{"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/mm-tts-a-unified-framework-for-multimodal","title":"UMETTS: A Unified Framework for Emotional Text-to-Speech Synthesis with Multimodal Prompts","arxiv_id":"2404.18398","date":"2024-04-29","proceeding":null,"authors":["Zhi-Qi Cheng","Xiang Li","Jun-Yan He","Junyao Chen","Xiaomao Fan","Xiaojiang Peng","Alexander G. Hauptmann"],"abstract":"Emotional Text-to-Speech (E-TTS) synthesis has garnered significant attention in recent years due to its potential to revolutionize human-computer interaction. However, current E-TTS approaches often struggle to capture the intricacies of human emotions, primarily relying on oversimplified emotional labels or single-modality input. In this paper, we introduce the Unified Multimodal Prompt-Induced Emotional Text-to-Speech System (UMETTS), a novel framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. The core of UMETTS consists of two key components: the Emotion Prompt Alignment Module (EP-Align) and the Emotion Embedding-Induced TTS Module (EMI-TTS). (1) EP-Align employs contrastive learning to align emotional features across text, audio, and visual modalities, ensuring a coherent fusion of multimodal information. (2) Subsequently, EMI-TTS integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions. Extensive evaluations show that UMETTS achieves significant improvements in emotion accuracy and speech naturalness, outperforming traditional E-TTS methods on both objective and subjective metrics.","url_abs":"https://arxiv.org/abs/2404.18398v2","url_pdf":"https://arxiv.org/pdf/2404.18398v2.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":"mm-tts-a-unified-framework-for-multimodal","repo_url":"https://github.com/kttrcdl/umetts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2404.18398","atlas_url":"https://app.syntology.ai/?focus=2404.18398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.18398"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kttrcdl/umetts","reach":{"status":"ok","spdx":"GPL-2.0"}}],"summary":{"ran_draft_wrong":2,"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":"83e2c862f7374ac7","entry":"dynamic_range_compression","repo":"kttrcdl/umetts","repo_kind":"official","path":"EMITTS/Tacotron2/audio_processing.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/EMITTS/Tacotron2/audio_processing.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"83e2c862f7374ac7"}},{"code_sha256_prefix":"9f9ec26d4cdfdf7d","entry":"griffin_lim","repo":"kttrcdl/umetts","repo_kind":"official","path":"EMITTS/Tacotron2/audio_processing.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/EMITTS/Tacotron2/audio_processing.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"9f9ec26d4cdfdf7d"}},{"code_sha256_prefix":"66434bc22f9de43f","entry":"load_filelist","repo":"kttrcdl/umetts","repo_kind":"official","path":"metrics/SECS_MCD.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/metrics/SECS_MCD.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"66434bc22f9de43f"}},{"code_sha256_prefix":"4847c6eea67eddf5","entry":"remove_empty_strings","repo":"kttrcdl/umetts","repo_kind":"official","path":"metrics/WER_CER.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/metrics/WER_CER.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"4847c6eea67eddf5"}},{"code_sha256_prefix":"f7bf9f0265e33cf0","entry":"apply_gradient_allreduce","repo":"kttrcdl/umetts","repo_kind":"official","path":"EMITTS/Tacotron2/distributed.py","file_url":"https://github.com/kttrcdl/umetts/blob/HEAD/EMITTS/Tacotron2/distributed.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"f7bf9f0265e33cf0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}