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 37513800 of 6433 papers

TitleStatusHype
Quantifying and Maximizing the Benefits of Back-End Noise Adaption on Attention-Based Speech Recognition Models0
Quantifying the Dialect Gap and its Correlates Across Languages0
Quantifying the Role of Textual Predictability in Automatic Speech Recognition0
Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective0
Quantitative Analysis of Image Classification Techniques for Memory-Constrained Devices0
Quantization of Acoustic Model Parameters in Automatic Speech Recognition Framework0
Quantization of Deep Neural Networks for Accurate Edge Computing0
Quantized Approximate Signal Processing (QASP): Towards Homomorphic Encryption for audio0
Quaternion Neural Networks for Multi-channel Distant Speech Recognition0
Query-by-example on-device keyword spotting0
QuEst - A translation quality estimation framework0
Quran Recitation Recognition using End-to-End Deep Learning0
Qwen vs. Gemma Integration with Whisper: A Comparative Study in Multilingual SpeechLLM Systems0
RACAI Entry for the IWSLT 2016 Shared Task0
RADIA -- Radio Advertisement Detection with Intelligent Analytics0
Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals0
RAND: Robustness Aware Norm Decay For Quantized Seq2seq Models0
Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting0
Rapidly Testing the Interaction Model of a Pronunciation Training System via Wizard-of-Oz0
RAPIDNN: In-Memory Deep Neural Network Acceleration Framework0
RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition0
Rate-Invariant Analysis of Trajectories on Riemannian Manifolds with Application in Visual Speech Recognition0
Rationalizing Predictions by Adversarial Information Calibration0
Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition0
Readability Assessment of Translated Texts0
Reading Miscue Detection in Primary School through Automatic Speech Recognition0
Realization of common statistical methods in computational linguistics with functional automata0
Real-time Detection of AI-Generated Speech for DeepFake Voice Conversion0
Real-time Incremental Speech-to-Speech Translation of Dialogs0
Real-Time Keyword Extraction from Conversations0
Real-Time Neural Voice Camouflage0
Real-Time Speech Emotion and Sentiment Recognition for Interactive Dialogue Systems0
Real-Time Statistical Speech Translation0
Real to H-space Encoder for Speech Recognition0
Reassessing Noise Augmentation Methods in the Context of Adversarial Speech0
Recent Advances in Convolutional Neural Networks0
Recent Advances in End-to-End Automatic Speech Recognition0
Recent Progresses in Deep Learning based Acoustic Models (Updated)0
Recent Progress in the CUHK Dysarthric Speech Recognition System0
Recipe For Building Robust Spoken Dialog State Trackers: Dialog State Tracking Challenge System Description0
Recipes for building voice search UIs for automotive0
RecLight: A Recurrent Neural Network Accelerator with Integrated Silicon Photonics0
Recognition of Distress Calls in Distant Speech Setting: a Preliminary Experiment in a Smart Home0
Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers0
Recognition of Isolated Words using Zernike and MFCC features for Audio Visual Speech Recognition0
Recognize Foreign Low-Frequency Words with Similar Pairs0
Recognizing Dysarthric Speech due to Amyotrophic Lateral Sclerosis with Across-Speaker Articulatory Normalization0
Recognizing long-form speech using streaming end-to-end models0
Recognizing Multi-talker Speech with Permutation Invariant Training0
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks0
Show:102550
← PrevPage 76 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