Probing the Information Encoded in X-vectors
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationSentenceSpeaker RecognitionSpeaker VerificationText-Independent Speaker RecognitionSimilar Papers 제목 키워드 기반
Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space
The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) datase…
Open-Ended Question AnsweringBeyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
Probing learned concepts in large language models (LLMs) is crucial for understanding how semantic knowledge is encoded internally. Training linear classifiers on probing tasks is a principle approach to denote the vecto…
Text GenerationProbing with Noise: Unpicking the Warp and Weft of Embeddings
Improving our understanding of how information is encoded in vector space can yield valuable interpretability insights. Alongside vector dimensions, we argue that it is possible for the vector norm to also carry linguist…
SentenceDecoding Word Embeddings with Brain-Based Semantic Features
Word embeddings are vectorial semantic representations built with either counting or predicting techniques aimed at capturing shades of meaning from word co-occurrences. Since their introduction, these representations ha…
RetrievalWord EmbeddingsWave to Syntax: Probing spoken language models for syntax
Understanding which information is encoded in deep models of spoken and written language has been the focus of much research in recent years, as it is crucial for debugging and improving these architectures. Most previou…