Recent advancements in generative speech models based on audio-text prompts
have enabled remarkable innovations like high-quality zero-shot text-to-speech.
However, existing models still face limitations in handling diverse audio-text
speech generation tasks involving transforming input speech and processing
audio captured in adverse acoustic conditions. This paper introduces SpeechX, a
versatile speech generation model capable of zero-shot TTS and various speech
transformation tasks, dealing with both clean and noisy signals. SpeechX
combines neural codec language modeling with multi-task learning using
task-dependent prompting, enabling unified and extensible modeling and
providing a consistent way for leveraging textual input in speech enhancement
and transformation tasks. Experimental results show SpeechX's efficacy in
various tasks, including zero-shot TTS, noise suppression, target speaker
extraction, speech removal, and speech editing with or without background
noise, achieving comparable or superior performance to specialized models
across tasks. See this https URL for demo samples.

SpeechX 是一种通用的语音生成模型，能够实现零 - shot 语音合成和各种语音转换任务，处理干净和嘈杂信号。SpeechX 结合了神经编解码器的语言建模和多任务学习，通过任务相关的提示实现统一和可扩展的建模，并在语音增强和转换任务中提供一致的方法来利用文本输入。实验结果表明，SpeechX 在零 - shot 语音合成、降噪、目标扬声器提取、语音去除和语音编辑等多种任务中表现出效果，与专门模型相比实现了可比或更好的性能。