{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/speech-slytherin-examining-the-performance","title":"Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis","arxiv_id":"2407.09732","date":"2024-07-13","proceeding":null,"authors":["Xilin Jiang","Yinghao Aaron Li","Adrian Nicolas Florea","Cong Han","Nima Mesgarani"],"abstract":"It is too early to conclude that Mamba is a better alternative to transformers for speech before comparing Mamba with transformers in terms of both performance and efficiency in multiple speech-related tasks. To reach this conclusion, we propose and evaluate three models for three tasks: Mamba-TasNet for speech separation, ConMamba for speech recognition, and VALL-M for speech synthesis. We compare them with transformers of similar sizes in performance, memory, and speed. Our Mamba or Mamba-transformer hybrid models show comparable or higher performance than their transformer counterparts: Sepformer, Conformer, and VALL-E. They are more efficient than transformers in memory and speed for speech longer than a threshold duration, inversely related to the resolution of a speech token. Mamba for separation is the most efficient, and Mamba for recognition is the least. Further, we show that Mamba is not more efficient than transformer for speech shorter than the threshold duration and performs worse in models that require joint modeling of text and speech, such as cross or masked attention of two inputs. Therefore, we argue that the superiority of Mamba or transformer depends on particular problems and models. Code available at https://github.com/xi-j/Mamba-TasNet and https://github.com/xi-j/Mamba-ASR.","url_abs":"https://arxiv.org/abs/2407.09732v1","url_pdf":"https://arxiv.org/pdf/2407.09732v1.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":"speech-slytherin-examining-the-performance","repo_url":"https://github.com/xi-j/mamba-asr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"speech-slytherin-examining-the-performance","repo_url":"https://github.com/xi-j/Mamba-TasNet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"speech-slytherin-examining-the-performance","repo_url":"https://github.com/areffarhadi/mamba-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"speech-slytherin-examining-the-performance","repo_url":"https://github.com/khfs/DuplexMamba","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-separation","task_name":"Speech Separation"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.09732","atlas_url":"https://app.syntology.ai/?focus=2407.09732","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.09732"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.09732\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.09732"},"call":"get_concepts_for_paper(arxiv_id=\"2407.09732\")"}],"by_repo":[{"repo":"xi-j/mamba-asr","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"xi-j/Mamba-TasNet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.18257"],"harvested_for_calls":[{"arxiv_id":"2403.18257","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.18257"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.18257\")"}]},{"repo":"areffarhadi/mamba-asr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"khfs/DuplexMamba","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bc8346c02749cab4f629628ae6cb77a689c2314fc357ad50ffd0ac6a669ce7cb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}