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 55515600 of 6433 papers

TitleStatusHype
An Efficient and Effective Online Sentence Segmenter for Simultaneous Interpretation0
Automatic Speech Recognition Errors as a Predictor of L2 Listening Difficulties0
A Dataset for Multimodal Question Answering in the Cultural Heritage Domain0
Comparison of Grapheme-to-Phoneme Conversion Methods on a Myanmar Pronunciation Dictionary0
Using Ambiguity Detection to Streamline Linguistic Annotation0
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA0
Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition0
Invariant Representations for Noisy Speech Recognition0
An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning0
Geometric deep learning on graphs and manifolds using mixture model CNNsCode0
Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation0
Learning to Distill: The Essence Vector Modeling Framework0
Deep Recurrent Convolutional Neural Network: Improving Performance For Speech Recognition0
Robust end-to-end deep audiovisual speech recognition0
Neural Information Retrieval: A Literature Review0
Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models0
Compacting Neural Network Classifiers via Dropout Training0
Lip Reading Sentences in the Wild0
Tricks from Deep Learning0
Audio Visual Speech Recognition using Deep Recurrent Neural Networks0
Automatic recognition of child speech for robotic applications in noisy environments0
Discriminative Acoustic Word Embeddings: Recurrent Neural Network-Based Approaches0
Neural Networks Designing Neural Networks: Multi-Objective Hyper-Parameter Optimization0
Codeswitching Detection via Lexical Features in Conditional Random Fields0
Word-Level Language Identification and Predicting Codeswitching Points in Swahili-English Language Data0
Solving Verbal Questions in IQ Test by Knowledge-Powered Word Embedding0
Joint Transition-based Dependency Parsing and Disfluency Detection for Automatic Speech Recognition Texts0
Neural Morphological Analysis: Encoding-Decoding Canonical Segments0
Neural Sentiment Classification with User and Product AttentionCode0
Richer Interpolative Smoothing Based on Modified Kneser-Ney Language Modeling0
Convolutional Neural Network Language ModelsCode0
Latent Tree Language ModelCode0
Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems0
Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition0
Still not there? Comparing Traditional Sequence-to-Sequence Models to Encoder-Decoder Neural Networks on Monotone String Translation Tasks0
End-to-End Training Approaches for Discriminative Segmental Models0
Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalisation0
Embodiment of Learning in Electro-Optical Signal Processors0
A Bayesian Approach to Estimation of Speaker Normalization Parameters0
Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models0
Small-footprint Highway Deep Neural Networks for Speech Recognition0
End-to-end attention-based distant speech recognition with Highway LSTM0
Achieving Human Parity in Conversational Speech Recognition0
Exploiting Sentence and Context Representations in Deep Neural Models for Spoken Language Understanding0
Long Short-Term Memory based Convolutional Recurrent Neural Networks for Large Vocabulary Speech Recognition0
Multiple Instance Learning Convolutional Neural Networks for Object Recognition0
Very Deep Convolutional Networks for End-to-End Speech RecognitionCode0
Latent Sequence Decompositions0
A Semantic Analyzer for the Comprehension of the Spontaneous Arabic Speech0
A Gentle Tutorial of Recurrent Neural Network with Error BackpropagationCode0
Show:102550
← PrevPage 112 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