{"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/speechlmscore-evaluating-speech-generation","title":"SpeechLMScore: Evaluating speech generation using speech language model","arxiv_id":"2212.04559","date":"2022-12-08","proceeding":null,"authors":["Soumi Maiti","Yifan Peng","Takaaki Saeki","Shinji Watanabe"],"abstract":"While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human evaluation scores with machine learning models. However, they rely on supervised learning and thus suffer from high annotation costs and domain-shift problems. We propose SpeechLMScore, an unsupervised metric to evaluate generated speech using a speech-language model. SpeechLMScore computes the average log-probability of a speech signal by mapping it into discrete tokens and measures the average probability of generating the sequence of tokens. Therefore, it does not require human annotation and is a highly scalable framework. Evaluation results demonstrate that the proposed metric shows a promising correlation with human evaluation scores on different speech generation tasks including voice conversion, text-to-speech, and speech enhancement.","url_abs":"https://arxiv.org/abs/2212.04559v1","url_pdf":"https://arxiv.org/pdf/2212.04559v1.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":"speechlmscore-evaluating-speech-generation","repo_url":"https://github.com/espnet/espnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"speechlmscore-evaluating-speech-generation","repo_url":"https://github.com/soumimaiti/speechlmscore_tool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-enhancement","task_name":"Speech Enhancement"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"voice-conversion","task_name":"Voice Conversion"},{"task_slug":"model","task_name":"model"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2212.04559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.04559"}},"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/espnet/espnet","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/soumimaiti/speechlmscore_tool","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"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":"4f4f6b69a51a9e11","entry":"make_pad_mask","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/lm.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/lm.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f4f6b69a51a9e11"}},{"code_sha256_prefix":"4f238f6c91b66b7c","entry":"PositionalEmbedding","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/positional_embedding.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/positional_embedding.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":"4f238f6c91b66b7c"}},{"code_sha256_prefix":"573578680483eda9","entry":"collate_fn","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/dataloader.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/dataloader.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":"573578680483eda9"}},{"code_sha256_prefix":"01de5335205a29e0","entry":"get_feat_iterator","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"02b_dump_km_label.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/02b_dump_km_label.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":"01de5335205a29e0"}},{"code_sha256_prefix":"dfadf5d8966e992b","entry":"get_path_iterator","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"02a_dump_feature.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/02a_dump_feature.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":"dfadf5d8966e992b"}},{"code_sha256_prefix":"1083345fb9bbfd17","entry":"get_path_iterator","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/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":"1083345fb9bbfd17"}},{"code_sha256_prefix":"9b8c24f2854343b2","entry":"get_shard_range","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/utils.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/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":"9b8c24f2854343b2"}},{"code_sha256_prefix":"acd7b647eaf5189c","entry":"make_positions","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/positional_embedding.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/positional_embedding.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":"acd7b647eaf5189c"}},{"code_sha256_prefix":"ce10a394eb6dd5f4","entry":"pad_list","repo":"soumimaiti/speechlmscore_tool","repo_kind":"listed","path":"utils/dataloader.py","file_url":"https://github.com/soumimaiti/speechlmscore_tool/blob/HEAD/utils/dataloader.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":"ce10a394eb6dd5f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}