{"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-speech-language-modeling-via-energy","title":"Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space","arxiv_id":"2505.13181","date":"2025-05-19","proceeding":null,"authors":["Zhengrui Ma","Yang Feng","Chenze Shao","Fandong Meng","Jie zhou","Min Zhang"],"abstract":"We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective. The energy distance offers an analytical measure of the distributional gap by contrasting simulated and target samples, enabling efficient training to capture the underlying continuous autoregressive distribution. By bypassing reliance on residual vector quantization, SLED avoids discretization errors and eliminates the need for the complicated hierarchical architectures common in existing speech language models. It simplifies the overall modeling pipeline while preserving the richness of speech information and maintaining inference efficiency. Empirical results demonstrate that SLED achieves strong performance in both zero-shot and streaming speech synthesis, showing its potential for broader applications in general-purpose speech language models.","url_abs":"https://arxiv.org/abs/2505.13181v1","url_pdf":"https://arxiv.org/pdf/2505.13181v1.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-speech-language-modeling-via-energy","repo_url":"https://github.com/ictnlp/sled-tts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.13181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13181"}},"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":"deterministic:regex_extraction","url":"https://github.com/ictnlp/SLED-TTS","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ictnlp/sled-tts","reach":null}],"summary":{"ran":3,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"dfd1ec7416f79939","entry":"ResBlock","repo":"ictnlp/sled-tts","repo_kind":"official","path":"sled/energy_distance.py","file_url":"https://github.com/ictnlp/sled-tts/blob/HEAD/sled/energy_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dfd1ec7416f79939"}},{"code_sha256_prefix":"75c9b26159424936","entry":"ScoreLossZ","repo":"ictnlp/sled-tts","repo_kind":"official","path":"sled/energy_distance.py","file_url":"https://github.com/ictnlp/sled-tts/blob/HEAD/sled/energy_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"75c9b26159424936"}},{"code_sha256_prefix":"d00381278dd56ab1","entry":"SimpleMLPAdaLN","repo":"ictnlp/sled-tts","repo_kind":"official","path":"sled/energy_distance.py","file_url":"https://github.com/ictnlp/sled-tts/blob/HEAD/sled/energy_distance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d00381278dd56ab1"}},{"code_sha256_prefix":"49367e0988e7be59","entry":"adjust_length_to_model","repo":"ictnlp/SLED-TTS","repo_kind":"official","path":"scripts/run_offline.py","file_url":"https://github.com/ictnlp/SLED-TTS/blob/HEAD/scripts/run_offline.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"49367e0988e7be59"}},{"code_sha256_prefix":"51f7f9c55bdc58b0","entry":"load_manifest","repo":"ictnlp/SLED-TTS","repo_kind":"official","path":"scripts/train_libriheavy.py","file_url":"https://github.com/ictnlp/SLED-TTS/blob/HEAD/scripts/train_libriheavy.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"51f7f9c55bdc58b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}