相关论文: Unsupervised Style and Content Separation by Minim…

Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models…

Deep learning based models have significantly improved the performance of speech separation with input mixtures like the cocktail party. Prominent methods (e.g., frequency-domain and time-domain speech separation) usually build regression…

Large-scale noisy web image-text datasets have been proven to be efficient for learning robust vision-language models. However, when transferring them to the task of video retrieval, models still need to be fine-tuned on hand-curated paired…

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Existing text style transfer (TST) methods rely on style classifiers to disentangle the text's content and style attributes for text style transfer. While the style classifier plays a critical role in existing TST methods, there is no known…

The goal of speech separation is to extract multiple speech sources from a single microphone recording. Recently, with the advancement of deep learning and availability of large datasets, speech separation has been formulated as a…

Video-to-speech synthesis involves reconstructing the speech signal of a speaker from a silent video. The implicit assumption of this task is that the sound signal is either missing or contains a high amount of noise/corruption such that it…

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data. This makes creating models for multiple styles expensive and…

We introduce a new method for generating text, and in particular song lyrics, based on the speech-like acoustic qualities of a given audio file. We repurpose a vocal source separation algorithm and an acoustic model trained to recognize…

In this work, we propose a novel method for modeling numerous speakers, which enables expressing the overall characteristics of speakers in detail like a trained multi-speaker model without additional training on the target speaker's…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal…

In settings where only unlabelled speech data is available, speech technology needs to be developed without transcriptions, pronunciation dictionaries, or language modelling text. A similar problem is faced when modelling infant language…

By representing speaker characteristic as a single fixed-length vector extracted solely from speech, we can train a neural multi-speaker speech synthesis model by conditioning the model on those vectors. This model can also be adapted to…

To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

Denoising Diffusion Probabilistic Models have shown extraordinary ability on various generative tasks. However, their slow inference speed renders them impractical in speech synthesis. This paper proposes a linear diffusion model (LinDiff)…

We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference. UniTTS represents multiple style attributes in a single unified embedding space by the…