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 …

Abstract Machine learning, including neural network techniques, have been applied to
virtually every domain in natural language processing. One problem that has been …

In the English speech-to-text (STT) machine learning task, acoustic models are
conventionally trained on uncased Latin characters, and any necessary orthography (such …

While there have been several contributions exploring state of the art techniques for text
normalization, the problem of inverse text normalization (ITN) remains relatively unexplored …

Text normalization (TN) is an important step in conversational systems. It converts written
text to its spoken form to facilitate speech recognition, natural language understanding and …

Inverse text normalization (ITN) converts spoken-domain automatic speech recognition
(ASR) output into written-domain text to improve the readability of the ASR output. Many …

We perform text normalization, ie the transformation of words from the written to the spoken
form, using a memory augmented neural network. With the addition of dynamic memory …

Automatic Speech Recognition (ASR) systems typically yield output in lexical form. However,
humans prefer a written form output. To bridge this gap, ASR systems usually employ …

This paper proposes a novel method to jointly generate spoken and written text from input
speech for expanding use cases of speech-based applications. The spoken text generated …

Human professional transcription services provide a variety of transcription styles to
customize different needs. To accommodate different users and facilitate seamless …