This report introduces FunAudioLLM, a model family designed to enhance natural voice
interactions between humans and large language models (LLMs). At its core are two …

Recent advancements in spoken dialogue models, exemplified by systems like GPT-4o,
have captured significant attention in the speech domain. Compared to traditional three-tier …

Text-to-speech (TTS), also known as speech synthesis, is a prominent research area that
aims to generate natural-sounding human speech from text. Recently, with the increasing …

Generative retrieval, which has demonstrated effectiveness in text-to-text retrieval, utilizes a
sequence-to-sequence model to directly generate candidate identifiers based on natural …

Recent advancements in large language models (LLMs) and multimodal speech-text
models have laid the groundwork for seamless voice interactions, enabling real-time …

Speech watermarking techniques can proactively mitigate the potential harmful
consequences of instant voice cloning techniques. These techniques involve the insertion of …

Recent research in the domain of multimodal unified representations predominantly
employs codebook as representation forms, utilizing Vector Quantization (VQ) for …