Research
A Theoretical Framework for Acoustic Neighbor Embeddings
This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embe
This paper provides a theoretical framework for interpreting acoustic neighbor embeddings, which are representations of the phonetic content of variable-width audio or text in a fixed-dimensional embedding space. A probabilistic interpretation of the distances between embeddings is proposed, based on a general quantitative definition of phonetic similarity between words. This provides us a framework for understanding and applying the embeddings in a principled manner. Theoretical and empirical evidence to support an approximation of uniform cluster-wise isotropy are shown, which allows us to…
Related
- Do We Need Distinct Representations for Every Speech Token? Unveiling and Exploiting Redundancy in Large Speech Language Models
- In-Context Learning in Speech Language Models: Analyzing the Role of Acoustic Features, Linguistic Structure, and Induction Heads
- Nearest Neighbor Projection Removal Adversarial Training
- What if your HNSW index stored 3-bit embeddings instead of float32? [R]
Source: Apple ML Research | 2026-04-09