{"id":1169877,"date":"2026-04-27T11:16:58","date_gmt":"2026-04-27T18:16:58","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/slm-s2st-a-multimodal-language-model-for-direct-speech-to-speech-translation\/"},"modified":"2026-05-04T09:50:54","modified_gmt":"2026-05-04T16:50:54","slug":"slm-s2st-a-multimodal-language-model-for-direct-speech-to-speech-translation","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/slm-s2st-a-multimodal-language-model-for-direct-speech-to-speech-translation\/","title":{"rendered":"SLM-S2ST: A multimodal language model for direct speech-to-speech translation"},"content":{"rendered":"<p>Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In this paper, we present SLM-S2ST, a multimodal LM for direct speech-to-speech translation (S2ST), built on the opensource Phi4-MM model. SLM-S2ST extends its predecessor by generating translated speech using an audio transformer head that predicts audio tokens with a delay relative to text tokens, followed by a streaming vocoder for waveform synthesis. Our experimental results on the CVSS-C dataset demonstrate SLMS2ST\u2019s superior performance, significantly surpassing existing baseline models trained on the same dataset. Furthermore, when we scale up the training data and the model size, SLM-S2ST reaches on-par performance with the current SOTA model.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Speech-aware language models (LMs) have demonstrated capabilities in understanding spoken language while generating text-based responses. However, enabling them to produce speech output efficiently and effectively remains a challenge. In this paper, we present SLM-S2ST, a multimodal LM for direct speech-to-speech translation (S2ST), built on the opensource Phi4-MM model. SLM-S2ST extends its predecessor by generating translated [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":null,"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"arXiv","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":"","msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2025-06-04","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":false,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"ca67459a1fc7da9e408aaa122e0f2f8d7701a433"},{"provider":"doi","id":"10.1109\/ASRU65441.2025.11434639"},{"provider":"arxiv","id":"2506.04392"}],"msr_hide_image_in_river":null,"footnotes":""},"msr-research-highlight":[],"research-area":[243062,13545],"msr-publication-type":[193724],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[264253,248026],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1169877","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-audio-acoustics","msr-research-area-human-language-technologies","msr-locale-en_us","msr-field-of-study-audio-and-speech-processing","msr-field-of-study-engineering"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2025-06-04","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"arXiv","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"doi","viewUrl":"false","id":"false","title":"https:\/\/doi.org\/10.1109\/ASRU65441.2025.11434639","label_id":"243106","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2506.04392","label_id":"243109","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"name","value":"Yuxuan Hu","user_id":0,"rest_url":false},{"type":"name","value":"Haibin Wu","user_id":0,"rest_url":false},{"type":"name","value":"Ruchao Fan","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Xiaofei Wang","user_id":38658,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xiaofei Wang"},{"type":"name","value":"Heng Lu","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Yao Qian","user_id":34976,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Yao Qian"},{"type":"name","value":"Jinyu Li","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"miscellaneous","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1169877","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1169877\/revisions"}],"predecessor-version":[{"id":1170581,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1169877\/revisions\/1170581"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1169877"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1169877"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1169877"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1169877"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1169877"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1169877"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1169877"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1169877"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1169877"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1169877"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1169877"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1169877"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1169877"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}