{"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/esc-efficient-speech-coding-with-cross-scale","title":"ESC: Efficient Speech Coding with Cross-Scale Residual Vector Quantized Transformers","arxiv_id":"2404.19441","date":"2024-04-30","proceeding":null,"authors":["Yuzhe Gu","Enmao Diao"],"abstract":"Neural speech codecs aim to compress input signals into minimal bits while maintaining content quality in a low-latency manner. However, existing neural codecs often trade model complexity for reconstruction performance. These codecs primarily use convolutional blocks for feature transformation, which are not inherently suited for capturing the local redundancies in speech signals. To compensate, they require either adversarial discriminators or a large number of model parameters to enhance audio quality. In response to these challenges, we introduce the Efficient Speech Codec (ESC), a lightweight, parameter-efficient speech codec based on a cross-scale residual vector quantization scheme and transformers. Our model employs mirrored hierarchical window transformer blocks and performs step-wise decoding from coarse-to-fine feature representations. To enhance bitrate efficiency, we propose a novel combination of vector quantization techniques along with a pre-training paradigm. Extensive experiments demonstrate that ESC can achieve high-fidelity speech reconstruction with significantly lower model complexity, making it a promising alternative to existing convolutional audio codecs.","url_abs":"https://arxiv.org/abs/2404.19441v3","url_pdf":"https://arxiv.org/pdf/2404.19441v3.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"esc-efficient-speech-coding-with-cross-scale","repo_url":"https://github.com/yzguu830/efficient-speech-codec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.19441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19441"}},"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/yzGuu830/efficient-speech-codec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_fixture":1,"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":"0da6c85b36d54ca4","entry":"count_posterior","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/vq/codebook.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/vq/codebook.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":"0da6c85b36d54ca4"}},{"code_sha256_prefix":"f43d35e5fa5d55bf","entry":"pixel_shuffle","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/transformer/scale.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/transformer/scale.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":"f43d35e5fa5d55bf"}},{"code_sha256_prefix":"c45f32bde30f9fe2","entry":"pixel_unshuffle","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/transformer/scale.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/transformer/scale.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":"c45f32bde30f9fe2"}},{"code_sha256_prefix":"3b49a4d4fa33e8e3","entry":"sample_centroids","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/vq/initialize.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/vq/initialize.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":"3b49a4d4fa33e8e3"}},{"code_sha256_prefix":"f6b2d702fc756d64","entry":"window_partition","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/transformer/attention.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/transformer/attention.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b2d702fc756d64"}},{"code_sha256_prefix":"7b0d02f75bf6b439","entry":"window_reverse","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/transformer/attention.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/transformer/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b0d02f75bf6b439"}},{"code_sha256_prefix":"961d5f363d255b19","entry":"blk_func","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/models/utils.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/models/utils.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":"961d5f363d255b19"}},{"code_sha256_prefix":"62cd4c085351a362","entry":"power_law","repo":"yzGuu830/efficient-speech-codec","repo_kind":"official","path":"esc/modules/loss/generator_loss.py","file_url":"https://github.com/yzGuu830/efficient-speech-codec/blob/HEAD/esc/modules/loss/generator_loss.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":"62cd4c085351a362"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}