{"id":"https://openalex.org/W3198526264","doi":"https://doi.org/10.21437/interspeech.2021-733","title":"SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction","display_name":"SpecRec: An Alternative Solution for Improving End-to-End Speech-to-Text Translation via Spectrogram Reconstruction","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3198526264","doi":"https://doi.org/10.21437/interspeech.2021-733","mag":"3198526264"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034556928","display_name":"Junkun Chen","orcid":"https://orcid.org/0000-0003-0193-238X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junkun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009311991","display_name":"Mingbo Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingbo Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034431550","display_name":"Renjie Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Renjie Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101440599","display_name":"Liang Huang","orcid":"https://orcid.org/0009-0007-5846-849X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2232","last_page":"2236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8658699989318848},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.7371060252189636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.655249834060669},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6509696841239929},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6049414873123169},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5987329483032227},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41541799902915955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3747757077217102},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.32498854398727417},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.055265218019485474}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8658699989318848},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.7371060252189636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.655249834060669},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6509696841239929},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6049414873123169},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5987329483032227},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41541799902915955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3747757077217102},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.32498854398727417},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.055265218019485474},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2021-733","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-733","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1537859740","https://openalex.org/W2113106066","https://openalex.org/W2134546430","https://openalex.org/W2252212004","https://openalex.org/W2466918907","https://openalex.org/W2605131327","https://openalex.org/W2747874407","https://openalex.org/W2766219058","https://openalex.org/W2936774411","https://openalex.org/W2949328740","https://openalex.org/W2953356739","https://openalex.org/W2963250244","https://openalex.org/W2963779652","https://openalex.org/W2964102148","https://openalex.org/W2964172053","https://openalex.org/W2965373594","https://openalex.org/W2972448360","https://openalex.org/W2973048981","https://openalex.org/W2992632249","https://openalex.org/W2997436923","https://openalex.org/W3006988520","https://openalex.org/W3011411500","https://openalex.org/W3093218022"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W2728761353","https://openalex.org/W2883671469","https://openalex.org/W3007142233","https://openalex.org/W3037186962","https://openalex.org/W3177132412","https://openalex.org/W2989819126","https://openalex.org/W4372260133","https://openalex.org/W3097787369"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}