{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/efficient-sequence-transduction-by-jointly","title":"Efficient Sequence Transduction by Jointly Predicting Tokens and Durations","arxiv_id":"2304.06795","date":"2023-04-13","proceeding":null,"authors":["Hainan Xu","Fei Jia","Somshubra Majumdar","He Huang","Shinji Watanabe","Boris Ginsburg"],"abstract":"This paper introduces a novel Token-and-Duration Transducer (TDT) architecture for sequence-to-sequence tasks. TDT extends conventional RNN-Transducer architectures by jointly predicting both a token and its duration, i.e. the number of input frames covered by the emitted token. This is achieved by using a joint network with two outputs which are independently normalized to generate distributions over tokens and durations. During inference, TDT models can skip input frames guided by the predicted duration output, which makes them significantly faster than conventional Transducers which process the encoder output frame by frame. TDT models achieve both better accuracy and significantly faster inference than conventional Transducers on different sequence transduction tasks. TDT models for Speech Recognition achieve better accuracy and up to 2.82X faster inference than conventional Transducers. TDT models for Speech Translation achieve an absolute gain of over 1 BLEU on the MUST-C test compared with conventional Transducers, and its inference is 2.27X faster. In Speech Intent Classification and Slot Filling tasks, TDT models improve the intent accuracy by up to over 1% (absolute) over conventional Transducers, while running up to 1.28X faster. Our implementation of the TDT model will be open-sourced with the NeMo (https://github.com/NVIDIA/NeMo) toolkit.","url_abs":"https://arxiv.org/abs/2304.06795v2","url_pdf":"https://arxiv.org/pdf/2304.06795v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"efficient-sequence-transduction-by-jointly","repo_url":"https://github.com/NVIDIA/NeMo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"efficient-sequence-transduction-by-jointly","repo_url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"efficient-sequence-transduction-by-jointly","repo_url":"https://github.com/kehanlu/Nemo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"efficient-sequence-transduction-by-jointly","repo_url":"https://github.com/wd929/NeMo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"intent-classification-and-slot-filling","task_name":"Intent Classification and Slot Filling"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"speech-intent-classification","task_name":"Speech Intent Classification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/intent-classification-on-slurp","task":"Intent Classification","dataset":"SLURP","model":"TDT 0-8","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy (%)":"90.07"},"uses_additional_data":false},{"leaderboard":"/sota/slot-filling-on-slurp","task":"Slot Filling","dataset":"SLURP","model":"TDT 0-6","rank_in_archive_order":1,"of":5,"metrics":{"F1":"0.8061"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-callhome-spanish-speech","task":"Speech Recognition","dataset":"CALLHOME Spanish Speech","model":"TDT 0-2","rank_in_archive_order":1,"of":1,"metrics":{"WER":"17.95"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-facebook-multilingual","task":"Speech Recognition","dataset":"facebook/multilingual_librispeech german","model":"TDT 0-4","rank_in_archive_order":1,"of":1,"metrics":{"WER":"3.93"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.06795","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.06795"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kehanlu/Nemo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NVIDIA/NeMo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wd929/NeMo","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"5cbcb4692500af92","entry":"hydra_runner","repo":"chimechallenge/C8DASR-Baseline-NeMo","repo_kind":"listed","path":"nemo/core/config/hydra_runner.py","file_url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo/blob/HEAD/nemo/core/config/hydra_runner.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5cbcb4692500af92"}},{"code_sha256_prefix":"81455ff48953c8d5","entry":"wrap_training_step","repo":"chimechallenge/C8DASR-Baseline-NeMo","repo_kind":"listed","path":"nemo/utils/model_utils.py","file_url":"https://github.com/chimechallenge/C8DASR-Baseline-NeMo/blob/HEAD/nemo/utils/model_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81455ff48953c8d5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}