Related papers: TVTSyn: Content-Synchronous Time-Varying Timbre fo…

State-of-the-art Variational Auto-Encoders (VAEs) for learning disentangled latent representations give impressive results in discovering features like pitch, pause duration, and accent in speech data, leading to highly controllable…

Speaker embedding is an important front-end module to explore discriminative speaker features for many speech applications where speaker information is needed. Current SOTA backbone networks for speaker embedding are designed to aggregate…

Real-time voice agents face a dilemma: end-to-end models often lack deep reasoning, while cascaded pipelines incur high latency by executing ASR, LLM reasoning, and TTS strictly in sequence, unlike human conversation where listeners often…

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…

Timbre allows us to distinguish between sounds even when they share the same pitch and loudness, playing an important role in music, instrument recognition, and speech. Traditional approaches, such as frequency analysis or machine learning,…

Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities. Despite recent progress…

Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the…

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…

Zero-shot Text-to-Speech (TTS) has recently advanced significantly, enabling models to synthesize speech from text using short, limited-context prompts. These prompts serve as voice exemplars, allowing the model to mimic speaker identity,…

Zero-Shot Voice Conversion (VC) aims to transform the source speaker's timbre into an arbitrary unseen one while retaining speech content. Most prior work focuses on preserving the source's prosody, while fine-grained timbre information may…

Novel text-to-speech systems can generate entirely new voices that were not seen during training. However, it remains a difficult task to efficiently create personalized voices from a high-dimensional speaker space. In this work, we use…

This paper proposes speaker-adaptive neural vocoders for parametric text-to-speech (TTS) systems. Recently proposed WaveNet-based neural vocoding systems successfully generate a time sequence of speech signal with an autoregressive…

This paper proposes a deep multi-speaker text-to-speech (TTS) model for spoofing speaker verification (SV) systems. The proposed model employs one network to synthesize time-downsampled mel-spectrograms from text input and another network…

The goal of this work is to simultaneously generate natural talking faces and speech outputs from text. We achieve this by integrating Talking Face Generation (TFG) and Text-to-Speech (TTS) systems into a unified framework. We address the…

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks…

We present a lightweight adaptable neural TTS system with high quality output. The system is composed of three separate neural network blocks: prosody prediction, acoustic feature prediction and Linear Prediction Coding Net as a neural…

The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint…

Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outputs typically results in notable latency, which is…

The recently developed pitch-controllable text-to-speech (TTS) model, i.e. FastPitch, was conditioned for the pitch contours. However, the quality of the synthesized speech degraded considerably for pitch values that deviated significantly…

We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle…