Resourced Settings0
Creating Lithuanian and Latvian Speech Corpora from Inaccurately Annotated Web Data0
A Toolkit for Joint Speaker Diarization and Identification with Application to Speaker-Attributed ASR0
Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers0
CR-CTC: Consistency regularization on CTC for improved speech recognition0
CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments0
A Token-Wise Beam Search Algorithm for RNN-T0
Learning Speech Representation From Contrastive Token-Acoustic Pretraining0
A three-dimensional approach to Visual Speech Recognition using Discrete Cosine Transforms0
A Lightweight Speaker Recognition System Using Timbre Properties0
CPPF: A contextual and post-processing-free model for automatic speech recognition0
CPJD Corpus: Crowdsourced Parallel Speech Corpus of Japanese Dialects0
Coupling Speech Encoders with Downstream Text Models0
A Text-to-Speech Pipeline, Evaluation Methodology, and Initial Fine-Tuning Results for Child Speech Synthesis0
A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systems0
Active Learning for Speech Recognition: the Power of Gradients0
A Code-Switching Corpus of Turkish-German Conversations0
使用字典學習法於強健性語音辨識(The Use of Dictionary Learning Approach for Robustness Speech Recognition) [In Chinese]0
On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition0
Regularization Advantages of Multilingual Neural Language Models for Low Resource Domains0
A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method0
11 TeraFLOPs per second photonic convolutional accelerator for deep learning optical neural networks0
Coupling Knowledge-Based and Data-Driven Systems for Named Entity Recognition0
A Text Normalisation System for Non-Standard English Words0
Counting What Counts: Decompounding for Keyphrase Extraction0
Could a Computer Architect Understand our Brain?0
A Temporal Simulator for Developing Turn-Taking Methods for Spoken Dialogue Systems0
A light-weight and efficient punctuation and word casing prediction model for on-device streaming ASR0
CoT-ST: Enhancing LLM-based Speech Translation with Multimodal Chain-of-Thought0
ATCSpeechNet: A multilingual end-to-end speech recognition framework for air traffic control systems0
CoSTA: Code-Switched Speech Translation using Aligned Speech-Text Interleaving0
ATCSpeech: a multilingual pilot-controller speech corpus from real Air Traffic Control environment0
Algorithms For Automatic Accentuation And Transcription Of Russian Texts In Speech Recognition Systems0
COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning0
Correlation Distance Skip Connection Denoising Autoencoder (CDSK-DAE) for Speech Feature Enhancement0
Correlated Bigram LSA for Unsupervised Language Model Adaptation0
CorrectSpeech: A Fully Automated System for Speech Correction and Accent Reduction0
Show:102550
← PrevPage 42 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