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.
| Repository | Role | Ran |
|---|---|---|
| cornerfarmer/ctc_segmentation | canonical | 0 of 3 |
| lumaku/ctc-segmentation | pwc_unofficial | 3 of 4 |
| danoneata/espnet | pwc_unofficial | 0 of 3 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
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.