Regularizing Contrastive Predictive Coding for Speech Applications
원문 초록
Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task performance, such as automatic speech recognition. CPC learns representations by learning to predict future frames given current frames. Based on the observation that the acoustic information, e.g., phones, changes slower than the feature extraction rate in CPC, we propose regularization techniques that impose slowness constraints on the features. Here we propose two regularization techniques: Self-expressing constraint and Left-or-Right regularization. We evaluate the proposed model on ABX and linear phone classification tasks, acoustic unit discovery, and automatic speech recognition. The regularized CPC trained on 100 hours of unlabeled data matches the performance of the baseline CPC trained on 360 hours of unlabeled data. We also show that our regularization techniques are complementary to data augmentation and can further boost the system's performance. In monolingual, cross-lingual, or multilingual settings, with/without data augmentation, regardless of the amount of data used for training, our regularized models outperformed the baseline CPC models on the ABX task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Seewo's Submission to MLC-SLM: Lessons learned from Speech Reasoning Language Models
SimClass: A Classroom Speech Dataset Generated via Game Engine Simulation For Automatic Speech Recognition Research
LLM-based phoneme-to-grapheme for phoneme-based speech recognition
Improving Multilingual Speech Models on ML-SUPERB 2.0: Fine-tuning with Data Augmentation and LID-Aware CTC
Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
토론
이 논문과 연결된 포럼 글이 아직 없습니다.