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 44514500 of 6433 papers

TitleStatusHype
使用生成對抗網路於強健式自動語音辨識的應用(Exploiting Generative Adversarial Network for Robustness Automatic Speech Recognition)0
Multilingual End-to-End Speech Translation0
Domain Expansion in DNN-based Acoustic Models for Robust Speech Recognition0
探究端對端語音辨識於發音檢測與診斷(Investigating on Computer-Assisted Pronunciation Training Leveraging End-to-End Speech Recognition Techniques)0
State-of-the-Art Speech Recognition Using Multi-Stream Self-Attention With Dilated 1D ConvolutionsCode0
室內遠距離語音辨識實驗(Experiments on In-House Far-Field Speech Recognition)0
Additional Shared Decoder on Siamese Multi-view Encoders for Learning Acoustic Word Embeddings0
Spatio-Temporal Fusion Based Convolutional Sequence Learning for Lip Reading0
Neural Hybrid Recommender: Recommendation needs collaboration0
Language-Agnostic Syllabification with Neural Sequence LabelingCode0
Self-Attention Transducers for End-to-End Speech Recognition0
End-to-End Code-Switching ASR for Low-Resourced Language Pairs0
Improving RNN Transducer Modeling for End-to-End Speech RecognitionCode0
Optimizing Speech Recognition For The Edge0
Generating Robust Audio Adversarial Examples using Iterative Proportional Clipping0
Speech Recognition with Augmented Synthesized Speech0
Disentangling Speech and Non-Speech Components for Building Robust Acoustic Models from Found DataCode0
Unsupervised Learning of Efficient and Robust Speech Representations0
Self-Supervised Speech Recognition via Local Prior Matching0
AdaScale SGD: A Scale-Invariant Algorithm for Distributed Training0
Top-down training for neural networks0
Improved Training Techniques for Online Neural Machine Translation0
Breaking the Data Barrier: Towards Robust Speech Translation via Adversarial Stability Training0
Understanding Semantics from Speech Through Pre-training0
Improving OOV Detection and Resolution with External Language Models in Acoustic-to-Word ASR0
Persian Signature Verification using Fully Convolutional Networks0
A Random Gossip BMUF Process for Neural Language Modeling0
Self-Training for End-to-End Speech Recognition0
A Comparison of Hybrid and End-to-End Models for Syllable Recognition0
Code-Switched Language Models Using Neural Based Synthetic Data from Parallel Sentences0
Emotion Filtering at the Edge0
Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models0
NeMo: a toolkit for building AI applications using Neural Modules0
Harnessing Indirect Training Data for End-to-End Automatic Speech Translation: Tricks of the Trade0
Current Challenges in Spoken Dialogue Systems and Why They Are Critical for Those Living with Dementia0
An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models0
Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition0
FfDL : A Flexible Multi-tenant Deep Learning Platform0
A Comparative Study on Transformer vs RNN in Speech ApplicationsCode0
Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers0
Eligibility traces provide a data-inspired alternative to backpropagation through time0
Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model0
Language learning using Speech to Image retrieval0
Self-Teaching Networks0
Neural Network-Based Modeling of Phonetic Durations0
Learning Alignment for Multimodal Emotion Recognition from SpeechCode0
Bandwidth Embeddings for Mixed-bandwidth Speech RecognitionCode0
An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networks0
Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations0
Motivations, challenges, and perspectives for the development of an Automatic Speech Recognition System for the under-resourced Ngiemboon Language0
Show:102550
← PrevPage 90 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