相关论文: Characterisation of speech diversity using self-or…

In recent years, there has been growing interest in representing speech with discrete tokens, which serve as pseudo-text for speech language models (speechLMs) and as efficient intermediate representations for downstream tasks. These tokens…

Controlling the internal representation space of a neural network is a desirable feature because it allows to generate new data in a supervised manner. In this paper we will show how this can be achieved while building a low-dimensional…

Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Next generations of radio surveys are expected to identify tens of millions of new sources, and identifying and classifying their morphologies will require novel and more efficient methods. Self-Organising Maps (SOMs), a type of…

This work introduces a novel generative continual learning framework based on self-organizing maps (SOMs) and variational autoencoders (VAEs) to enable memory-efficient replay, eliminating the need to store raw data samples or task labels.…

Self-Organizing Map (SOM) is a promising tool for exploring large multi-dimensional data sets. It is quick and convenient to train in an unsupervised fashion and, as an outcome, it produces natural clusters of data patterns. An example of…

This paper presents methods for building speech recognizers tailored for Japanese speaking assessment tasks. Specifically, we build a speech recognizer that outputs phonemic labels with accent markers. Although Japanese is resource-rich,…

This paper introduces an incremental semantic mapping approach, with on-line unsupervised learning, based on Self-Organizing Maps (SOM) for robotic agents. The method includes a mapping module, which incrementally creates a topological map…

Recent advances in deep learning have facilitated the design of speaker verification systems that directly input raw waveforms. For example, RawNet extracts speaker embeddings from raw waveforms, which simplifies the process pipeline and…

In this paper we address an important economic question. Is there, as mainstream economic theory asserts it, an homogeneous labor market with mechanisms which govern supply and demand for work, producing an equilibrium with its remarkable…

Web 2.0 services have enabled people to express their opinions, experience and feelings in the form of user-generated content. Sentiment analysis or opinion mining involves identifying, classifying and aggregating opinions as per their…

Neural network algorithms have been recently applied to construct Parton Distribution Function (PDF) parametrizations which provide an alternative to standard global fitting procedures. We propose a technique based on an interactive neural…

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…

This paper defines a new learning architecture, Layered Self-Organizing Maps (LSOMs), that uses the SOM and supervised-SOM learning algorithms. The architecture is validated with the MNIST database of hand-written digit images. LSOMs are…

Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…

Self-supervised speech models (S3Ms) are known to encode rich phonetic information, yet how this information is structured remains underexplored. We conduct a comprehensive study across 96 languages to analyze the underlying structure of…

In this paper we propose a Sequential Representation Quantization AutoEncoder (SeqRQ-AE) to learn from primarily unpaired audio data and produce sequences of representations very close to phoneme sequences of speech utterances. This is…

Sign language datasets are often not representative in terms of vocabulary, underscoring the need for models that generalize to unseen signs. Vector quantization is a promising approach for learning discrete, token-like representations, but…

Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \etc., which can be challenging to cover using one small model designed for a single task. In…