SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.02382 · 2023

Unsupervised Speech Recognition with N-Skipgram and Positional Unigram Matching

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 8 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
lwang114/graphunsupasr canonical 8 of 9
FunctionStatusWhere it lives
detect_peaks Ran lwang114/graphunsupasr/espum/models/utils.py
code served (permissive licence) · get_code("d996cf06772c4c8f")
get_assignments Ran lwang114/graphunsupasr/w2vu_generate.py
code served (permissive licence) · get_code("5d7e11b26ae7fca1")
get_convolution_index_set Ran lwang114/graphunsupasr/kaldi_self_train/st/steps/nnet2/make_multisplice_configs.py
code served (permissive licence) · get_code("9d45b973f1eb1b50")
get_dataset_itr Ran lwang114/graphunsupasr/w2vu_generate.py
code served (permissive licence) · get_code("1a82e55d7de6917c")
load_lex Ran lwang114/graphunsupasr/kaldi_self_train/st/local/unsup_select.py
code served (permissive licence) · get_code("801f1e8e0d260afb")
load_tra Ran lwang114/graphunsupasr/kaldi_self_train/st/local/unsup_select.py
code served (permissive licence) · get_code("c79df675e2681009")
max_min_norm Ran lwang114/graphunsupasr/espum/models/utils.py
code served (permissive licence) · get_code("bed7cf8a53b7f8b7")
replicate_first_k_frames Ran lwang114/graphunsupasr/espum/models/utils.py
code served (permissive licence) · get_code("b962727751797747")
parse_splice_string Not yet run lwang114/graphunsupasr/kaldi_self_train/st/steps/nnet2/make_multisplice_configs.py
code served (permissive licence) · get_code("f1c7206adbb45460")

Repositories linked to this paper

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

Abstract

Training unsupervised speech recognition systems presents challenges due to GAN-associated instability, misalignment between speech and text, and significant memory demands. To tackle these challenges, we introduce a novel ASR system, ESPUM. This system harnesses the power of lower-order N-skipgrams (up to N=3) combined with positional unigram statistics gathered from a small batch of samples. Evaluated on the TIMIT benchmark, our model showcases competitive performance in ASR and phoneme segmentation tasks. Access our publicly available code at https://github.com/lwang114/GraphUnsupASR.

For agents

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

get_harvested_code_for_paper("2310.02382")
get_code_for_paper("2310.02382")
have("2310.02382")

Connect an agent — have() is free.