Related papers: Unsupervised Style and Content Separation by Minim…

Weakly supervised video anomaly detection (WS-VAD) is to distinguish anomalies from normal events based on discriminative representations. Most existing works are limited in insufficient video representations. In this work, we develop a…

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language…

Linguistic style is an essential part of written communication, with the power to affect both clarity and attractiveness. With recent advances in vision and language, we can start to tackle the problem of generating image captions that are…

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target), where source…

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Incremental text-to-speech (TTS) synthesis generates utterances in small linguistic units for the sake of real-time and low-latency applications. We previously proposed an incremental TTS method that leverages a large pre-trained language…

We introduce VoiceFilter-Lite, a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. Delivering such a model presents…

Semi-supervised learning that leverages synthetic data for training has been widely adopted for developing automatic post-editing (APE) models due to the lack of training data. With this aim, we focus on data-synthesis methods to create…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

Human language can be expressed in either written or spoken form, i.e. text or speech. Humans can acquire knowledge from text to improve speaking and listening. However, the quest for speech pre-trained models to leverage unpaired text has…

In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a…

Modern text-to-speech systems are able to produce natural and high-quality speech, but speech contains factors of variation (e.g. pitch, rhythm, loudness, timbre)\ that text alone cannot contain. In this work we move towards a speech…

This paper proposes a multilingual speech synthesis method which combines unsupervised phonetic representations (UPR) and supervised phonetic representations (SPR) to avoid reliance on the pronunciation dictionaries of target languages. In…

Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources,…

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are…

BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…

Isolating the voice of a specific person while filtering out other voices or background noises is challenging when video is shot in noisy environments. We propose audio-visual methods to isolate the voice of a single speaker and eliminate…

Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying…

We present a novel generative model that combines state-of-the-art neural text-to-speech (TTS) with semi-supervised probabilistic latent variable models. By providing partial supervision to some of the latent variables, we are able to force…