R.I.P.
👻
Ghosted
🏛️ 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
Detecting Audio Attacks on ASR Systems with Dropout Uncertainty
R.I.P.
👻
Ghosted
Singing Synthesis: with a little help from my attention
R.I.P.
👻
Ghosted
Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events
R.I.P.
👻
Ghosted
Additive Margin SincNet for Speaker Recognition
R.I.P.
👻
Ghosted
Scaling Speech Enhancement in Unseen Environments with Noise Embeddings
R.I.P.
👻
Ghosted
Investigating accuracy of pitch-accent annotations in neural network-based speech synthesis and denoising effects
R.I.P.
👻
Ghosted
Learning Spontaneity to Improve Emotion Recognition In Speech
R.I.P.
👻
Ghosted
One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection
R.I.P.
👻
Ghosted
Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer
R.I.P.
👻
Ghosted
Automatic Disfluency Detection from Untranscribed Speech
🌅
💤
Eternal Rest
Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction
R.I.P.
👻
Ghosted
Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data
R.I.P.
👻
Ghosted
Simulating realistic speech overlaps improves multi-talker ASR
R.I.P.
👻
Ghosted
Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in Automatic Speech Recognition
R.I.P.
👻
Ghosted
Assessing ASR Model Quality on Disordered Speech using BERTScore
R.I.P.
👻
Ghosted
UserLibri: A Dataset for ASR Personalization Using Only Text
R.I.P.
👻
Ghosted
Efficient Neural Architecture Search for End-to-end Speech Recognition via Straight-Through Gradients
R.I.P.
👻
Ghosted
Data augmentation using prosody and false starts to recognize non-native children's speech
R.I.P.
👻
Ghosted
SNR-Based Teachers-Student Technique for Speech Enhancement
R.I.P.
👻
Ghosted
MP3 Compression To Diminish Adversarial Noise in End-to-End Speech Recognition
R.I.P.
👻
Ghosted
Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition
R.I.P.
👻
Ghosted
Leveraging End-to-End Speech Recognition with Neural Architecture Search
R.I.P.
⏳
Coming Soon™