Speech pre-training has primarily demonstrated efficacy on classification
tasks, while its capability of generating novel speech, similar to how GPT-2
can generate coherent paragraphs, has barely been explored. Generative Spoken
Language Modeling (GSLM) \cite{Lakhotia2021} is the only prior work addressing
the generative aspects of speech pre-training, which replaces text with
discovered phone-like units for language modeling and shows the ability to
generate meaningful novel sentences. Unfortunately, despite eliminating the
need of text, the units used in GSLM discard most of the prosodic information.
Hence, GSLM fails to leverage prosody for better comprehension, and does not
generate expressive speech. In this work, we present a prosody-aware generative
spoken language model (pGSLM). It is composed of a multi-stream transformer
language model (MS-TLM) of speech, represented as discovered unit and prosodic
feature streams, and an adapted HiFi-GAN model converting MS-TLM outputs to
waveforms. We devise a series of metrics for prosody modeling and generation,
and re-use metrics from GSLM for content modeling. Experimental results show
that the pGSLM can utilize prosody to improve both prosody and content
modeling, and also generate natural, meaningful, and coherent speech given a
spoken prompt. Audio samples can be found at this https URL
Codes and models are available at
this https URL

本文提出了一种基于多流 Transformer 和 HiFi-GAN 的韵律感知生成口语语言模型 (pGSLM)，利用韵律为生成式预训练提供了更好的理解和生成能力。实验结果表明，该模型可以显著提高韵律和内容建模，并能够生成自然、有意义和连贯的语音。