Related papers: Learning Multiscale Features Directly From Wavefor…

Recently end-to-end neural audio/speech coding has shown its great potential to outperform traditional signal analysis based audio codecs. This is mostly achieved by following the VQ-VAE paradigm where blind features are learned,…

The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…

One key step in audio signal processing is to transform the raw signal into representations that are efficient for encoding the original information. Traditionally, people transform the audio into spectral representations, as a function of…

We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. F0 estimation is important in various speech processing and music…

Capturing high-frequency data concerning the condition of complex systems, e.g. by acoustic monitoring, has become increasingly prevalent. Such high-frequency signals typically contain time dependencies ranging over different time scales…

The goal of this paper is to develop state-of-the-art models for lip reading -- visual speech recognition. We develop three architectures and compare their accuracy and training times: (i) a recurrent model using LSTMs; (ii) a fully…

This thesis focuses on representation learning for sequence data over time or space, aiming to improve downstream sequence prediction tasks by using the learned representations. Supervised learning has been the most dominant approach for…

Deep Reinforcement Learning has shown significant progress in extracting useful representations from high-dimensional inputs albeit using hand-crafted auxiliary tasks and pseudo rewards. Automatically learning such representations in an…

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…

Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivator for spectrogram-based representations was…

Automatically assessing emotional valence in human speech has historically been a difficult task for machine learning algorithms. The subtle changes in the voice of the speaker that are indicative of positive or negative emotional states…

Self-supervised pre-training of a speech foundation model, followed by supervised fine-tuning, has shown impressive quality improvements on automatic speech recognition (ASR) tasks. Fine-tuning separate foundation models for many downstream…

Recent work in neural networks for image classification has seen a strong tendency towards increasing the spatial context. Whether achieved through large convolution kernels or self-attention, models scale poorly with the increased spatial…

Functional magnetic resonance imaging produces high dimensional data, with a less then ideal number of labelled samples for brain decoding tasks (predicting brain states). In this study, we propose a new deep temporal convolutional neural…

Recently, direct modeling of raw waveforms using deep neural networks has been widely studied for a number of tasks in audio domains. In speaker verification, however, utilization of raw waveforms is in its preliminary phase, requiring…

Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can…

Accent recognition with deep learning framework is a similar work to deep speaker identification, they're both expected to give the input speech an identifiable representation. Compared with the individual-level features learned by speaker…

Multi-channel speech enhancement extracts speech using multiple microphones that capture spatial cues. Effectively utilizing directional information is key for multi-channel enhancement. Deep learning shows great potential on multi-channel…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Speaker recognition using i-vector has been replaced by speaker recognition using deep learning. Speaker recognition based on Convolutional Neural Networks (CNNs) has been widely used in recent years, which learn low-level speech…