SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.15297 · 2024

YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
rorizzz/yolo-stutter canonical 4 of 5
FunctionStatusWhere it lives
convert_pad_shape Ran rorizzz/yolo-stutter/yolo-stutter/utils/vits/commons.py
code served (permissive licence) · get_code("59ae0708b1e8d94b")
get_padding Ran rorizzz/yolo-stutter/yolo-stutter/utils/vits/commons.py
code served (permissive licence) · get_code("a26f85d7c72ef39a")
get_sample_rate_wave Ran rorizzz/yolo-stutter/yolo-stutter/etc/inference.py
code served (permissive licence) · get_code("55b57dbda68f807e")
print_shapes Ran rorizzz/yolo-stutter/yolo-stutter/utils/model_utils/check_dims.py
code served (permissive licence) · get_code("2a1a83e3efb39fb0")
intersperse Not yet run rorizzz/yolo-stutter/yolo-stutter/utils/vits/commons.py
code served (permissive licence) · get_code("c01a3efb274ff778")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2408.15297")
get_code_for_paper("2408.15297")
have("2408.15297")

Connect an agent — have() is free.