{"task":"Language Modelling","dataset":"SALMon","metric_names":["Sentiment Consistency","Speaker Consistency","Gender Consistency","Background (Domain) Consistency","Background (Random) Consistency","Room Consistency","Sentiment Alignment","Background Alignment"],"rows":[{"id":33760,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"Spirit-LM (Expr.)","metrics":{"Background (Domain) Consistency":"55.0","Background (Random) Consistency":"64.0","Background Alignment":"59.5","Gender Consistency":"85.0","Room Consistency":"54.5","Sentiment Alignment":"52.0","Sentiment Consistency":"73.5","Speaker Consistency":"81.0"},"paper_url":"https://arxiv.org/abs/2402.05755v2","paper_title":"Spirit LM: Interleaved Spoken and Written Language Model","paper_date":"2024-02-08","code_links":[{"title":"facebookresearch/spiritlm","url":"https://github.com/facebookresearch/spiritlm"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33761,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"LAST 1.3B","metrics":{"Background (Domain) Consistency":"56.0","Background (Random) Consistency":"61.0","Background Alignment":"53.0","Gender Consistency":"68.5","Room Consistency":"62.5","Sentiment Alignment":"53.5","Sentiment Consistency":"65.0","Speaker Consistency":"64.5"},"paper_url":"https://arxiv.org/abs/2409.03701v2","paper_title":"LAST: Language Model Aware Speech Tokenization","paper_date":"2024-09-05","code_links":[],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33762,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"LAST 350M","metrics":{"Background (Domain) Consistency":"55.5","Background (Random) Consistency":"60.5","Background Alignment":"54.5","Gender Consistency":"70.5","Room Consistency":"61.0","Sentiment Alignment":"51.5","Sentiment Consistency":"64.0","Speaker Consistency":"63.0"},"paper_url":"https://arxiv.org/abs/2409.03701v2","paper_title":"LAST: Language Model Aware Speech Tokenization","paper_date":"2024-09-05","code_links":[],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33763,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"TWIST 7B","metrics":{"Background (Domain) Consistency":"55.0","Background (Random) Consistency":"60.5","Background Alignment":"54.5","Gender Consistency":"70.0","Room Consistency":"62.0","Sentiment Alignment":"51.5","Sentiment Consistency":"61.5","Speaker Consistency":"71.0"},"paper_url":"https://arxiv.org/abs/2305.13009v3","paper_title":"Textually Pretrained Speech Language Models","paper_date":"2023-05-22","code_links":[{"title":"slp-rl/spokenstorycloze","url":"https://github.com/slp-rl/spokenstorycloze"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33764,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"TWIST 1.3B","metrics":{"Background (Domain) Consistency":"55.5","Background (Random) Consistency":"60.5","Background Alignment":"56.5","Gender Consistency":"69.5","Room Consistency":"59.0","Sentiment Alignment":"53.0","Sentiment Consistency":"61.5","Speaker Consistency":"69.0"},"paper_url":"https://arxiv.org/abs/2305.13009v3","paper_title":"Textually Pretrained Speech Language Models","paper_date":"2023-05-22","code_links":[{"title":"slp-rl/spokenstorycloze","url":"https://github.com/slp-rl/spokenstorycloze"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33765,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"TWIST 350M","metrics":{"Background (Domain) Consistency":"54.0","Background (Random) Consistency":"61.5","Background Alignment":"56.5","Gender Consistency":"68.0","Room Consistency":"59.0","Sentiment Alignment":"51.5","Sentiment Consistency":"59.0","Speaker Consistency":"69.5"},"paper_url":"https://arxiv.org/abs/2305.13009v3","paper_title":"Textually Pretrained Speech Language Models","paper_date":"2023-05-22","code_links":[{"title":"slp-rl/spokenstorycloze","url":"https://github.com/slp-rl/spokenstorycloze"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33766,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"TASLM 1B (token)","metrics":{"Gender Consistency":"70.5","Room Consistency":"61.0","Sentiment Consistency":"59.0","Speaker Consistency":"68.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33767,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"TASLM 1B (embedding)","metrics":{"Gender Consistency":"75.5","Room Consistency":"50.0","Sentiment Consistency":"57.5","Speaker Consistency":"67.0"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":0,"source":"archive","tags":[]},{"id":33768,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"Spirit-LM (base)","metrics":{"Background (Domain) Consistency":"53.5","Background (Random) Consistency":"55.5","Background Alignment":"51.5","Gender Consistency":"67.0","Room Consistency":"54.5","Sentiment Alignment":"48.0","Sentiment Consistency":"54.5","Speaker Consistency":"69.5"},"paper_url":"https://arxiv.org/abs/2402.05755v2","paper_title":"Spirit LM: Interleaved Spoken and Written Language Model","paper_date":"2024-02-08","code_links":[{"title":"facebookresearch/spiritlm","url":"https://github.com/facebookresearch/spiritlm"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]},{"id":33769,"task":"Language Modelling","parent_task":null,"dataset":"SALMon","model_name":"pGSLM","metrics":{"Background (Domain) Consistency":"57.0","Background (Random) Consistency":"66.0","Background Alignment":"53.5","Gender Consistency":"88.5","Room Consistency":"53.5","Sentiment Alignment":"55.5","Sentiment Consistency":"40.5","Speaker Consistency":"83.0"},"paper_url":"https://arxiv.org/abs/2109.03264v2","paper_title":"Text-Free Prosody-Aware Generative Spoken Language Modeling","paper_date":"2021-09-07","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq"}],"metrics_order":"[\"Sentiment Consistency\", \"Speaker Consistency\", \"Gender Consistency\", \"Background (Domain) Consistency\", \"Background (Random) Consistency\", \"Room Consistency\", \"Sentiment Alignment\", \"Background Alignment\"]","area":"Medical","uses_additional_data":1,"source":"archive","tags":[]}]}