Related papers: Phase perturbation improves channel robustness for…
Teleconferencing is becoming essential during the COVID-19 pandemic. However, in real-world applications, speech quality can deteriorate due to, for example, background interference, noise, or reverberation. To solve this problem, target…
We investigate multi-stage pretraining for prosody modeling in diffusion-based TTS. A speaker-conditioned dual-stream encoder is trained with masked language modeling followed by SigLIP-style cross-modal contrastive learning using…
Monaural speech enhancement (SE) is an ill-posed problem due to the irreversible degradation process. Recent methods to achieve SE tasks rely solely on positive information, e.g., ground-truth speech and speech-relevant features. Different…
Chaotic synchronization is generally extremely sensitive to the presence of noise and other inference in the channel. Is this sensitivity a fundamental property of chaotic synchronization or is it related to the choice of synchronization…
Deepfakes have become a universal and rapidly intensifying concern of generative AI across various media types such as images, audio, and videos. Among these, audio deepfakes have been of particular concern due to the ease of high-quality…
Typically, unsupervised segmentation of speech into the phone and word-like units are treated as separate tasks and are often done via different methods which do not fully leverage the inter-dependence of the two tasks. Here, we unify them…
In this work, we study the task of encoding logical information via a noisy quantum circuit. It is known that at superlogarithmic depth, the output of any noisy circuit without reset gates or intermediate measurements becomes…
Phonemic segmentation of speech is a critical step of speech recognition systems. We propose a novel unsupervised algorithm based on sequence prediction models such as Markov chains and recurrent neural network. Our approach consists in…
Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modalities of auxiliary information such as prompts and emotion…
Despite rapid advancement in recent years, current speech enhancement models often produce speech that differs in perceptual quality from real clean speech. We propose a learning objective that formalizes differences in perceptual quality,…
For the lack of adequate paired noisy-clean speech corpus in many real scenarios, non-parallel training is a promising task for DNN-based speech enhancement methods. However, because of the severe mismatch between input and target speeches,…
Enhancing speech quality is an indispensable yet difficult task as it is often complicated by a range of degradation factors. In addition to additive noise, reverberation, clipping, and speech attenuation can all adversely affect speech…
Current state-of-the-art (SOTA) codec-based audio synthesis systems can mimic anyone's voice with just a 3-second sample from that specific unseen speaker. Unfortunately, malicious attackers may exploit these technologies, causing misuse…
Language models, characterized by their black-box nature, often hallucinate and display sensitivity to input perturbations, causing concerns about trust. To enhance trust, it is imperative to gain a comprehensive understanding of the…
Advances in neural speech synthesis have brought us technology that is not only close to human naturalness, but is also capable of instant voice cloning with little data, and is highly accessible with pre-trained models available.…
We propose prosody embeddings for emotional and expressive speech synthesis networks. The proposed methods introduce temporal structures in the embedding networks, thus enabling fine-grained control of the speaking style of the synthesized…
Audio spoofing detection has become increasingly important due to the rise in real-world cases. Current spoofing detectors, referred to as spoofing countermeasures (CM), are mainly trained and focused on audio waveforms with a single…
Computational efficiency has remained a critical consideration in scaling high-capacity language models, with inference latency and resource consumption presenting significant constraints on real-time applications. The study has introduced…
Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and…
Cycle-consistent generative adversarial networks (CycleGAN) have shown their promising performance for speech enhancement (SE), while one intractable shortcoming of these CycleGAN-based SE systems is that the noise components propagate…