{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AOMELPD6UMSIFSCWMDTC3ZFMBJ","short_pith_number":"pith:AOMELPD6","schema_version":"1.0","canonical_sha256":"039845bc7ea32482c85660e62de4ac0a70c8816f027b9a928bec7debe640691d","source":{"kind":"arxiv","id":"2606.10231","version":1},"attestation_state":"computed","paper":{"title":"LLM can Read Spectrogram: Encoder-free Speech-Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Ren, Jinyu Li, Ruchao Fan, Xiaofei Wang, Yao Qian, Yiming Wang, Yufei Xia, Yuxuan Hu","submitted_at":"2026-06-08T22:44:04Z","abstract_excerpt":"Recent speech-aware large language models (Speech-LLMs) rely on a pre-trained speech encoder to convert audio into semantic-rich representations consumable by LLM. In this work, instead, we explore: can an LLM learn to read Mel spectrogram directly without a dedicated speech encoder? We propose Mel-LLM, an encoder-free Speech-LLM that feeds lightly pre-processed Mel spectrogram patches directly into the LLM through a linear projection, allowing the LLM to learn speech-text alignment purely through its own parameters. We conduct extensive experiments on both automatic speech recognition (ASR) a"},"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":"2606.10231","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T22:44:04Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"816f133c5a845f7dd2edd7029aa8cc0b8be0ae2a178a42a7c38b14ac2a7e9370","abstract_canon_sha256":"5cc51fc713113b1bb66e5a75605136180c087cb8ad0e222b58f00f091b4a6942"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:00.781191Z","signature_b64":"MLyHP1c7P1A5mAk0DsmzubB4Y1erGeXV2Jur93ryn/m8lPh8liG7mmFD9Fd/KplS5l0x1USXOaZUqkxpu30mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"039845bc7ea32482c85660e62de4ac0a70c8816f027b9a928bec7debe640691d","last_reissued_at":"2026-06-10T01:09:00.780338Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:00.780338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM can Read Spectrogram: Encoder-free Speech-Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Bo Ren, Jinyu Li, Ruchao Fan, Xiaofei Wang, Yao Qian, Yiming Wang, Yufei Xia, Yuxuan Hu","submitted_at":"2026-06-08T22:44:04Z","abstract_excerpt":"Recent speech-aware large language models (Speech-LLMs) rely on a pre-trained speech encoder to convert audio into semantic-rich representations consumable by LLM. In this work, instead, we explore: can an LLM learn to read Mel spectrogram directly without a dedicated speech encoder? We propose Mel-LLM, an encoder-free Speech-LLM that feeds lightly pre-processed Mel spectrogram patches directly into the LLM through a linear projection, allowing the LLM to learn speech-text alignment purely through its own parameters. We conduct extensive experiments on both automatic speech recognition (ASR) a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10231","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/2606.10231/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":"2606.10231","created_at":"2026-06-10T01:09:00.780483+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10231v1","created_at":"2026-06-10T01:09:00.780483+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10231","created_at":"2026-06-10T01:09:00.780483+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOMELPD6UMSI","created_at":"2026-06-10T01:09:00.780483+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOMELPD6UMSIFSCW","created_at":"2026-06-10T01:09:00.780483+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOMELPD6","created_at":"2026-06-10T01:09:00.780483+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ","json":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ.json","graph_json":"https://pith.science/api/pith-number/AOMELPD6UMSIFSCWMDTC3ZFMBJ/graph.json","events_json":"https://pith.science/api/pith-number/AOMELPD6UMSIFSCWMDTC3ZFMBJ/events.json","paper":"https://pith.science/paper/AOMELPD6"},"agent_actions":{"view_html":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ","download_json":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ.json","view_paper":"https://pith.science/paper/AOMELPD6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10231&json=true","fetch_graph":"https://pith.science/api/pith-number/AOMELPD6UMSIFSCWMDTC3ZFMBJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AOMELPD6UMSIFSCWMDTC3ZFMBJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ/action/storage_attestation","attest_author":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ/action/author_attestation","sign_citation":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ/action/citation_signature","submit_replication":"https://pith.science/pith/AOMELPD6UMSIFSCWMDTC3ZFMBJ/action/replication_record"}},"created_at":"2026-06-10T01:09:00.780483+00:00","updated_at":"2026-06-10T01:09:00.780483+00:00"}