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 48514900 of 6433 papers

TitleStatusHype
Robust Neural Machine Translation with Joint Textual and Phonetic Embedding0
VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram MaskingCode2
Dense Multimodal Fusion for Hierarchically Joint Representation0
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks0
Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling0
Combining Natural Gradient with Hessian Free Methods for Sequence Training0
Learning Noise-Invariant Representations for Robust Speech Recognition0
Optimal Completion Distillation for Sequence LearningCode0
Neural Speech Translation at AppTek0
The Sogou-TIIC Speech Translation System for IWSLT 20180
The AFRL IWSLT 2018 Systems: What Worked, What Didn’t0
Using Spoken Word Posterior Features in Neural Machine Translation0
Extended Bit-Plane Compression for Convolutional Neural Network AcceleratorsCode0
探討聲學模型的合併技術與半監督鑑別式訓練於會議語音辨識之研究 (Investigating acoustic model combination and semi-supervised discriminative training for meeting speech recognition) [In Chinese]0
使用長短期記憶類神經網路建構中文語音辨識器之研究 (A study on Mandarin speech recognition using Long Short-Term Memory neural network) [In Chinese]0
會議語音辨識使用語者資訊之語言模型調適技術 (On the Use of Speaker-Aware Language Model Adaptation Techniques for Meeting Speech Recognition ) [In Chinese]0
Improving Neural Language Models with Weight Norm Initialization and Regularization0
Automatically Tailoring Unsupervised Morphological Segmentation to the Language0
Self-training improves Recurrent Neural Networks performance for Temporal Relation Extraction0
Words Worth: Verbal Content and Hirability Impressions in YouTube Video Resumes0
A Morphological Analyzer for Shipibo-Konibo0
Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task0
Acoustic Word Disambiguation with Phonogical Features in Danish ASR0
Deep Learning for Social Media Health Text Classification0
Research Challenges in Building a Voice-based Artificial Personal Shopper - Position Paper0
Estimating Marginal Probabilities of n-grams for Recurrent Neural Language Models0
Listening Comprehension over Argumentative Content0
MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling0
Session-level Language Modeling for Conversational Speech0
Dual Fixed-Size Ordinally Forgetting Encoding (FOFE) for Competitive Neural Language Models0
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding0
Joint On-line Learning of a Zero-shot Spoken Semantic Parser and a Reinforcement Learning Dialogue Manager0
NICE: Noise Injection and Clamping Estimation for Neural Network QuantizationCode1
Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture0
Characterizing Audio Adversarial Examples Using Temporal Dependency0
Zero-shot Learning for Speech Recognition with Universal Phonetic Model0
End-to-End Multi-Lingual Multi-Speaker Speech Recognition0
EXPLORATION OF EFFICIENT ON-DEVICE ACOUSTIC MODELING WITH NEURAL NETWORKS0
Non-native children speech recognition through transfer learning0
Hindi-English Code-Switching Speech Corpus0
From Audio to Semantics: Approaches to end-to-end spoken language understanding0
Low Frequency Adversarial PerturbationCode0
Perfect match: Improved cross-modal embeddings for audio-visual synchronisation0
Scene Text Recognition from Two-Dimensional Perspective0
Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Neural Network Algorithm0
Study and Observation of the Variations of Accuracies for Handwritten Digits Recognition with Various Hidden Layers and Epochs using Convolutional Neural Network0
End-to-end Audiovisual Speech Activity Detection with Bimodal Recurrent Neural Models0
Isolated and Ensemble Audio Preprocessing Methods for Detecting Adversarial Examples against Automatic Speech Recognition0
A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations0
End-to-end speech recognition using lattice-free MMI0
Show:102550
← PrevPage 98 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
9Gated ConvNetsWord Error Rate (WER)4.8Unverified
10HMM-TDNN + iVectorsWord 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
7HMM-TDNN + pNorm + speed up/down speechPercentage error12.9Unverified
8DNN MPEPercentage error12.9Unverified
9DNN MMIPercentage error12.9Unverified
10CNN + Bi-RNN + CTC (speech to letters), 25.9% WER if trainedonlyon SWBPercentage 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
6TC-DNN-BLSTM-DNNWord Error Rate (WER)3.5Unverified
7Convolutional Speech RecognitionWord 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