Related papers: Unsupervised Learning of Semantic Audio Representa…
Annotating time boundaries of sound events is labor-intensive, limiting the scalability of strongly supervised learning in audio detection. To reduce annotation costs, weakly-supervised learning with only clip-level labels has been widely…
Real-world sound scenes consist of time-varying collections of sound sources, each generating characteristic sound events that are mixed together in audio recordings. The association of these constituent sound events with their mixture and…
The lack of labeled data is a common challenge in speech classification tasks, particularly those requiring extensive subjective assessment, such as cognitive state classification. In this work, we propose a Semi-Supervised Learning (SSL)…
This paper proposes a zero-shot learning approach for audio classification based on the textual information about class labels without any audio samples from target classes. We propose an audio classification system built on the bilinear…
Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…
Self-supervised learning (SSL) in audio holds significant potential across various domains, particularly in situations where abundant, unlabeled data is readily available at no cost. This is pertinent in bioacoustics, where biologists…
Although supervised deep learning has revolutionized speech and audio processing, it has necessitated the building of specialist models for individual tasks and application scenarios. It is likewise difficult to apply this to dialects and…
We study the merit of transfer learning for two sound recognition problems, i.e., audio tagging and sound event detection. Employing feature fusion, we adapt a baseline system utilizing only spectral acoustic inputs to also make use of…
We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without transcriptions or…
Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector…
The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks. The visual and language communities have established benchmarks to compare…
There is growing interest in models that can learn from unlabelled speech paired with visual context. This setting is relevant for low-resource speech processing, robotics, and human language acquisition research. Here we study how a…
Audio features have been proven useful for increasing the performance of automated topic segmentation systems. This study explores the novel task of using audio embeddings for automated, topically coherent segmentation of radio shows. We…
Semi-supervised learning deals with the problem of how, if possible, to take advantage of a huge amount of unclassified data, to perform a classification in situations when, typically, there is little labeled data. Even though this is not…
(Part of the abstract) In this thesis, we investigate the use of unsupervised spoken term discovery in tackling this problem. Unsupervised spoken term discovery aims to discover topic-related terminologies in a speech without knowing the…
We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…
Deep learning is very data hungry, and supervised learning especially requires massive labeled data to work well. Machine listening research often suffers from limited labeled data problem, as human annotations are costly to acquire, and…
In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on…
Labeling and maintaining a commercial sound effects library is a time-consuming task exacerbated by databases that continually grow in size and undergo taxonomy updates. Moreover, sound search and taxonomy creation are complicated by…
Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…