相关论文: Improving Zero-shot Voice Style Transfer via Disen…

Factorizing speech as disentangled speech representations is vital to achieve highly controllable style transfer in voice conversion (VC). Conventional speech representation learning methods in VC only factorize speech as speaker and…

Given a pair of source and reference speech recordings, speech-to-speech (S2S) emotion style transfer involves the generation of an output speech that mimics the emotion characteristics of the reference while preserving the content and…

Attention injection-based style transfer has achieved remarkable progress in recent years. However, existing methods often suffer from content leakage, where the undesired semantic content of the style image mistakenly appears in the…

Zero-shot Text-To-Speech (TTS) synthesis shows great promise for personalized voice customization through voice cloning. However, current methods for achieving zero-shot TTS heavily rely on large model scales and extensive training datasets…

Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common semantic characteristics between the visual modality and…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

In this paper we propose modifications to the neural network framework, AutoVC for the task of singing technique conversion. This includes utilising a pretrained singing technique encoder which extracts technique information, upon which a…

An increasing number of people in the world today speak a mixed-language as a result of being multilingual. However, building a speech recognition system for code-switching remains difficult due to the availability of limited resources and…

Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…

One-shot voice conversion aims to change the timbre of any source speech to match that of the unseen target speaker with only one speech sample. Existing methods face difficulties in satisfactory speech representation disentanglement and…

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information.…

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models…

Deep-embedding methods aim to discover representations of a domain that make explicit the domain's class structure and thereby support few-shot learning. Disentangling methods aim to make explicit compositional or factorial structure. We…

Previously, we introduced VoiceGrad, a nonparallel voice conversion (VC) technique enabling mel-spectrogram conversion from source to target speakers using a score-based diffusion model. The concept involves training a score network to…

As parallel training data is scarce for one-shot voice conversion (VC) tasks, waveform reconstruction is typically performed by various VC systems. A typical one-shot VC system comprises a content encoder and a speaker encoder. However, two…

We present a new approach to perform zero-shot cross-modal transfer between speech and text for translation tasks. Multilingual speech and text are encoded in a joint fixed-size representation space. Then, we compare different approaches to…

Non-parallel many-to-many voice conversion is recently attract-ing huge research efforts in the speech processing community. A voice conversion system transforms an utterance of a source speaker to another utterance of a target speaker by…

Voice conversion is a common speech synthesis task which can be solved in different ways depending on a particular real-world scenario. The most challenging one often referred to as one-shot many-to-many voice conversion consists in copying…