Related papers: Training Keyword Spotters with Limited and Synthes…
Producing a large amount of annotated speech data for training ASR systems remains difficult for more than 95% of languages all over the world which are low-resourced. However, we note human babies start to learn the language by the sounds…
Neural network based approaches to speech enhancement have shown to be particularly powerful, being able to leverage a data-driven approach to result in a significant performance gain versus other approaches. Such approaches are reliant on…
While recent neural text-to-speech (TTS) systems perform remarkably well, they typically require a substantial amount of recordings from the target speaker reading in the desired speaking style. In this work, we present a novel 3-step…
In this study, we present an approach to train a single speech enhancement network that can perform both personalized and non-personalized speech enhancement. This is achieved by incorporating a frame-wise conditioning input that specifies…
Although end-to-end text-to-speech (TTS) models such as Tacotron have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs for training, which are expensive to collect. In this paper, we propose…
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference. Most state-of-the-art neural models for these tasks rely on pretrained word embedding and…
(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…
Large language models (LLMs) have enabled a range of applications in zero-shot and few-shot learning settings, including the generation of synthetic datasets for training and testing. However, to reliably use these synthetic datasets, it is…
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, limiting its scope of application. In this paper, we leverage…
The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…
Discrete speech representation learning has recently attracted increasing interest in both acoustic and semantic modeling. Existing approaches typically encode 16 kHz waveforms into discrete tokens at a rate of 25 or 50 tokens per second.…
The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity. In this paper, we present Personalized…
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding. This study tackles the unsupervised learning of semantic…
Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from…
We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…
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…
The success of AI models relies on the availability of large, diverse, and high-quality datasets, which can be challenging to obtain due to data scarcity, privacy concerns, and high costs. Synthetic data has emerged as a promising solution…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…