content type videopublished November 6, 2023
research area Health

Apple Workshop on Machine Learning for Health: Pre-trained Model Representations and their Robustness against Noise for Speech Emotion Analysis

AuthorsVikram Mitra (Apple)

Related readings and updates.

Revisiting ASR Error Correction with Specialized Models

July 6, 2026research area Methods and Algorithms, research area Speech and Natural Language Processing

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce latency and hallucination concerns. We revisit ASR error correction with compact seq2seq models, trained on ASR errors from real and synthetic audio. To scale training, we construct synthetic corpora via cascaded…

Read more

Path-Constrained Mixture-of-Experts

July 6, 2026research area Methods and Algorithms, research area Speech and Natural Language Processing

Sparse Mixture-of-Experts (MoE) architectures route each token through a subset of experts at each layer independently. We propose viewing MoE computation through the lens of expert paths—the sequence of expert selections a token makes across all layers. This perspective reveals that, despite N^L possible paths for N experts across L layers, tokens in practice cluster into a small fraction of paths that align with linguistic function, yet the…

Read more