Related papers: A Neural Vocoder Based Packet Loss Concealment Alg…

A large number of streaming applications use reliable transport protocols such as TCP to deliver content over the Internet. However, head-of-line blocking due to packet loss recovery can often result in unwanted behavior and poor…

Singing voice separation (SVS) is a task that separates singing voice audio from its mixture with instrumental audio. Previous SVS studies have mainly employed the spectrogram masking method which requires a large dimensionality in…

We present a universal neural vocoder based on Parallel WaveNet, with an additional conditioning network called Audio Encoder. Our universal vocoder offers real-time high-quality speech synthesis on a wide range of use cases. We tested it…

We propose an end-to-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message…

This paper proposes a spectral-domain perceptual weighting technique for Parallel WaveGAN-based text-to-speech (TTS) systems. The recently proposed Parallel WaveGAN vocoder successfully generates waveform sequences using a fast…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

Semantic communication has emerged as a promising paradigm for next-generation wireless systems, improving the communication efficiency by transmitting high-level semantic features. However, reliance on unimodal representations can degrade…

Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal. Language is a particularly pragmatic cover…

The increasing use of cloud-based speech assistants has heightened the need for effective speech anonymization, which aims to obscure a speaker's identity while retaining critical information for subsequent tasks. One approach to achieving…

Speaker anonymization aims to conceal a speaker's identity while preserving content information in speech. Current mainstream neural-network speaker anonymization systems disentangle speech into prosody-related, content, and speaker…

This Ph.D. thesis focuses on developing a system for high-quality speech synthesis and voice conversion. Vocoder-based speech analysis, manipulation, and synthesis plays a crucial role in various kinds of statistical parametric speech…

We propose a protocol for conditional suppression of losses in direct quantum state transmission over a lossy quantum channel. The method works by noiselessly attenuating the input state prior to transmission through a lossy channel…

The task of Mel vocoding, i.e., the inversion of a Mel magnitude spectrogram to an audio waveform, is still a key component in many text-to-speech (TTS) systems today. Based on generative flow matching, our prior work on generative STFT…

Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that…

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…

We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to…

Speaker verification is a task of confirming an individual's identity through the analysis of their voice. Whispered speech differs from phonated speech in acoustic characteristics, which degrades the performance of speaker verification…

This paper proposes a generative pretraining foundation model for high-quality speech restoration tasks. By directly operating on complex-valued short-time Fourier transform coefficients, our model does not rely on any vocoders for…

We present a concept to achieve non-repudiation for natural language conversations by electronically signing packet-based, digital, voice communication. Signing a VoIP-based conversation means to protect the integrity and authenticity of…

We present a transformer-based architecture for voice separation of a target speaker from multiple other speakers and ambient noise. We achieve this by using two separate neural networks: (A) An enrolment network designed to craft…