相关论文: Creating New Voices using Normalizing Flows

While neural-based text to speech (TTS) models can synthesize natural and intelligible voice, they usually require high-quality speech data, which is costly to collect. In many scenarios, only noisy speech of a target speaker is available,…

Recently, the effectiveness of text-to-speech (TTS) systems combined with neural vocoders to generate high-fidelity speech has been shown. However, collecting the required training data and building these advanced systems from scratch are…

Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speaking style of the source speaker or mimic the distinctive…

Singing voice conversion is to convert the source singing voice into the target singing voice except for the content. Currently, flow-based models can complete the task of voice conversion, but they struggle to effectively extract latent…

We propose a unified framework for Singing Voice Synthesis (SVS) and Conversion (SVC), addressing the limitations of existing approaches in cross-domain SVS/SVC, poor output musicality, and scarcity of singing data. Our framework enables…

Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style. Previous work has two shortcomings: (1) suffering from obtaining facial embeddings that are well-aligned with the…

Automatically generating videos in which synthesized speech is synchronized with lip movements in a talking head has great potential in many human-computer interaction scenarios. In this paper, we present an automatic method to generate…

This paper explores the use of TTS synthesized training data for KWS (keyword spotting) task while minimizing development cost and time. Keyword spotting models require a huge amount of training data to be accurate, and obtaining such…

With the recent developments in speech synthesis via machine learning, this study explores incorporating linguistics knowledge to visualise and evaluate synthetic speech model training. If changes to the first and second formant (in turn,…

Text-to-speech (TTS) technology has achieved impressive results for widely spoken languages, yet many under-resourced languages remain challenged by limited data and linguistic complexities. In this paper, we present a novel methodology…

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS…

While generative methods have progressed rapidly in recent years, generating expressive prosody for an utterance remains a challenging task in text-to-speech synthesis. This is particularly true for systems that model prosody explicitly…

The mapping of text to speech (TTS) is non-deterministic, letters may be pronounced differently based on context, or phonemes can vary depending on various physiological and stylistic factors like gender, age, accent, emotions, etc. Neural…

Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made…

Multi-speaker text-to-speech (TTS) using a few adaption data is a challenge in practical applications. To address that, we propose a zero-shot multi-speaker TTS, named nnSpeech, that could synthesis a new speaker voice without fine-tuning…

Voice conversion models modify timbre while preserving paralinguistic features, enabling applications like dubbing and identity protection. However, most VC systems require access to target utterances, limiting their use when target data is…

End-to-end neural TTS has shown improved performance in speech style transfer. However, the improvement is still limited by the available training data in both target styles and speakers. Additionally, degenerated performance is observed…

The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and…

Modern voice cloning, also known as zero-shot text-to-speech (TTS), can synthesize speech that closely matches a target speaker from only seconds of reference audio, enabling applications such as personalized speech interfaces and dubbing.…

Laughter is one of the most expressive and natural aspects of human speech, conveying emotions, social cues, and humor. However, most text-to-speech (TTS) systems lack the ability to produce realistic and appropriate laughter sounds,…