🏛️ The Audio & Speech Crypt
eess.AS: Where Audio & Speech papers rest without their code.
1388
Total Papers
1179
No Code
18
Twilight
191
Has Code
13.8%
Survival Rate
R.I.P.
👻
Ghosted
R.I.P.
👻
Ghosted
Wake Word Detection with Alignment-Free Lattice-Free MMI
🌅
🌅
Old Age
Multi-task Learning Based Spoofing-Robust Automatic Speaker Verification System
R.I.P.
👻
Ghosted
Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantification
R.I.P.
👻
Ghosted
Hybrid Transformer/CTC Networks for Hardware Efficient Voice Triggering
R.I.P.
👻
Ghosted
EEG based Continuous Speech Recognition using Transformers
R.I.P.
👻
Ghosted
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
R.I.P.
👻
Ghosted
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR
R.I.P.
👻
Ghosted
Self-Adaptive Soft Voice Activity Detection using Deep Neural Networks for Robust Speaker Verification
R.I.P.
👻
Ghosted
Bootstrapping non-parallel voice conversion from speaker-adaptive text-to-speech
R.I.P.
👻
Ghosted
Connecting and Comparing Language Model Interpolation Techniques
R.I.P.
👻
Ghosted
Automatic Spelling Correction with Transformer for CTC-based End-to-End Speech Recognition
R.I.P.
👻
Ghosted
Acoustic Scene Classification: A Competition Review
R.I.P.
👻
Ghosted
Prosodic-Enhanced Siamese Convolutional Neural Networks for Cross-Device Text-Independent Speaker Verification
R.I.P.
👻
Ghosted
Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition
🌅
🌅
Old Age
Pop Music Highlighter: Marking the Emotion Keypoints
R.I.P.
👻
Ghosted
Triplet Network with Attention for Speaker Diarization
R.I.P.
👻
Ghosted
Multilingual Adaptation of RNN Based ASR Systems
R.I.P.
👻
Ghosted
Speak While You Think: Streaming Speech Synthesis During Text Generation
R.I.P.
👻
Ghosted
Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction
R.I.P.
👻
Ghosted
Learning Multiple Sound Source 2D Localization
R.I.P.
👻
Ghosted
Optimizing Short-Time Fourier Transform Parameters via Gradient Descent
R.I.P.
👻
Ghosted
End-to-End Text-to-Speech using Latent Duration based on VQ-VAE
R.I.P.
👻
Ghosted