Abstract: A general approach to speaker adaptation in speech recognition is described, in which speaker differences are treated as arising from a ...

We have been experimenting with models for speaker adaptation based on acoustic-phonetic principles following the methods originally described by. Hunt 141. In ...

Oct 22, 2024 · Abstract. A general approach to speaker adaptation in speech recognition is described, in which speaker differences are treated as arising from ...

Spectral mismatch between training and testing utterances can cause significant degradation in the performance of automatic speech recognition (ASR) systems.

Unsupervised Speaker Adaptation by Probabilistic Spectrum Fitting. In Proc. Int. Conf. on. Acoustics, Speech, and Signal Processing, pages 294–297,. Glasgow ...

We describe the use of spectral transformation to perform speaker adaptation for HMM based isolated-word speech recognition.

Jul 23, 2019 · The objective of VTLN is to maximize the “similarity” (in a probabilistic sense) between the acoustic features of two speakers. This is a ...

Alternatively, unsupervised training can be applied to learn embeddings for the different adaptation classes, such as i-vectors [56] or bottleneck features ...

We propose a novel unsupervised speaker adaptation technique for batch normalized acoustic models. The key idea is to adjust the linear transformations ...

Unsupervised speaker adaptation by probabilistic spectrum fitting. SJ Cox, JS Bridle. International Conference on Acoustics, Speech, and Signal Processing ...