Year: 2023
Type: preprint
Abstract: We investigate recent transformer networks pre-trained for automatic speech recognition for their ability to detect speaker and language changes in speech. We do this by simply adding speaker (change) or language targets to the labels. For Wav2vec2 pre-trained networks, we also investigate if the representation for the speaker change symbol can be conditioned to capture speaker identity characteristics. Using a number of constructed data sets we show that these capabilities are definitely there, with speaker recognition equal error rates of the order of 10% and language detection error rates of a few percent. We will publish the code for reproducibility.
Source: arXiv (Cornell University)
Institution: Radboud University Nijmegen
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4321472280