Related papers: Mid-attribute speaker generation using optimal-tra…
A primary challenge when deploying speaker recognition systems in real-world applications is performance degradation caused by environmental mismatch. We propose a diffusion-based method that takes speaker embeddings extracted from a…
This paper aims to build a multi-speaker expressive TTS system, synthesizing a target speaker's speech with multiple styles and emotions. To this end, we propose a novel contrastive learning-based TTS approach to transfer style and emotion…
For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…
The automatic speaker verification system is sometimes vulnerable to various spoofing attacks. The 2-class Gaussian Mixture Model classifier for genuine and spoofed speech is usually used as the baseline for spoofing detection. However, the…
Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this…
Imbalanced Learning is an important learning algorithm for the classification models, which have enjoyed much popularity on many applications. Typically, imbalanced learning algorithms can be partitioned into two types, i.e., data level…
For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…
When the available data of a target speaker is insufficient to train a high quality speaker-dependent neural text-to-speech (TTS) system, we can combine data from multiple speakers and train a multi-speaker TTS model instead. Many studies…
We investigate a novel cross-lingual multi-speaker text-to-speech synthesis approach for generating high-quality native or accented speech for native/foreign seen/unseen speakers in English and Mandarin. The system consists of three…
Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…
Recently, text-guided content generation has received extensive attention. In this work, we explore the possibility of text description-based speaker generation, i.e., using text prompts to control the speaker generation process.…
This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…
This paper introduces the performance evaluation of statistical approaches for TextIndependent speaker recognition system using source feature. Linear prediction LP residual is used as a representation of excitation information in speech.…
Cross-speaker emotion transfer in speech synthesis relies on extracting speaker-independent emotion embeddings for accurate emotion modeling without retaining speaker traits. However, existing timbre compression methods fail to fully…
Emotional text-to-speech seeks to convey affect while preserving intelligibility and prosody, yet existing methods rely on coarse labels or proxy classifiers and receive only utterance-level feedback. We introduce Emotion-Aware Stepwise…
We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap…
We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…
Generative adversarial networks (GANs) learn the distribution of observed samples through a zero-sum game between two machine players, a generator and a discriminator. While GANs achieve great success in learning the complex distribution of…
How can we teach robots or virtual assistants to gesture naturally? Can we go further and adapt the gesturing style to follow a specific speaker? Gestures that are naturally timed with corresponding speech during human communication are…
The cross-speaker emotion transfer task in text-to-speech (TTS) synthesis particularly aims to synthesize speech for a target speaker with the emotion transferred from reference speech recorded by another (source) speaker. During the…