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 50515100 of 6433 papers

TitleStatusHype
ASR-based Features for Emotion Recognition: A Transfer Learning Approach0
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksCode0
Targeted Adversarial Examples for Black Box Audio SystemsCode0
Unsupervised Cross-Modal Alignment of Speech and Text Embedding Spaces0
Composing Finite State Transducers on GPUs0
A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese0
Improved ASR for Under-Resourced Languages Through Multi-Task Learning with Acoustic Landmarks0
A Purely End-to-end System for Multi-speaker Speech Recognition0
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning0
RETURNN as a Generic Flexible Neural Toolkit with Application to Translation and Speech RecognitionCode1
TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptationCode3
A comparable study of modeling units for end-to-end Mandarin speech recognition0
Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations0
Improved training of end-to-end attention models for speech recognitionCode1
Boosting Noise Robustness of Acoustic Model via Deep Adversarial Training0
Open ASR for Icelandic: Resources and a Baseline System0
Unified Guidelines and Resources for Arabic Dialect Orthography0
A Web Service for Pre-segmenting Very Long Transcribed Speech Recordings0
Parallel Corpora in Mboshi (Bantu C25, Congo-Brazzaville)0
Pronunciation Variants and ASR of Colloquial Speech: A Case Study on Czech0
A Vietnamese Dialog Act Corpus Based on ISO 24617-2 standard0
Using Discourse Information for Education with a Spanish-Chinese Parallel Corpus0
TF-LM: TensorFlow-based Language Modeling ToolkitCode0
A Real-life, French-accented Corpus of Air Traffic Control Communications0
Design and Development of Speech Corpora for Air Traffic Control Training0
Simulating ASR errors for training SLU systems0
Construction of English-French Multimodal Affective Conversational Corpus from TV Dramas0
MirasVoice: A bilingual (English-Persian) speech corpus0
A Semi-autonomous System for Creating a Human-Machine Interaction Corpus in Virtual Reality: Application to the ACORFORMed System for Training Doctors to Break Bad News0
Speech Rate Calculations with Short Utterances: A Study from a Speech-to-Speech, Machine Translation Mediated Map Task0
Classification of Closely Related Sub-dialects of Arabic Using Support-Vector Machines0
From `Solved Problems' to New Challenges: A Report on LDC Activities0
Discovering Canonical Indian English Accents: A Crowdsourcing-based Approach0
Creating Lithuanian and Latvian Speech Corpora from Inaccurately Annotated Web Data0
DART: A Large Dataset of Dialectal Arabic Tweets0
Evaluation of Feature-Space Speaker Adaptation for End-to-End Acoustic Models0
Evaluation Phonemic Transcription of Low-Resource Tonal Languages for Language DocumentationCode0
ASR for Documenting Acutely Under-Resourced Indigenous Languages0
Improved Transcription and Indexing of Oral History Interviews for Digital Humanities Research0
Preparing Data from Psychotherapy for Natural Language ProcessingCode0
Interpersonal Relationship Labels for the CALLHOME CorpusCode0
Multilingual Parallel Corpus for Global Communication Plan0
A Leveled Reading Corpus of Modern Standard Arabic0
FARMI: A FrAmework for Recording Multi-Modal Interactions0
Data-Driven Pronunciation Modeling of Swiss German Dialectal Speech for Automatic Speech Recognition0
Increasing the Accessibility of Time-Aligned Speech Corpora with Spokes Mix0
VAST: A Corpus of Video Annotation for Speech Technologies0
Collection and Analysis of Code-switch Egyptian Arabic-English Speech Corpus0
Phonetically Balanced Code-Mixed Speech Corpus for Hindi-English Automatic Speech Recognition0
Text Normalization Infrastructure that Scales to Hundreds of Language Varieties0
Show:102550
← PrevPage 102 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