Related papers: FabasedVC: Enhancing Voice Conversion with Text Mo…
Nowadays, as more and more systems achieve good performance in traditional voice conversion (VC) tasks, people's attention gradually turns to VC tasks under extreme conditions. In this paper, we propose a novel method for zero-shot voice…
This paper proposes a new "decompose-and-edit" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in…
Video-to-Speech (VTS) generation aims to synthesize speech from a silent video without auditory signals. However, existing VTS methods disregard the hierarchical nature of speech, which spans coarse speaker-aware semantics to fine-grained…
Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different…
As the recently proposed voice cloning system, NAUTILUS, is capable of cloning unseen voices using untranscribed speech, we investigate the feasibility of using it to develop a unified cross-lingual TTS/VC system. Cross-lingual speech…
Speech enhancement improves speech quality and promotes the performance of various downstream tasks. However, most current speech enhancement work was mainly devoted to improving the performance of downstream automatic speech recognition…
Modern sequence to sequence neural TTS systems provide close to natural speech quality. Such systems usually comprise a network converting linguistic/phonetic features sequence to an acoustic features sequence, cascaded with a neural…
Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks…
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…
We propose a neural network for zero-shot voice conversion (VC) without any parallel or transcribed data. Our approach uses pre-trained models for automatic speech recognition (ASR) and speaker embedding, obtained from a speaker…
Automatic speaker verification (ASV) is the process to recognize persons using voice as biometric. The ASV systems show considerable recognition performance with sufficient amount of speech from matched condition. One of the crucial…
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…
Singing voice conversion (SVC) aims to render the target singer's timbre while preserving melody and lyrics. However, existing zero-shot SVC systems remain fragile in real songs due to harmony interference, F0 errors, and the lack of…
Singing Voice Conversion (SVC) aims to transform a source singing voice into a target singer while preserving lyrics and melody. Most existing SVC methods depend on F0 extractors to capture the lead melody from clean vocals. However, no…
Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in…
Most text-to-speech (TTS) methods use high-quality speech corpora recorded in a well-designed environment, incurring a high cost for data collection. To solve this problem, existing noise-robust TTS methods are intended to use noisy speech…
Automatic speech recognition (ASR) has shown rapid advances in recent years but still degrades significantly in far-field and noisy environments. The recent development of self-supervised learning (SSL) technology can improve the ASR…
Modelling prosody variation is critical for synthesizing natural and expressive speech in end-to-end text-to-speech (TTS) systems. In this paper, a cross-utterance conditional VAE (CUC-VAE) is proposed to estimate a posterior probability…
Recent advances in zero-shot text-to-speech (TTS), driven by language models, diffusion models and masked generation, have achieved impressive naturalness in speech synthesis. Nevertheless, stability and fidelity remain key challenges,…
End-to-end neural TTS has achieved superior performance on reading style speech synthesis. However, it's still a challenge to build a high-quality conversational TTS due to the limitations of the corpus and modeling capability. This study…