Entropy-based Coarse and Compressed Semantic Speech Representation Learning
By: Jialong Zuo , Guangyan Zhang , Minghui Fang and more
Potential Business Impact:
Makes computers understand talking with fewer details.
Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second. However, given that speech generally conveys only 2 to 5 words per second, such fine-grained tokenization introduces redundancy and hinders efficiency in downstream training and inference. Moreover, semantic speech representations at this frequency primarily capture phonetic-level information, while semantic understanding may not require such detailed token-level resolution. To address these limitations, we propose an entropy-based dynamic aggregation framework for learning compressed semantic speech representations. A speech language model is first pre-trained via next-token prediction on large-scale unlabeled data to capture frequent token patterns. Predictive entropy is then used to adaptively determine aggregation boundaries, followed by a cross-attention module that fuses information within each segment. By adjusting the entropy threshold, the granularity and compression ratio of the representations can be flexibly controlled. Experiments on ASR, speech-to-text translation, and voice conversion tasks demonstrate that the compressed representations perform on par with or better than dense token sequences, demonstrating the effectiveness of the proposed approach.
Similar Papers
Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR
Computation and Language
Cleans noisy speech for better understanding.
A Novel Semantic Compression Approach for Ultra-low Bandwidth Voice Communication
Sound
Makes voices sound clear with less data.
Know Your Limits: Entropy Estimation Modeling for Compression and Generalization
Computation and Language
Makes computers understand and write language better.