Scaling text-to-speech (TTS) to large-scale, multi-speaker, and in-the-wild datasets is
important to capture the diversity in human speech such as speaker identities, prosodies …

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 …

Scaling text-to-speech (TTS) with autoregressive language model (LM) to large-scale
datasets by quantizing waveform into discrete speech tokens is making great progress to …

Retrieval is a widely adopted approach for improving language models leveraging external
information. As the field moves towards multi-modal large language models, it is important to …

Speech analysis is a crucial tool in discerning the complex cognitive and emotional
subtleties of individuals. It holds a significant role in psychiatric research, particularly in the …

Expressive speech synthesis models are trained by adding corpora with diverse speakers,
various emotions, and different speaking styles to the dataset, in order to control various …

Retrieval is a widely adopted approach for improving language models leveraging external
information. As the field moves towards multi-modal large language models, it is important to …

This study focuses on a systematic review of the literature and an experimental comparison
of 20 English speech synthesis methods. Nine of the models were subjected to a …

Conventional compression techniques for text are based on typical frequencies of individual
letters within the text, independent of higher-level semantics. This disclosure describes a …