{"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/audio-linguistic-embeddings-for-spoken","title":"Audio-Linguistic Embeddings for Spoken Sentences","arxiv_id":"1902.07817","date":"2019-02-20","proceeding":null,"authors":["Albert Haque","Michelle Guo","Prateek Verma","Li Fei-Fei"],"abstract":"We propose spoken sentence embeddings which capture both acoustic and\nlinguistic content. While existing works operate at the character, phoneme, or\nword level, our method learns long-term dependencies by modeling speech at the\nsentence level. Formulated as an audio-linguistic multitask learning problem,\nour encoder-decoder model simultaneously reconstructs acoustic and natural\nlanguage features from audio. Our results show that spoken sentence embeddings\noutperform phoneme and word-level baselines on speech recognition and emotion\nrecognition tasks. Ablation studies show that our embeddings can better model\nhigh-level acoustic concepts while retaining linguistic content. Overall, our\nwork illustrates the viability of generic, multi-modal sentence embeddings for\nspoken language understanding.","url_abs":"http://arxiv.org/abs/1902.07817v1","url_pdf":"http://arxiv.org/pdf/1902.07817v1.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":"audio-linguistic-embeddings-for-spoken","repo_url":"https://github.com/awesomericky/Speech2Pickup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embeddings","task_name":"Sentence Embeddings"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07817","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}