Related papers: Multi-Axis Speech Similarity via Factor-Partitione…

Embeddings in AI convert symbolic structures into fixed-dimensional vectors, effectively fusing multiple signals. However, the nature of this fusion in real-world data is often unclear. To address this, we introduce two methods: (1)…

There is a lot of research interest in encoding variable length sentences into fixed length vectors, in a way that preserves the sentence meanings. Two common methods include representations based on averaging word vectors, and…

Given the speech generation framework that represents the speaker attribute with an embedding vector, asynchronous voice anonymization can be achieved by modifying the speaker embedding derived from the original speech. However, the…

Embodied cognition states that semantics is encoded in the brain as firing patterns of neural circuits, which are learned according to the statistical structure of human multimodal experience. However, each human brain is idiosyncratically…

Embedding audio signal segments into vectors with fixed dimensionality is attractive because all following processing will be easier and more efficient, for example modeling, classifying or indexing. Audio Word2Vec previously proposed was…

In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…

Modeling the rich prosodic variations inherent in human speech is essential for generating natural-sounding speech. While speaker embeddings are commonly used as conditioning inputs in personalized speech generation, they are typically…

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised…

Distributed word embeddings have yielded state-of-the-art performance in many NLP tasks, mainly due to their success in capturing useful semantic information. These representations assign only a single vector to each word whereas a large…

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…

In the field of speaker verification, session or channel variability poses a significant challenge. While many contemporary methods aim to disentangle session information from speaker embeddings, we introduce a novel approach using an…

Acoustic word embeddings (AWEs) are vector representations of spoken word segments. AWEs can be learned jointly with embeddings of character sequences, to generate phonetically meaningful embeddings of written words, or acoustically…

Most existing word embedding methods can be categorized into Neural Embedding Models and Matrix Factorization (MF)-based methods. However some models are opaque to probabilistic interpretation, and MF-based methods, typically solved using…

Speech signal is constituted and contributed by various informative factors, such as linguistic content and speaker characteristic. There have been notable recent studies attempting to factorize speech signal into these individual factors…

Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a…

As a fundamental task in natural language processing, word embedding converts each word into a representation in a vector space. A challenge with word embedding is that as the vocabulary grows, the vector space's dimension increases, which…

While Transformer has become the de-facto standard for speech, modeling upon the fine-grained frame-level features remains an open challenge of capturing long-distance dependencies and distributing the attention weights. We propose…

In retrieval applications, binary hashes are known to offer significant improvements in terms of both memory and speed. We investigate the compression of sentence embeddings using a neural encoder-decoder architecture, which is trained by…

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.…

We investigate a novel cross-lingual multi-speaker text-to-speech synthesis approach for generating high-quality native or accented speech for native/foreign seen/unseen speakers in English and Mandarin. The system consists of three…