Related papers: MF-Speech: Achieving Fine-Grained and Compositiona…
This article introduces AnCoGen, a novel method that leverages a masked autoencoder to unify the analysis, control, and generation of speech signals within a single model. AnCoGen can analyze speech by estimating key attributes, such as…
Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority…
Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…
Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio. To enhance speech beyond…
Conventional spoken language understanding systems consist of two main components: an automatic speech recognition module that converts audio to a transcript, and a natural language understanding module that transforms the resulting text…
In this paper, we present Multi-scale Feature Aggregation Conformer (MFA-Conformer), an easy-to-implement, simple but effective backbone for automatic speaker verification based on the Convolution-augmented Transformer (Conformer). The…
Articulatory trajectories like electromagnetic articulography (EMA) provide a low-dimensional representation of the vocal tract filter and have been used as natural, grounded features for speech synthesis. Differentiable digital signal…
Text-to-speech systems recently achieved almost indistinguishable quality from human speech. However, the prosody of those systems is generally flatter than natural speech, producing samples with low expressiveness. Disentanglement of…
A method for statistical parametric speech synthesis incorporating generative adversarial networks (GANs) is proposed. Although powerful deep neural networks (DNNs) techniques can be applied to artificially synthesize speech waveform, the…
This paper presents a novel speaking-style captioning method that generates diverse descriptions while accurately predicting speaking-style information. Conventional learning criteria directly use original captions that contain not only…
In this work, we introduce Speech-Copilot, a modular framework for instruction-oriented speech-processing tasks that minimizes human effort in toolset construction. Unlike end-to-end methods using large audio-language models, Speech-Copilot…
Diffusion-based generative speech enhancement (SE) has recently received attention, but reverse diffusion remains time-consuming. One solution is to initialize the reverse diffusion process with enhanced features estimated by a predictive…
Deep learning-based models have greatly advanced the performance of speech enhancement (SE) systems. However, two problems remain unsolved, which are closely related to model generalizability to noisy conditions: (1) mismatched noisy…
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce \textbf{G}enerative…
A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain…
In this work, we introduce a new approach for face stylization. Despite existing methods achieving impressive results in this task, there is still room for improvement in generating high-quality artistic faces with diverse styles and…
In this paper, we propose multi-band MelGAN, a much faster waveform generation model targeting to high-quality text-to-speech. Specifically, we improve the original MelGAN by the following aspects. First, we increase the receptive field of…
The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused…
Expectations aid and bias our perception. In speech, expected words are easier to recognise than unexpected words, particularly in noisy environments, and incorrect expectations can make us misunderstand our conversational partner.…
Obtaining multiple meaningfully diverse, high quality samples from Large Language Models for a fixed prompt remains an open challenge. Current methods for increasing diversity often only operate at the token-level, paraphrasing the same…