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 29012950 of 6433 papers

TitleStatusHype
Improved Mask-CTC for Non-Autoregressive End-to-End ASR0
Improved Meta Learning for Low Resource Speech Recognition0
Improved Meta-Learning Training for Speaker Verification0
改良調變頻譜統計圖等化法於強健性語音辨識之研究 (Improved Modulation Spectrum Histogram Equalization for Robust Speech Recognition) [In Chinese]0
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer0
An Oral History Annotation Tool for INTER-VIEWs0
Advances and Challenges in Deep Lip Reading0
Improved Regularization Techniques for End-to-End Speech Recognition0
Enhancing Indonesian Automatic Speech Recognition: Evaluating Multilingual Models with Diverse Speech Variabilities0
Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information0
Contextual RNN-T For Open Domain ASR0
Improved Speech Enhancement with the Wave-U-Net0
Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit0
Improved Speech Representations with Multi-Target Autoregressive Predictive Coding0
Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs0
Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation0
Contextual-Utterance Training for Automatic Speech Recognition0
Enhancing Documentation of Hupa with Automatic Speech Recognition0
Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning0
Improved Transcription and Indexing of Oral History Interviews for Digital Humanities Research0
Improvements to deep convolutional neural networks for LVCSR0
Improve Sinhala Speech Recognition Through e2e LF-MMI Model0
Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis0
Improving Accented Speech Recognition with Multi-Domain Training0
Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning0
Improving accuracy of rare words for RNN-Transducer through unigram shallow fusion0
BridgeNets: Student-Teacher Transfer Learning Based on Recursive Neural Networks and its Application to Distant Speech Recognition0
Improving Arabic Diacritization through Syntactic Analysis0
Improving ASR Contextual Biasing with Guided Attention0
An Open Web Platform for Rule-Based Speech-to-Sign Translation0
Enhancing CTC-Based Visual Speech Recognition0
Improving Automatic Speech Recognition with Decoder-Centric Regularisation in Encoder-Decoder Models0
Improving Black-box Speech Recognition using Semantic Parsing0
Improving callsign recognition with air-surveillance data in air-traffic communication0
Enhancing CTC-based speech recognition with diverse modeling units0
Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models0
Improving Child Speech Recognition and Reading Mistake Detection by Using Prompts0
Improving child speech recognition with augmented child-like speech0
Improving Code-switched ASR with Linguistic Information0
Improving Code-Switching and Named Entity Recognition in ASR with Speech Editing based Data Augmentation0
Improving Code-switching Language Modeling with Artificially Generated Texts using Cycle-consistent Adversarial Networks0
Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition0
Breaking Walls: Pioneering Automatic Speech Recognition for Central Kurdish: End-to-End Transformer Paradigm0
Enhancing Code-Switching Speech Recognition with LID-Based Collaborative Mixture of Experts Model0
Improving Continuous Sign Language Recognition with Cross-Lingual Signs0
Improving cross-domain n-gram language modelling with skipgrams0
Improving Cross-Lingual Transfer Learning for End-to-End Speech Recognition with Speech Translation0
Improving CTC-AED model with integrated-CTC and auxiliary loss regularization0
Improving CTC-based ASR Models with Gated Interlayer Collaboration0
Enhancing Code-switching Speech Recognition with Interactive Language Biases0
Show:102550
← PrevPage 59 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