.png){kind=icon}
.png){kind=icon}
Return
SPIRIT-LM: Interleaved Spoken and Written Language Model
.png){kind=icon}
PRE
AI
N
M
Y
C
E
P
R
D
A
M
G
W
S
P
S
D
DOI：10.1162/tacl_a_00728.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We introduce SPIRIT-LM, a foundation multi- modal language model that freely mixes text and speech. Our model is based on a 7B pre- trained text language model that we extend to the speech modality by continuously training it on text and speech units. Speech and text sequences are concatenated as a single stream of tokens, and trained with a word-level interleaving method using a small automatically curated speech-text parallel corpus. SPIRIT--LM comes in two versions: a BASE version that uses speech phonetic units (HuBERT) and an EXPRESSIVE version that models expressivity using pitch and style units in addition to the phonetic units. For both versions, the text is encoded with subword BPE tokens. The resulting model displays both the semantic abilities of text models and the expressive abilities of speech models. Additionally, we demonstrate that SPIRIT-LM can learn new tasks in a few-shot fashion across modalities (i.e., ASR, TTS, Speech Classification). We make available model weights and inference code.(1, 2)
Journal
T
IF:
6.9
Papers:
486
Citations:
5.7K
Organization
Cited Papers