{"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/hyporadise-an-open-baseline-for-generative-1","title":"HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models","arxiv_id":"2309.15701","date":"2023-09-27","proceeding":"NeurIPS 2023 11","authors":["Chen Chen","Yuchen Hu","Chao-Han Huck Yang","Sabato Macro Siniscalchi","Pin-Yu Chen","Eng Siong Chng"],"abstract":"Advancements in deep neural networks have allowed automatic speech recognition (ASR) systems to attain human parity on several publicly available clean speech datasets. However, even state-of-the-art ASR systems experience performance degradation when confronted with adverse conditions, as a well-trained acoustic model is sensitive to variations in the speech domain, e.g., background noise. Intuitively, humans address this issue by relying on their linguistic knowledge: the meaning of ambiguous spoken terms is usually inferred from contextual cues thereby reducing the dependency on the auditory system. Inspired by this observation, we introduce the first open-source benchmark to utilize external large language models (LLMs) for ASR error correction, where N-best decoding hypotheses provide informative elements for true transcription prediction. This approach is a paradigm shift from the traditional language model rescoring strategy that can only select one candidate hypothesis as the output transcription. The proposed benchmark contains a novel dataset, HyPoradise (HP), encompassing more than 334,000 pairs of N-best hypotheses and corresponding accurate transcriptions across prevalent speech domains. Given this dataset, we examine three types of error correction techniques based on LLMs with varying amounts of labeled hypotheses-transcription pairs, which gains a significant word error rate (WER) reduction. Experimental evidence demonstrates the proposed technique achieves a breakthrough by surpassing the upper bound of traditional re-ranking based methods. More surprisingly, LLM with reasonable prompt and its generative capability can even correct those tokens that are missing in N-best list. We make our results publicly accessible for reproducible pipelines with released pre-trained models, thus providing a new evaluation paradigm for ASR error correction with LLMs.","url_abs":"https://arxiv.org/abs/2309.15701v2","url_pdf":"https://arxiv.org/pdf/2309.15701v2.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":"hyporadise-an-open-baseline-for-generative-1","repo_url":"https://github.com/hypotheses-paradise/hypo2trans","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"re-ranking","task_name":"Re-Ranking"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-ted-lium","task":"Speech Recognition","dataset":"TED-LIUM","model":"Whisper-LLaMa-7b","rank_in_archive_order":1,"of":2,"metrics":{"Word Error Rate (WER)":"4.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-recognition-on-tedlium","task":"Speech Recognition","dataset":"Tedlium","model":"Whispering-LLaMa-7b","rank_in_archive_order":3,"of":4,"metrics":{"Word Error Rate (WER)":"4.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.15701","atlas_url":"https://app.syntology.ai/?focus=2309.15701","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15701"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/hypotheses-paradise/hypo2trans","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"6e0808fc4828513a","entry":"exact_div","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/utils.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e0808fc4828513a"}},{"code_sha256_prefix":"e56996b20b9c19cb","entry":"optional_int","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/utils.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e56996b20b9c19cb"}},{"code_sha256_prefix":"5d9d25629a2e0506","entry":"pad_or_trim","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/audio.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/audio.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d9d25629a2e0506"}},{"code_sha256_prefix":"e529c9641c178fe0","entry":"sinusoids","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/model.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/model.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e529c9641c178fe0"}},{"code_sha256_prefix":"176b6ba6c2c2940c","entry":"str2bool","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/utils.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"176b6ba6c2c2940c"}},{"code_sha256_prefix":"f475a7a8460e2abc","entry":"build_tokenizer","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/tokenizer.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/tokenizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f475a7a8460e2abc"}},{"code_sha256_prefix":"51e0aca11651c4d4","entry":"transcribe","repo":"hypotheses-paradise/hypo2trans","repo_kind":"official","path":"generate_data/whisper/whisper/transcribe.py","file_url":"https://github.com/hypotheses-paradise/hypo2trans/blob/HEAD/generate_data/whisper/whisper/transcribe.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51e0aca11651c4d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}