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 50015050 of 6433 papers

TitleStatusHype
Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech RecognitionCode0
On Training Recurrent Networks with Truncated Backpropagation Through Time in Speech Recognition0
Foreign English Accent Adjustment by Learning Phonetic Patterns0
Improving Deep Learning through Automatic Programming0
Learning The Sequential Temporal Information with Recurrent Neural Networks0
Neural Language Codes for Multilingual Acoustic Models0
Exploring End-to-End Techniques for Low-Resource Speech Recognition0
Weight-importance sparse training in keyword spotting0
Integrating Multiple NLP Technologies into an Open-source Platform for Multilingual Media Monitoring0
Automatic Detection of Code-switching Style from Acoustics0
Augmented Cyclic Adversarial Learning for Low Resource Domain AdaptationCode0
Improving Slot Filling in Spoken Language Understanding with Joint Pointer and AttentionCode0
Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base0
Language Informed Modeling of Code-Switched Text0
A Bilingual Interactive Human Avatar Dialogue System0
Low-Resource Machine Transliteration Using Recurrent Neural Networks of Asian Languages0
The Importance of Recommender and Feedback Features in a Pronunciation Learning Aid0
Sentiment Analysis using Imperfect Views from Spoken Language and Acoustic Modalities0
OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models0
Joint Part-of-Speech and Language ID Tagging for Code-Switched Data0
Language Modeling for Code-Mixing: The Role of Linguistic Theory based Synthetic Data0
A Unified Neural Architecture for Joint Dialog Act Segmentation and Recognition in Spoken Dialog System0
Estimating User Interest from Open-Domain Dialogue0
Phone Merging For Code-Switched Speech Recognition0
Global-Locally Self-Attentive Encoder for Dialogue State Tracking0
Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR0
Contextual Language Model Adaptation for Conversational Agents0
Evaluating Gammatone Frequency Cepstral Coefficients with Neural Networks for Emotion Recognition from SpeechCode0
Deep Reinforcement Learning: An Overview0
Persistent Hidden States and Nonlinear Transformation for Long Short-Term Memory0
Towards Automated Single Channel Source Separation using Neural Networks0
Quaternion Convolutional Neural Networks for End-to-End Automatic Speech RecognitionCode0
Recurrent DNNs and its Ensembles on the TIMIT Phone Recognition TaskCode0
Speaker Adapted Beamforming for Multi-Channel Automatic Speech Recognition0
Recommending Scientific Videos based on Metadata Enrichment using Linked Open Data0
End-to-End Speech Recognition From the Raw WaveformCode0
A Survey of Recent DNN Architectures on the TIMIT Phone Recognition TaskCode0
Semi-tied Units for Efficient Gating in LSTM and Highway Networks0
Extending Recurrent Neural Aligner for Streaming End-to-End Speech Recognition in Mandarin0
Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition0
Deep Lip Reading: a comparison of models and an online application0
RAPIDNN: In-Memory Deep Neural Network Acceleration Framework0
Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems0
A Study of Enhancement, Augmentation, and Autoencoder Methods for Domain Adaptation in Distant Speech Recognition0
Unsupervised Adaptation with Interpretable Disentangled Representations for Distant Conversational Speech Recognition0
Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages0
Quaternion Recurrent Neural NetworksCode0
Domain Adversarial Training for Accented Speech Recognition0
Training Augmentation with Adversarial Examples for Robust Speech Recognition0
LSTM Benchmarks for Deep Learning FrameworksCode0
Show:102550
← PrevPage 101 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