English
Related papers

Related papers: Probing the Information Encoded in X-vectors

200 papers

We first observe a potential weakness of continuous vector representations of symbols in neural machine translation. That is, the continuous vector representation, or a word embedding vector, of a symbol encodes multiple dimensions of…

Computation and Language · Computer Science 2016-07-05 Heeyoul Choi , Kyunghyun Cho , Yoshua Bengio

In this paper, we apply the variational information bottleneck approach to end-to-end neural diarization with encoder-decoder attractors (EEND-EDA). This allows us to investigate what information is essential for the model. EEND-EDA…

Sound · Computer Science 2024-06-21 Lin Zhang , Themos Stafylakis , Federico Landini , Mireia Diez , Anna Silnova , Lukáš Burget

We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…

Sound · Computer Science 2018-04-27 Sergey Novoselov , Andrey Shulipa , Ivan Kremnev , Alexandr Kozlov , Vadim Shchemelinin

In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…

Computation and Language · Computer Science 2017-11-07 Yu-An Chung , James Glass

A deep learning approach has been proposed recently to derive speaker identifies (d-vector) by a deep neural network (DNN). This approach has been applied to text-dependent speaker recognition tasks and shows reasonable performance gains…

Computation and Language · Computer Science 2015-06-30 Lantian Li , Yiye Lin , Zhiyong Zhang , Dong Wang

There are various factors that can influence the performance of speaker recognition systems, such as emotion, language and other speaker-related or context-related variations. Since individual speech frames do not contribute equally to the…

Sound · Computer Science 2026-01-23 Junjie Li , Kong Aik Lee , Duc-Tuan Truong , Tianchi Liu , Man-Wai Mak

Semantic sentence embedding models encode natural language sentences into vectors, such that closeness in embedding space indicates closeness in the semantics between the sentences. Bilingual data offers a useful signal for learning such…

Computation and Language · Computer Science 2020-11-20 John Wieting , Graham Neubig , Taylor Berg-Kirkpatrick

Animal vocalizations contain sequential structures that carry important communicative information, yet most computational bioacoustics studies average the extracted frame-level features across the temporal axis, discarding the order of the…

Machine Learning · Computer Science 2025-11-14 Eklavya Sarkar , Mathew Magimai. -Doss

Deep learning is still not a very common tool in speaker verification field. We study deep convolutional neural network performance in the text-prompted speaker verification task. The prompted passphrase is segmented into word states - i.e.…

Audio and Speech Processing · Electrical Eng. & Systems 2018-03-15 Sergey Novoselov , Oleg Kudashev , Vadim Schemelinin , Ivan Kremnev , Galina Lavrentyeva

Speech production involves the movement of various articulators, including tongue, jaw, and lips. Estimating the movement of the articulators from the acoustics of speech is known as acoustic-to-articulatory inversion (AAI). Recently, it…

Audio and Speech Processing · Electrical Eng. & Systems 2020-06-23 Aravind Illa , Prasanta Kumar Ghosh

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited labeled data. Traditionally, it has been assumed that emotion…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-03 Ismail Rasim Ulgen , Zongyang Du , Carlos Busso , Berrak Sisman

The vast majority of approaches to speaker anonymization involve the extraction of fundamental frequency estimates, linguistic features and a speaker embedding which is perturbed to obfuscate the speaker identity before an anonymized speech…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-15 Michele Panariello , Francesco Nespoli , Massimiliano Todisco , Nicholas Evans

Text embedding representing natural language documents in a semantic vector space can be used for document retrieval using nearest neighbor lookup. In order to study the feasibility of neural models specialized for retrieval in a…

Information Retrieval · Computer Science 2019-05-03 Tolgahan Cakaloglu , Christian Szegedy , Xiaowei Xu

Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as fixed vectors in high-dimensional space. This could lead to…

Sound · Computer Science 2022-06-28 Siqi Zheng , Hongbin Suo , Qian Chen

Sentence embeddings from transformer models encode in a fixed length vector much linguistic information. We explore the hypothesis that these embeddings consist of overlapping layers of information that can be separated, and on which…

Computation and Language · Computer Science 2024-07-03 Vivi Nastase , Paola Merlo

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

Sound · Computer Science 2024-06-21 KiHyun Nam , Hee-Soo Heo , Jee-weon Jung , Joon Son Chung

The pervasive use of distributional semantic models or word embeddings in a variety of research fields is due to their remarkable ability to represent the meanings of words for both practical application and cognitive modeling. However,…

Computation and Language · Computer Science 2018-02-07 Akira Utsumi

In this paper, we demonstrate a method for training speaker embedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-10 Themos Stafylakis , Ladislav Mošner , Oldřich Plchot , Johan Rohdin , Anna Silnova , Lukáš Burget , Jan "Honza'' Černocký

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…

Audio and Speech Processing · Electrical Eng. & Systems 2019-04-09 Mirco Ravanelli , Yoshua Bengio

This paper introduces a sentence to vector encoding framework suitable for advanced natural language processing. Our latent representation is shown to encode sentences with common semantic information with similar vector representations.…

Computation and Language · Computer Science 2018-09-30 Chi Zhang , Shagan Sah , Thang Nguyen , Dheeraj Peri , Alexander Loui , Carl Salvaggio , Raymond Ptucha