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 851900 of 6433 papers

TitleStatusHype
Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer GeneratorCode0
Greek2MathTex: A Greek Speech-to-Text Framework for LaTeX Equations GenerationCode0
Guiding Frame-Level CTC Alignments Using Self-knowledge DistillationCode0
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech RecognitionCode0
A Unified Speaker Adaptation Approach for ASRCode0
HuBERT-EE: Early Exiting HuBERT for Efficient Speech RecognitionCode0
Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMCode0
Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model DecodingCode0
Geometric deep learning on graphs and manifolds using mixture model CNNsCode0
Generating gender-ambiguous voices for privacy-preserving speech recognitionCode0
Long-term Conversation Analysis: Exploring Utility and PrivacyCode0
Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech RecognitionCode0
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired SpeechCode0
Gammatonegram Representation for End-to-End Dysarthric Speech Processing Tasks: Speech Recognition, Speaker Identification, and Intelligibility AssessmentCode0
LT-LM: a novel non-autoregressive language model for single-shot lattice rescoringCode0
A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech RecognitionCode0
Generative Adversarial Training Data Adaptation for Very Low-resource Automatic Speech RecognitionCode0
AI-Generated Song Detection via Lyrics TranscriptsCode0
From Gameplay to Symbolic Reasoning: Learning SAT Solver Heuristics in the Style of Alpha(Go) ZeroCode0
A Simplified Fully Quantized Transformer for End-to-end Speech RecognitionCode0
Game of Gradients: Mitigating Irrelevant Clients in Federated LearningCode0
FLEURS: Few-shot Learning Evaluation of Universal Representations of SpeechCode0
Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language UnderstandingCode0
FlowSense: Monitoring Airflow in Building Ventilation Systems Using Audio SensingCode0
First Automatic Fongbe Continuous Speech Recognition System: Development of Acoustic Models and Language ModelsCode0
Assessing the Use of Prosody in Constituency Parsing of Imperfect TranscriptsCode0
AI4D -- African Language ProgramCode0
Finnish Parliament ASR corpus - Analysis, benchmarks and statisticsCode0
First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNsCode0
Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous ClientsCode0
Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2SeqCode0
Automatic Dialect Detection in Arabic Broadcast SpeechCode0
Fine-Grained Grounding for Multimodal Speech RecognitionCode0
Federated Learning in ASR: Not as Easy as You ThinkCode0
Fast-Slow Recurrent Neural NetworksCode0
On the Choice of Modeling Unit for Sequence-to-Sequence Speech RecognitionCode0
FastEmit: Low-latency Streaming ASR with Sequence-level Emission RegularizationCode0
A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality ConversionCode0
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative StudyCode0
Improving Children's Speech Recognition by Fine-tuning Self-supervised Adult Speech RepresentationsCode0
Extended Bit-Plane Compression for Convolutional Neural Network AcceleratorsCode0
Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)Code0
Leveraging Cross-Lingual Transfer Learning in Spoken Named Entity Recognition SystemsCode0
Analysis of French Phonetic Idiosyncrasies for Accent RecognitionCode0
Exploring Generative Error Correction for Dysarthric Speech RecognitionCode0
Exploring neural oscillations during speech perception via surrogate gradient spiking neural networksCode0
Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event LocalizationCode0
Exploiting Adapters for Cross-lingual Low-resource Speech RecognitionCode0
Exploiting Hidden Representations from a DNN-based Speech Recogniser for Speech Intelligibility Prediction in Hearing-impaired ListenersCode0
Exploring spectro-temporal features in end-to-end convolutional neural networksCode0
Show:102550
← PrevPage 18 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