SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.09127 · 2020

CTC-Segmentation of Large Corpora for German End-to-end Speech Recognition

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 3 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
cornerfarmer/ctc_segmentation canonical 0 of 3
lumaku/ctc-segmentation pwc_unofficial 3 of 4
danoneata/espnet pwc_unofficial 0 of 3
FunctionStatusWhere it lives
get_partitions Ran lumaku/ctc-segmentation/ctc_segmentation/partitioning.py
code served (permissive licence) · get_code("05b5b68ce0fb9aa0")
prepare_text Ran lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py
code served (permissive licence) · get_code("a99ea16d4a737423")
prepare_tokenized_text Ran lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py
code served (permissive licence) · get_code("2073edbaac1f78f1")
adadelta_eps_decay Not yet run danoneata/espnet/espnet/asr/asr_utils.py
code served (permissive licence) · get_code("bb3665ddb6b8dd2d")
adam_lr_decay Not yet run danoneata/espnet/espnet/asr/asr_utils.py
code served (permissive licence) · get_code("1fa5ca494ed9750a")
ctc_segmentation Not yet run lumaku/ctc-segmentation/ctc_segmentation/ctc_segmentation.py
code served (permissive licence) · get_code("97301ff4a47ba9d9")
prepare_text Not yet run cornerfarmer/ctc_segmentation/align.py
code served (permissive licence) · get_code("4122d89455a8def4")
recognize Not yet run cornerfarmer/ctc_segmentation/decode.py
code served (permissive licence) · get_code("d4a13bf0db9e2d8f")
restore_snapshot Not yet run danoneata/espnet/espnet/asr/asr_utils.py
code served (permissive licence) · get_code("96081a60369c59e0")
write_output Not yet run cornerfarmer/ctc_segmentation/align.py
code served (permissive licence) · get_code("8fd1afbcfc039bd4")

Repositories linked to this paper

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

Abstract

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters and model capacity. However, these models also require more training data to achieve comparable performance. In this work, we combine freely available corpora for German speech recognition, including yet unlabeled speech data, to a big dataset of over $1700$h of speech data. For data preparation, we propose a two-stage approach that uses an ASR model pre-trained with Connectionist Temporal Classification (CTC) to boot-strap more training data from unsegmented or unlabeled training data. Utterances are then extracted from label probabilities obtained from the network trained with CTC to determine segment alignments. With this training data, we trained a hybrid CTC/attention Transformer model that achieves $12.8\%$ WER on the Tuda-DE test set, surpassing the previous baseline of $14.4\%$ of conventional hybrid DNN/HMM ASR.

For agents

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

get_harvested_code_for_paper("2007.09127")
get_code_for_paper("2007.09127")
have("2007.09127")

Connect an agent — have() is free.