Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Probing the Information Encoded in X-vectors (1909.06351v2)

Published 13 Sep 2019 in eess.AS, cs.CL, and cs.SD

Abstract: Deep neural network based speaker embeddings, such as x-vectors, have been shown to perform well in text-independent speaker recognition/verification tasks. In this paper, we use simple classifiers to investigate the contents encoded by x-vector embeddings. We probe these embeddings for information related to the speaker, channel, transcription (sentence, words, phones), and meta information about the utterance (duration and augmentation type), and compare these with the information encoded by i-vectors across a varying number of dimensions. We also study the effect of data augmentation during extractor training on the information captured by x-vectors. Experiments on the RedDots data set show that x-vectors capture spoken content and channel-related information, while performing well on speaker verification tasks.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Desh Raj (32 papers)
  2. David Snyder (17 papers)
  3. Daniel Povey (45 papers)
  4. Sanjeev Khudanpur (74 papers)
Citations (84)

Summary

We haven't generated a summary for this paper yet.