2021 Reading Group
2021.09.07 Interspeech 2021 Paper list
- Speech SimCLR: Combining Contrastive and Reconstruction Objective for Self-Supervised Speech Representation Learning
- Stochastic Attention Head Removal: A Simple and Effective Method for Improving Transformer Based ASR Models
- Graph-PIT: Generalized Permutation Invariant Training for Continuous Separation of Arbitrary Numbers of Speakers
2021.10.12 Interspeech 2021 Paper list
- LT-LM: A Novel Non-Autoregressive Language Model for Single-Shot Lattice Rescoring
- Variable Frame Rate Acoustic Models Using Minimum Error Reinforcement Learning
- Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement
- Speech Denoising Without Clean Training Data: A Noise2Noise Approach
- Efficient and Stable Adversarial Learning Using Unpaired Data for Unsupervised Multichannel Speech Separation
- Sparse Mixture of Local Experts for Efficient Speech Enhancement
- Manifold-Aware Deep Clustering: Maximizing Angles Between Embedding Vectors Based on Regular Simplex
2021.10.19 Multimodal Speech Summarization (Speaker: Shruti)
2021.10.26 Code Switching introduction (Speaker: Dan)
Papers:
- TOWARDS END-TO-END CODE-SWITCHING SPEECH RECOGNITION
- Towards Context-Aware End-to-End Code-Switching Speech Recognition
- Detection of language boundary in code-switching utterances by bi-phone probabilities
- Bilingual Language Mixing: Why Do Bilinguals Code-Switch?
- An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech
- Data Augmentation for end-to-end Code-Switching Speech Recognition
- Constrained Output Embeddings for End-to-End Code-Switching Speech Recognition with Only Monolingual Data
Slides:
2021.11.09 Waspaa 2021 Paper list (Selector: Zhong-Qiu)
- DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement
- Self-Supervised Learning from Automatically Separated Sound Scenes
- HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding