{"id":962034,"date":"2023-08-13T17:10:42","date_gmt":"2023-08-14T00:10:42","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&#038;p=962034"},"modified":"2023-08-13T18:03:40","modified_gmt":"2023-08-14T01:03:40","slug":"speechx-neural-codec-language-model-as-a-versatile-speech-transformer","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/speechx-neural-codec-language-model-as-a-versatile-speech-transformer\/","title":{"rendered":"SpeechX: Neural Codec Language Model as a Versatile Speech Transformer"},"content":{"rendered":"<p>Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot TTS and various speech transformation tasks, dealing with both clean and noisy signals. SpeechX combines neural codec language modeling with multi-task learning using task-dependent prompting, enabling unified and extensible modeling and providing a consistent way for leveraging textual input in speech enhancement and transformation tasks. Experimental results show SpeechX&#8217;s efficacy in various tasks, including zero-shot TTS, noise suppression, target speaker extraction, speech removal, and speech editing with or without background noise, achieving comparable or superior performance to specialized models across tasks. See <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"https:\/\/aka.ms\/speechx\">https:\/\/aka.ms\/speechx<span class=\"sr-only\"> (opens in new tab)<\/span><\/a> for demo samples.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Recent advancements in generative speech models based on audio-text prompts have enabled remarkable innovations like high-quality zero-shot text-to-speech. However, existing models still face limitations in handling diverse audio-text speech generation tasks involving transforming input speech and processing audio captured in adverse acoustic conditions. This paper introduces SpeechX, a versatile speech generation model capable of zero-shot [&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":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,243062,13545],"msr-publication-type":[193715],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-962034","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-audio-acoustics","msr-research-area-human-language-technologies","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2023-8-13","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":"","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":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/08\/Audio_Transformation__X_-64d97d5dab99b.pdf","id":"962067","title":"audio_transformation__x_-64d97d5dab99b","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":962067,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/08\/Audio_Transformation__X_-64d97d5dab99b.pdf"},{"id":962037,"url":"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2023\/08\/Audio_Transformation__X_.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Xiaofei Wang","user_id":38658,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xiaofei Wang"},{"type":"user_nicename","value":"Manthan Thakker","user_id":39627,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Manthan Thakker"},{"type":"user_nicename","value":"Zhuo Chen","user_id":38589,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Zhuo Chen"},{"type":"user_nicename","value":"Naoyuki Kanda","user_id":38661,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Naoyuki Kanda"},{"type":"edited_text","value":"Sefik Emre Eskimez","user_id":38655,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Sefik Emre Eskimez"},{"type":"text","value":"Sanyuan Chen","user_id":0,"rest_url":false},{"type":"text","value":"Min Tang","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Shujie Liu","user_id":33634,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Shujie Liu"},{"type":"user_nicename","value":"Jinyu Li","user_id":32312,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Jinyu Li"},{"type":"user_nicename","value":"Takuya Yoshioka","user_id":36278,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Takuya Yoshioka"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"article","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/962034"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":4,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/962034\/revisions"}],"predecessor-version":[{"id":962070,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/962034\/revisions\/962070"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=962034"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=962034"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=962034"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=962034"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=962034"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=962034"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=962034"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=962034"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=962034"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=962034"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=962034"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=962034"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=962034"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=962034"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=962034"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=962034"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}