Related papers: Introducing Latent Timbre Synthesis

We introduce a novel convolutional network architecture with an interpretable latent space for modeling guitar amplifiers. Leveraging domain knowledge of popular amplifiers spanning a range of styles, the proposed system intuitively…

Recently, end-to-end multi-speaker text-to-speech (TTS) systems gain success in the situation where a lot of high-quality speech plus their corresponding transcriptions are available. However, laborious paired data collection processes…

Timbre transfer aims to modify the timbral identity of a musical recording while preserving the original melody and rhythm. While single-instrument timbre transfer has made substantial progress, existing approaches to multi-instrument…

Text-to-speech (TTS) synthesis is a technology that converts written text into spoken words, enabling a natural and accessible means of communication. This abstract explores the key aspects of TTS synthesis, encompassing its underlying…

We present MParrotTTS, a unified multilingual, multi-speaker text-to-speech (TTS) synthesis model that can produce high-quality speech. Benefiting from a modularized training paradigm exploiting self-supervised speech representations,…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

Neural audio synthesis is an actively researched topic, having yielded a wide range of techniques that leverages machine learning architectures. Google Magenta elaborated a novel approach called Differential Digital Signal Processing (DDSP)…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its…

We present an end-to-end text-to-speech (TTS) synthesis system that generates audio and synchronized tongue motion directly from text. This is achieved by adapting a 3D model of the tongue surface to an articulatory dataset and training a…

Although lip-to-speech synthesis (L2S) has achieved significant progress in recent years, current state-of-the-art methods typically rely on intermediate representations such as mel-spectrograms or discrete self-supervised learning (SSL)…

We study timbre transfer as an inference-time editing problem for music audio. Starting from a strong pre-trained latent diffusion model, we introduce a lightweight procedure that requires no additional training: (i) a dimension-wise noise…

Reward modeling, crucial for aligning large language models (LLMs) with human preferences, is often bottlenecked by the high cost of preference data. Existing textual data synthesis methods are computationally expensive. We propose a novel…

Unconstrained lip-to-speech synthesis aims to generate corresponding speeches from silent videos of talking faces with no restriction on head poses or vocabulary. Current works mainly use sequence-to-sequence models to solve this problem,…

In this paper we introduce Latent Tree Language Model (LTLM), a novel approach to language modeling that encodes syntax and semantics of a given sentence as a tree of word roles. The learning phase iteratively updates the trees by moving…

With the rapid development of deep learning techniques, the generation and counterfeiting of multimedia material are becoming increasingly straightforward to perform. At the same time, sharing fake content on the web has become so simple…

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…

Neural Audio Synthesis (NAS) models offer interactive musical control over high-quality, expressive audio generators. While these models can operate in real-time, they often suffer from high latency, making them unsuitable for intimate…

This chapter explores advancements in decoding strategies for large language models (LLMs), focusing on enhancing the Locally Typical Sampling (LTS) algorithm. Traditional decoding methods, such as top-k and nucleus sampling, often struggle…

With the similarity between music and speech synthesis from symbolic input and the rapid development of text-to-speech (TTS) techniques, it is worthwhile to explore ways to improve the MIDI-to-audio performance by borrowing from TTS…