Related papers: Combining Adversarial Training and Disentangled Sp…
(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…
Disentangled and invariant representations are two critical goals of representation learning and many approaches have been proposed to achieve either one of them. However, those two goals are actually complementary to each other so that we…
Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization. The embeddings learned by softmax are not discriminative enough for open-set verification…
This paper summarizes the work done by the authors for the Zero Resource Speech Challenge organized in the technical program of Interspeech 2015. The goal of the challenge is to discover linguistic units directly from unlabeled speech data.…
Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…
Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…
Recent advances in neural network based acoustic modelling have shown significant improvements in automatic speech recognition (ASR) performance. In order for acoustic models to be able to handle large acoustic variability, large amounts of…
The present study tackles the problem of automatically discovering spoken keywords from untranscribed audio archives without requiring word-by-word speech transcription by automatic speech recognition (ASR) technology. The problem is of…
Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal…
In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…
In this work, we propose a zero-shot voice conversion method using speech representations trained with self-supervised learning. First, we develop a multi-task model to decompose a speech utterance into features such as linguistic content,…
The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, speaker diarisation, audio surveillance or auditory scene…
Recently, the standard variational autoencoder has been successfully used to learn a probabilistic prior over speech signals, which is then used to perform speech enhancement. Variational autoencoders have then been conditioned on a label…
This work presents a broad study on the adaptation of neural network acoustic models by means of learning hidden unit contributions (LHUC) -- a method that linearly re-combines hidden units in a speaker- or environment-dependent manner…
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…
In zero-resource settings where transcribed speech audio is unavailable, unsupervised feature learning is essential for downstream speech processing tasks. Here we compare two recent methods for frame-level acoustic feature learning. For…
In recent studies, self-supervised pre-trained models tend to outperform supervised pre-trained models in transfer learning. In particular, self-supervised learning (SSL) of utterance-level speech representation can be used in speech…
Zero-resource speech technology is a growing research area that aims to develop methods for speech processing in the absence of transcriptions, lexicons, or language modelling text. Early term discovery systems focused on identifying…
We propose a novel adversarial multi-task learning scheme, aiming at actively curtailing the inter-talker feature variability while maximizing its senone discriminability so as to enhance the performance of a deep neural network (DNN) based…
Previous works have shown that automatic speaker verification (ASV) is seriously vulnerable to malicious spoofing attacks, such as replay, synthetic speech, and recently emerged adversarial attacks. Great efforts have been dedicated to…