Related papers: NanoVoice: Efficient Speaker-Adaptive Text-to-Spee…

With rapid progress in neural text-to-speech (TTS) models, personalized speech generation is now in high demand for many applications. For practical applicability, a TTS model should generate high-quality speech with only a few audio…

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

With recent advancements in voice cloning, the performance of speech synthesis for a target speaker has been rendered similar to the human level. However, autoregressive voice cloning systems still suffer from text alignment failures,…

This paper proposes a voice conversion (VC) method using sequence-to-sequence (seq2seq or S2S) learning, which flexibly converts not only the voice characteristics but also the pitch contour and duration of input speech. The proposed…

State-of-the-art text-to-speech (TTS) systems require several hours of recorded speech data to generate high-quality synthetic speech. When using reduced amounts of training data, standard TTS models suffer from speech quality and…

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…

Speaker adaptive training (SAT) of neural network acoustic models learns models in a way that makes them more suitable for adaptation to test conditions. Conventionally, model-based speaker adaptive training is performed by having a set of…

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…

In this work, we present DiffVoice, a novel text-to-speech model based on latent diffusion. We propose to first encode speech signals into a phoneme-rate latent representation with a variational autoencoder enhanced by adversarial training,…

Silent and whispered speech offer promise for always-available voice interaction with AI, yet existing methods struggle to balance vocabulary size, wearability, silence, and noise robustness. We present NasoVoce, a nose-bridge-mounted…

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to…

We introduce MiniMax-Speech, an autoregressive Transformer-based Text-to-Speech (TTS) model that generates high-quality speech. A key innovation is our learnable speaker encoder, which extracts timbre features from a reference audio without…

High-fidelity speech can be synthesized by end-to-end text-to-speech models in recent years. However, accessing and controlling speech attributes such as speaker identity, prosody, and emotion in a text-to-speech system remains a challenge.…

There is a rising interest and trend in research towards directly translating speech from one language to another, known as end-to-end speech-to-speech translation. However, most end-to-end models struggle to outperform cascade models,…

In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without…

With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of…

This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck feature extractor…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…