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 34013450 of 6433 papers

TitleStatusHype
Non-autoregressive Mandarin-English Code-switching Speech Recognition0
AI4D -- African Language ProgramCode0
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency0
SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitionCode0
End-to-End Speaker-Attributed ASR with Transformer0
Streaming Multi-talker Speech Recognition with Joint Speaker Identification0
SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network0
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding0
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion0
Speaker conditioned acoustic modeling for multi-speaker conversational ASR0
Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition0
Talk, Don't Write: A Study of Direct Speech-Based Image Retrieval0
TransfoRNN: Capturing the Sequential Information in Self-Attention Representations for Language Modeling0
Towards Lifelong Learning of End-to-end ASR0
Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties0
TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech RecognitionCode0
On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRCode0
Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition0
ExKaldi-RT: A Real-Time Automatic Speech Recognition Extension Toolkit of KaldiCode1
HMM-Free Encoder Pre-Training for Streaming RNN Transducer0
Context-sensitive evaluation of automatic speech recognition: considering user experience & language variation0
Dialect Identification through Adversarial Learning and Knowledge Distillation on Romanian BERT0
A Survey on Paralinguistics in Tamil Speech Processing0
Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yol\'oxochitl Mixtec0
Disfluency Correction using Unsupervised and Semi-supervised Learning0
Tutorial Proposal: End-to-End Speech Translation0
Interactive spatial speech recognition maps based on simulated speech recognition experiments0
Configurable Privacy-Preserving Automatic Speech Recognition0
Keyword Transformer: A Self-Attention Model for Keyword SpottingCode1
Multilingual and code-switching ASR challenges for low resource Indian languagesCode1
Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition0
Adversarial Attacks and Defenses for Speech Recognition Systems0
XY Neural Networks0
Integer-only Zero-shot Quantization for Efficient Speech RecognitionCode1
Compressing 1D Time-Channel Separable Convolutions using Sparse Random Ternary Matrices0
Large-Scale Pre-Training of End-to-End Multi-Talker ASR for Meeting Transcription with Single Distant Microphone0
MediaSpeech: Multilanguage ASR Benchmark and DatasetCode1
A study of latent monotonic attention variants0
Improved Meta-Learning Training for Speaker Verification0
Scaling sparsemax based channel selection for speech recognition with ad-hoc microphone arrays0
Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition0
Shrinking Bigfoot: Reducing wav2vec 2.0 footprint0
Transformer-based end-to-end speech recognition with residual Gaussian-based self-attention0
Libri-adhoc40: A dataset collected from synchronized ad-hoc microphone arraysCode1
Quantifying Bias in Automatic Speech RecognitionCode0
BART based semantic correction for Mandarin automatic speech recognition system0
Construction of a Large-scale Japanese ASR Corpus on TV Recordings0
Mutually-Constrained Monotonic Multihead Attention for Online ASR0
Leveraging pre-trained representations to improve access to untranscribed speech from endangered languagesCode1
Radically Old Way of Computing Spectra: Applications in End-to-End ASRCode1
Show:102550
← PrevPage 69 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