Related papers: Acoustic Neighbor Embeddings
Speaker identification typically involves three stages. First, a front-end speaker embedding model is trained to embed utterance and speaker profiles. Second, a scoring function is applied between a runtime utterance and each speaker…
This article presents a novel approach for learning domain-invariant speaker embeddings using Generative Adversarial Networks. The main idea is to confuse a domain discriminator so that is can't tell if embeddings are from the source or…
We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and…
Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as…
On-device speech recognition requires training models of different sizes for deploying on devices with various computational budgets. When building such different models, we can benefit from training them jointly to take advantage of the…
Dense high dimensional vectors are becoming increasingly vital in fields such as computer vision, machine learning, and large language models (LLMs), serving as standard representations for multimodal data. Now the dimensionality of these…
This paper presents an end-to-end text-independent speaker verification framework by jointly considering the speaker embedding (SE) network and automatic speech recognition (ASR) network. The SE network learns to output an embedding vector…
Recent research has shown that word embedding spaces learned from text corpora of different languages can be aligned without any parallel data supervision. Inspired by the success in unsupervised cross-lingual word embeddings, in this paper…
We extend a well-known dimension reduction method, t-distributed stochastic neighbor embedding (t-SNE), from non-parametric to parametric by training neural networks. The main advantage of a parametric technique is the generalization of…
Self-supervised learning can significantly improve the performance of downstream tasks, however, the dimensions of learned representations normally lack explicit physical meanings. In this work, we propose a novel self-supervised approach…
Dimension reduction, widely used in science, maps high-dimensional data into low-dimensional space. We investigate a basic mathematical model underlying the techniques of stochastic neighborhood embedding (SNE) and its popular variant…
Embedding into hyperbolic space is emerging as an effective representation technique for datasets that exhibit hierarchical structure. This development motivates the need for algorithms that are able to effectively extract knowledge and…
We present a deep learning approach for learning the joint semantic embeddings of images and captions in a Euclidean space, such that the semantic similarity is approximated by the L2 distances in the embedding space. For that, we introduce…
The use of spatial information with multiple microphones can improve far-field automatic speech recognition (ASR) accuracy. However, conventional microphone array techniques degrade speech enhancement performance when there is an array…
Personal Voice Activity Detection (PVAD) is crucial for identifying target speaker segments in the mixture, yet its performance heavily depends on the quality of speaker embeddings. A key practical limitation is the short enrollment…
Recently, hyperspherical embeddings have established themselves as a dominant technique for face and voice recognition. Specifically, Euclidean space vector embeddings are learned to encode person-specific information in their direction…
Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…
Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…
In Magnetic Resonance Fingerprinting (MRF) the quality of the estimated parameter maps depends on the encoding capability of the variable flip angle train. In this work we show how the dimensionality reduction technique Hierarchical…
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…