Speaker individuality information is among the most critical elements within speech signals.
By thoroughly and accurately modeling this information, it can be utilized in various …

Neural codecs have become crucial to recent speech and audio generation research. In
addition to signal compression capabilities, discrete codecs have also been found to …

Singing Voice Synthesis (SVS) has witnessed significant advancements with the advent of
deep learning techniques. However, a significant challenge in SVS is the scarcity of labeled …

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based
systems offer competitive performance to their counterparts. Further optimization can be …

In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for
various speech, audio, and music signals. The toolkit features a Pythonic interface with …

The rapid advancement of speech generation technologies in the era of large language
models (LLMs) has established discrete speech tokens as a foundational paradigm for …

We propose a new speech discrete token vocoder, vec2wav 2.0, which advances voice
conversion (VC). We use discrete tokens from speech self-supervised models as the content …

This paper proposes a method for extracting speaker embedding for each speaker from a
variable-length recording containing multiple speakers. Speaker embeddings are crucial not …

Although discrete speech tokens have exhibited strong potential for language model-based
speech generation, their high bitrates and redundant timbre information restrict the …

We introduce ESPnet-EZ, an extension of the open-source speech processing toolkit
ESPnet, aimed at quick and easy development of speech models. ESPnet-EZ focuses on …