Related papers: SemaVoice: Semantic-Aware Continuous Autoregressiv…
Recent advances in generative language modeling applied to discrete speech tokens presented a new avenue for text-to-speech (TTS) synthesis. These speech language models (SLMs), similarly to their textual counterparts, are scalable,…
Modern autoregressive speech synthesis models leveraging language models have demonstrated remarkable performance. However, the sequential nature of next token prediction in these models leads to significant latency, hindering their…
Text-to-speech synthesis (TTS) is a task to convert texts into speech. Two of the factors that have been driving TTS are the advancements of probabilistic models and latent representation learning. We propose a TTS method based on latent…
Recently, excellent progress has been made in speech recognition. However, pure data-driven approaches have struggled to solve the problem in domain-mismatch and long-tailed data. Considering that knowledge-driven approaches can help…
We propose a novel autoregressive modeling approach for speech synthesis, combining a variational autoencoder (VAE) with a multi-modal latent space and an autoregressive model that uses Gaussian Mixture Models (GMM) as the conditional…
The development of autoregressive modeling (AM) in computer vision lags behind natural language processing (NLP) in self-supervised pre-training. This is mainly caused by the challenge that images are not sequential signals and lack a…
Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms…
Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the…
Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…
To further improve the speaking styles of synthesized speeches, current text-to-speech (TTS) synthesis systems commonly employ reference speeches to stylize their outputs instead of just the input texts. These reference speeches are…
Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global…
In this paper, we present SANE-TTS, a stable and natural end-to-end multilingual TTS model. By the difficulty of obtaining multilingual corpus for given speaker, training multilingual TTS model with monolingual corpora is unavoidable. We…
Generative adversarial networks have seen rapid development in recent years and have led to remarkable improvements in generative modelling of images. However, their application in the audio domain has received limited attention, and…
Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a…
We propose a novel approach to significantly improve the intelligibility in the Non-Audible Murmur (NAM)-to-speech conversion task, leveraging self-supervision and sequence-to-sequence (Seq2Seq) learning techniques. Unlike conventional…
We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit.…
Speech enhancement (SE) recovers clean speech from noisy signals and is vital for applications such as telecommunications and automatic speech recognition (ASR). While generative approaches achieve strong perceptual quality, they often rely…
Recent advances in text-to-speech (TTS) led to the development of flexible multi-speaker end-to-end TTS systems. We extend state-of-the-art attention-based automatic speech recognition (ASR) systems with synthetic audio generated by a TTS…
The increased adoption of digital assistants makes text-to-speech (TTS) synthesis systems an indispensable feature of modern mobile devices. It is hence desirable to build a system capable of generating highly intelligible speech in the…
We present S$^2$Voice, the winning system of the Singing Voice Conversion Challenge (SVCC) 2025 for both the in-domain and zero-shot singing style conversion tracks. Built on the strong two-stage Vevo baseline, S$^2$Voice advances style…