{"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/enhancing-speaker-diarization-with-large","title":"Enhancing Speaker Diarization with Large Language Models: A Contextual Beam Search Approach","arxiv_id":"2309.05248","date":"2023-09-11","proceeding":null,"authors":["Tae Jin Park","Kunal Dhawan","Nithin Koluguri","Jagadeesh Balam"],"abstract":"Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam search to incorporate cues from both modalities: audio and text. Our experiments demonstrate that infusing lexical knowledge from the LLM into an acoustics-only diarization system improves overall speaker-attributed word error rate (SA-WER). The experimental results show that LLMs can provide complementary information to acoustic models for the speaker diarization task via proposed beam search decoding approach showing up to 39.8% relative delta-SA-WER improvement from the baseline system. Thus, we substantiate that the proposed technique is able to exploit contextual information that is inaccessible to acoustics-only systems which is represented by speaker embeddings. In addition, these findings point to the potential of using LLMs to improve speaker diarization and other speech processing tasks by capturing semantic and contextual cues.","url_abs":"https://arxiv.org/abs/2309.05248v3","url_pdf":"https://arxiv.org/pdf/2309.05248v3.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":"enhancing-speaker-diarization-with-large","repo_url":"https://github.com/tango4j/llm_speaker_tagging","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.05248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05248"}},"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/tango4j/llm_speaker_tagging","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":5},"by_repo_kind":{"listed":{"samples":5,"ran":0,"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":"4d1579a6e3fd7867","entry":"add_placeholder_speaker_softmax","repo":"tango4j/llm_speaker_tagging","repo_kind":"listed","path":"beam_search_utils.py","file_url":"https://github.com/tango4j/llm_speaker_tagging/blob/HEAD/beam_search_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":"4d1579a6e3fd7867"}},{"code_sha256_prefix":"bfe24aba2d5ea13c","entry":"count_num_of_spks","repo":"tango4j/llm_speaker_tagging","repo_kind":"listed","path":"beam_search_utils.py","file_url":"https://github.com/tango4j/llm_speaker_tagging/blob/HEAD/beam_search_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":"bfe24aba2d5ea13c"}},{"code_sha256_prefix":"d86ac2ddacbbd6b5","entry":"optuna_suggest_params","repo":"tango4j/llm_speaker_tagging","repo_kind":"listed","path":"hyper_optim.py","file_url":"https://github.com/tango4j/llm_speaker_tagging/blob/HEAD/hyper_optim.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":"d86ac2ddacbbd6b5"}},{"code_sha256_prefix":"e2d5bb1e27b5bc6c","entry":"process_session_data","repo":"tango4j/llm_speaker_tagging","repo_kind":"listed","path":"speaker_tagging_cpwer_jsons.py","file_url":"https://github.com/tango4j/llm_speaker_tagging/blob/HEAD/speaker_tagging_cpwer_jsons.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":"e2d5bb1e27b5bc6c"}},{"code_sha256_prefix":"bd3015ecb7bf80c1","entry":"run_mp_beam_search_decoding","repo":"tango4j/llm_speaker_tagging","repo_kind":"listed","path":"beam_search_utils.py","file_url":"https://github.com/tango4j/llm_speaker_tagging/blob/HEAD/beam_search_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":"bd3015ecb7bf80c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}