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 44014450 of 6433 papers

TitleStatusHype
Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition0
Successes and critical failures of neural networks in capturing human-like speech recognition0
Suffix Trees as Language Models0
SUH_ASR@LT-EDI-ACL2022: Transformer based Approach for Speech Recognition for Vulnerable Individuals in Tamil0
Summary on the ISCSLP 2022 Chinese-English Code-Switching ASR Challenge0
Supervised Adaptation of Sequence-to-Sequence Speech Recognition Systems using Batch-Weighting0
Supervised and Unsupervised Transfer Learning for Question Answering0
Supervised Attention in Sequence-to-Sequence Models for Speech Recognition0
Supervised Contrastive Learning for Accented Speech Recognition0
Supervised level-wise pretraining for recurrent neural network initialization in multi-class classification0
Supervised Morphological Segmentation in a Low-Resource Learning Setting using Conditional Random Fields0
Supervision-Guided Codebooks for Masked Prediction in Speech Pre-training0
Sur l'utilisation de la reconnaissance automatique de la parole pour l'aide au diagnostic diff\'erentiel entre la maladie de Parkinson et l'AMS (On using automatic speech recognition for the differential diagnosis of Parkinson's Disease and MSA This article presents a study regarding the contribution of automatic speech processing in the differential diagnosis between Parkinson's disease and MSA (Multi-System Atrophies))0
Surrogate Gradient Spiking Neural Networks as Encoders for Large Vocabulary Continuous Speech Recognition0
Survey of Machine Learning Accelerators0
SUTAV: A Turkish Audio-Visual Database0
Svarah: Evaluating English ASR Systems on Indian Accents0
Swedish Whispers; Leveraging a Massive Speech Corpus for Swedish Speech Recognition0
SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer0
Switching Independent Vector Analysis and Its Extension to Blind and Spatially Guided Convolutional Beamforming Algorithms0
SWP-LeafNET: A novel multistage approach for plant leaf identification based on deep CNN0
Syllabification by Phone Categorization0
Syllable and language model based features for detecting non-scorable tests in spoken language proficiency assessment applications0
Syllable based DNN-HMM Cantonese Speech to Text System0
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition0
Synchronous Transformers for End-to-End Speech Recognition0
Syntactic and Semantic Features For Code-Switching Factored Language Models0
Syntactic annotation of spontaneous speech: application to call-center conversation data0
Synth2Aug: Cross-domain speaker recognition with TTS synthesized speech0
SynthASR: Unlocking Synthetic Data for Speech Recognition0
Synthesising Audio Adversarial Examples for Automatic Speech Recognition0
Synthesizing Dysarthric Speech Using Multi-talker TTS for Dysarthric Speech Recognition0
Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition0
Synthetic Dataset Generation for Privacy-Preserving Machine Learning0
Synthetic Query Generation using Large Language Models for Virtual Assistants0
SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision0
Synt++: Utilizing Imperfect Synthetic Data to Improve Speech Recognition0
Systolic Arrays and Structured Pruning Co-design for Efficient Transformers in Edge Systems0
Tackling Sequence to Sequence Mapping Problems with Neural Networks0
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks0
Tag and correct: high precision post-editing approach to correction of speech recognition errors0
Taiwanese Speech Recognition Based on Hybrid Deep Neural Network Architecture0
TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos0
TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline0
Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval0
Talking to Your TV: Context-Aware Voice Search with Hierarchical Recurrent Neural Networks0
TalTech Systems for the Interspeech 2025 ML-SUPERB 2.0 Challenge0
Tamil Language Computing: the Present and the Future0
Tandem Multitask Training of Speaker Diarisation and Speech Recognition for Meeting Transcription0
探究端對端混合模型架構於華語語音辨識 (An Investigation of Hybrid CTC-Attention Modeling in Mandarin Speech Recognition)0
Show:102550
← PrevPage 89 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