相关论文: Parallel WaveNet: Fast High-Fidelity Speech Synthe…

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success…

Binaural rendering aims to synthesize binaural audio that mimics natural hearing based on a mono audio and the locations of the speaker and listener. Although many methods have been proposed to solve this problem, they struggle with…

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…

This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet. Compared to a naive implementation that has complexity O(2^L) (L denotes the number of layers in the network), our proposed approach…

Histopathology can help clinicians make accurate diagnoses, determine disease prognosis, and plan appropriate treatment strategies. As deep learning techniques prove successful in the medical domain, the primary challenges become limited…

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

In recent years, several text-to-speech systems have been proposed to synthesize natural speech in zero-shot, few-shot, and low-resource scenarios. However, these methods typically require training with data from many different speakers.…

Recent advances in artificial speech and audio technologies have improved the abilities of deep-fake operators to falsify media and spread malicious misinformation. Anyone with limited coding skills can use freely available speech synthesis…

Dataset distillation aims to find a synthetic training set such that training on the synthetic data achieves similar performance to training on real data, with orders of magnitude less computational requirements. Existing methods can be…

Speech Enhancement techniques have become core technologies in mobile devices and voice software. Still, modern deep learning solutions often require high amount of computational resources what makes their usage on low-resource devices…

Recent advances in the design of neural network architectures, in particular those specialized in modeling sequences, have provided significant improvements in speech separation performance. In this work, we propose to use a bio-inspired…

The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…

This paper addresses the challenges of high computational cost and slow inference in deploying large language models. It proposes a distillation strategy guided by multiple teacher models. The method constructs several teacher models and…

We propose using self-supervised discrete representations for the task of speech resynthesis. To generate disentangled representation, we separately extract low-bitrate representations for speech content, prosodic information, and speaker…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persistent challenge. In this paper, we propose a novel self-supervised speaker verification approach, Self-Distillation…

Background: Active noise cancellation has been a subject of research for decades. Traditional techniques, like the Fast Fourier Transform, have limitations in certain scenarios. This research explores the use of deep neural networks (DNNs)…

Neural network-based vocoders have recently demonstrated the powerful ability to synthesize high-quality speech. These models usually generate samples by conditioning on spectral features, such as Mel-spectrogram and fundamental frequency,…

Classical parametric speech coding techniques provide a compact representation for speech signals. This affords a very low transmission rate but with a reduced perceptual quality of the reconstructed signals. Recently, autoregressive deep…

Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas,…

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output…