├── LICENSE ├── README.md ├── assets ├── attn.png ├── lattice.png ├── layers.png ├── poster.pdf └── sactc.pdf ├── configs ├── baseline_ctc.yaml ├── baseline_sot_ctc.yaml ├── baseline_sot_only.yaml ├── decode │ ├── decode_asr_aed_ctc.yaml │ ├── decode_asr_aed_only.yaml │ └── decode_asr_ctc.yaml ├── proposed_sactc_r15.yaml ├── proposed_sactc_sot_r05.yaml ├── proposed_sactc_sot_r10.yaml ├── proposed_sactc_sot_r15.yaml ├── proposed_sactc_sot_r20.yaml └── readme.md ├── espnet2-patch ├── asr │ ├── espnet_model.py │ └── sactc.py └── tasks │ └── asr.py ├── run_demo.sh └── scoring ├── files └── librispeechmix │ ├── dev_clean_2mix │ └── utt2ovlp_rate │ ├── dev_clean_3mix │ └── utt2ovlp_rate │ ├── test_clean_2mix │ └── utt2ovlp_rate │ └── test_clean_3mix │ └── utt2ovlp_rate ├── requirements.txt ├── run_pi_scoring.sh ├── search_best_permutation.py └── subset_by_ovlp_rate.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/README.md -------------------------------------------------------------------------------- /assets/attn.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/assets/attn.png -------------------------------------------------------------------------------- /assets/lattice.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/assets/lattice.png -------------------------------------------------------------------------------- /assets/layers.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/assets/layers.png -------------------------------------------------------------------------------- /assets/poster.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/assets/poster.pdf -------------------------------------------------------------------------------- /assets/sactc.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/assets/sactc.pdf -------------------------------------------------------------------------------- /configs/baseline_ctc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/baseline_ctc.yaml -------------------------------------------------------------------------------- /configs/baseline_sot_ctc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/baseline_sot_ctc.yaml -------------------------------------------------------------------------------- /configs/baseline_sot_only.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/baseline_sot_only.yaml -------------------------------------------------------------------------------- /configs/decode/decode_asr_aed_ctc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/decode/decode_asr_aed_ctc.yaml -------------------------------------------------------------------------------- /configs/decode/decode_asr_aed_only.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/decode/decode_asr_aed_only.yaml -------------------------------------------------------------------------------- /configs/decode/decode_asr_ctc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/decode/decode_asr_ctc.yaml -------------------------------------------------------------------------------- /configs/proposed_sactc_r15.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/proposed_sactc_r15.yaml -------------------------------------------------------------------------------- /configs/proposed_sactc_sot_r05.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/proposed_sactc_sot_r05.yaml -------------------------------------------------------------------------------- /configs/proposed_sactc_sot_r10.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/proposed_sactc_sot_r10.yaml -------------------------------------------------------------------------------- /configs/proposed_sactc_sot_r15.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/proposed_sactc_sot_r15.yaml -------------------------------------------------------------------------------- /configs/proposed_sactc_sot_r20.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/proposed_sactc_sot_r20.yaml -------------------------------------------------------------------------------- /configs/readme.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/configs/readme.md -------------------------------------------------------------------------------- /espnet2-patch/asr/espnet_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/espnet2-patch/asr/espnet_model.py -------------------------------------------------------------------------------- /espnet2-patch/asr/sactc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/espnet2-patch/asr/sactc.py -------------------------------------------------------------------------------- /espnet2-patch/tasks/asr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/espnet2-patch/tasks/asr.py -------------------------------------------------------------------------------- /run_demo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/run_demo.sh -------------------------------------------------------------------------------- /scoring/files/librispeechmix/dev_clean_2mix/utt2ovlp_rate: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/files/librispeechmix/dev_clean_2mix/utt2ovlp_rate -------------------------------------------------------------------------------- /scoring/files/librispeechmix/dev_clean_3mix/utt2ovlp_rate: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/files/librispeechmix/dev_clean_3mix/utt2ovlp_rate -------------------------------------------------------------------------------- /scoring/files/librispeechmix/test_clean_2mix/utt2ovlp_rate: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/files/librispeechmix/test_clean_2mix/utt2ovlp_rate -------------------------------------------------------------------------------- /scoring/files/librispeechmix/test_clean_3mix/utt2ovlp_rate: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/files/librispeechmix/test_clean_3mix/utt2ovlp_rate -------------------------------------------------------------------------------- /scoring/requirements.txt: -------------------------------------------------------------------------------- 1 | click 2 | tqdm 3 | editdistance 4 | -------------------------------------------------------------------------------- /scoring/run_pi_scoring.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/run_pi_scoring.sh -------------------------------------------------------------------------------- /scoring/search_best_permutation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/search_best_permutation.py -------------------------------------------------------------------------------- /scoring/subset_by_ovlp_rate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kjw11/Speaker-Aware-CTC/HEAD/scoring/subset_by_ovlp_rate.py --------------------------------------------------------------------------------