Papers › Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model

Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Model

24 Apr 2023arXiv:2304.13731archive 2025-07-28

Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria

The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural language processing (NLP) tasks. Inspired by such successes, we adopt such an instruction-tuned LLM Flan-T5 as the text encoder for text-to-audio (TTA) generation -- a task where the goal is to generate an audio from its textual description. The prior works on TTA either pre-trained a joint text-audio encoder or used a non-instruction-tuned model, such as, T5. Consequently, our latent diffusion model (LDM)-based approach TANGO outperforms the state-of-the-art AudioLDM on most metrics and stays comparable on the rest on AudioCaps test set, despite training the LDM on a 63 times smaller dataset and keeping the text encoder frozen. This improvement might also be attributed to the adoption of audio pressure level-based sound mixing for training set augmentation, whereas the prior methods take a random mix.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

declare-lab/tango officialmentioned in papermentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Audio Generation	AudioCaps	TANGO	FAD	1.59	#14 of 23	Archive leaderboard	report
Audio Generation	AudioCaps	TANGO	FD	24.52	#14 of 23	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adafactor Attention Attention Dropout BPE Dense Connections Diffusion Dropout Flan-T5 Gated Linear Unit Inverse Square Root Schedule Latent Diffusion Model Layer Normalization Linear Layer Multi-Head Attention Residual Connection SentencePiece Softmax T5 Test

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections