Search Results for author:
Found 5 papers, 1 papers with code
Probing emergent geometry in speech models via replica theory
The success of deep neural networks in visual tasks have motivated recent theoretical and empirical work to understand how these networks operate.
Untangling in Invariant Speech Recognition
Higher level concepts such as parts-of-speech and context dependence also emerge in the later layers of the network.
Scaling Laws for Acoustic Models
We extend previous work to jointly predict loss due to model size, to training set size, and to the inherent "irreducible loss" of the task.
Fusion of Embeddings Networks for Robust Combination of Text Dependent and Independent Speaker Recognition
Based on whether the speech content is constrained or not, both text-dependent (TD) and text-independent (TI) speaker recognition models may be used.
Building Synthetic Speaker Profiles in Text-to-Speech Systems
The diversity of speaker profiles in multi-speaker TTS systems is a crucial aspect of its performance, as it measures how many different speaker profiles TTS systems could possibly synthesize.
