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 …

We introduce GLM-4-Voice, an intelligent and human-like end-to-end spoken chatbot. It
supports both Chinese and English, engages in real-time voice conversations, and varies …

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

The recognition of rare named entities, such as personal names and terminologies, is
challenging for automatic speech recognition (ASR) systems, especially when they are not …

Contextual ASR or hotword customization holds substantial practical value. Despite the
impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) …

The recognition of rare named entities, such as personal names and terminologies, is
challenging for automatic speech recognition (ASR) systems, especially when they are not …

The image-based multimodal automatic speech recognition (ASR) model enhances speech
recognition performance by incorporating audio-related image. However, some works …

Although contextualized automatic speech recognition (ASR) systems are commonly used to
improve the recognition of uncommon words, their effectiveness is hindered by the inherent …

End-to-end automatic speech recognition (ASR) systems often struggle to recognize rare
name entities, such as personal names, organizations and terminologies that are not …

Deep biasing methods and shallow fusion methods have been demonstrated to improve the
performance of end-to-end ASR effectively. However, accurate recognition often becomes …