{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TFF6HTQ3APGXBCCR5RFK5LS2MX","short_pith_number":"pith:TFF6HTQ3","schema_version":"1.0","canonical_sha256":"994be3ce1b03cd708851ec4aaeae5a65c383fae8181db648e1405f78fd01edb3","source":{"kind":"arxiv","id":"2309.10294","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qian Chen, Shiliang Zhang, Wen Wu, Xie Chen, Yiwei Guo, Zhisheng Zheng, Ziyang Ma","submitted_at":"2023-09-19T03:52:01Z","abstract_excerpt":"In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS. First, we investigated the representation ability of different speech self-supervised pre-trained models, and we found that data2vec has a good representation ability on the SER task. Second, we employed a powerful large language model (LLM), GPT-4, and emotional text-to-speech (TTS) model, Azure TTS, to generate emotionally congruent text and speech. We carefully designed the te"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2309.10294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T03:52:01Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"f6b68eaaa360f6e260764edc5621b44a98bb0a2ff2dab9f245ad6adc0d32363c","abstract_canon_sha256":"e82cfc0ce7c16cc0cd4601311af4b488c237854d7a7337c18a41567b2eb2e19e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:33.494163Z","signature_b64":"7gvW8GcbwRoShKQobzBdZnYz8bqreQx7Ck9l6A70hvHut9nH8nN9UukgNmdT6WgbgoJZL0m3KP1P1/XiM/UFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"994be3ce1b03cd708851ec4aaeae5a65c383fae8181db648e1405f78fd01edb3","last_reissued_at":"2026-07-05T09:25:33.493757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:33.493757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Qian Chen, Shiliang Zhang, Wen Wu, Xie Chen, Yiwei Guo, Zhisheng Zheng, Ziyang Ma","submitted_at":"2023-09-19T03:52:01Z","abstract_excerpt":"In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS. First, we investigated the representation ability of different speech self-supervised pre-trained models, and we found that data2vec has a good representation ability on the SER task. Second, we employed a powerful large language model (LLM), GPT-4, and emotional text-to-speech (TTS) model, Azure TTS, to generate emotionally congruent text and speech. We carefully designed the te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10294","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.10294/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2309.10294","created_at":"2026-07-05T09:25:33.493809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.10294v1","created_at":"2026-07-05T09:25:33.493809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10294","created_at":"2026-07-05T09:25:33.493809+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFF6HTQ3APGX","created_at":"2026-07-05T09:25:33.493809+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFF6HTQ3APGXBCCR","created_at":"2026-07-05T09:25:33.493809+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFF6HTQ3","created_at":"2026-07-05T09:25:33.493809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.01728","citing_title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","ref_index":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX","json":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX.json","graph_json":"https://pith.science/api/pith-number/TFF6HTQ3APGXBCCR5RFK5LS2MX/graph.json","events_json":"https://pith.science/api/pith-number/TFF6HTQ3APGXBCCR5RFK5LS2MX/events.json","paper":"https://pith.science/paper/TFF6HTQ3"},"agent_actions":{"view_html":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX","download_json":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX.json","view_paper":"https://pith.science/paper/TFF6HTQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.10294&json=true","fetch_graph":"https://pith.science/api/pith-number/TFF6HTQ3APGXBCCR5RFK5LS2MX/graph.json","fetch_events":"https://pith.science/api/pith-number/TFF6HTQ3APGXBCCR5RFK5LS2MX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX/action/storage_attestation","attest_author":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX/action/author_attestation","sign_citation":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX/action/citation_signature","submit_replication":"https://pith.science/pith/TFF6HTQ3APGXBCCR5RFK5LS2MX/action/replication_record"}},"created_at":"2026-07-05T09:25:33.493809+00:00","updated_at":"2026-07-05T09:25:33.493809+00:00"}