Get quick answers to your questions about the article from our AI researcher chatbot
{'id': 'https://openalex.org/W2067459736', 'doi': 'https://doi.org/10.1002/ecjb.10119', 'title': 'Model‐based speaker normalization methods for speech recognition', 'display_name': 'Model‐based speaker normalization methods for speech recognition', 'publication_year': 2003, 'publication_date': '2003-01-15', 'ids': {'openalex': 'https://openalex.org/W2067459736', 'doi': 'https://doi.org/10.1002/ecjb.10119', 'mag': '2067459736'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1002/ecjb.10119', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4210198954', 'display_name': 'Electronics and Communications in Japan (Part II Electronics)', 'issn_l': '1520-6432', 'issn': ['1520-6432', '8756-663X'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320595', 'host_organization_name': 'Wiley', 'host_organization_lineage': ['https://openalex.org/P4310320595'], 'host_organization_lineage_names': ['Wiley'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'article', 'type_crossref': 'journal-article', 'indexed_in': ['crossref'], 'open_access': {'is_oa': False, 'oa_status': 'closed', 'oa_url': None, 'any_repository_has_fulltext': False}, 'authorships': [{'author_position': 'first', 'author': {'id': 'https://openalex.org/A5013227099', 'display_name': 'Masaki Naito', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I4210104143', 'display_name': 'Advanced Telecommunications Research Institute International', 'ror': 'https://ror.org/01pe1d703', 'country_code': 'JP', 'type': 'facility', 'lineage': ['https://openalex.org/I4210104143']}], 'countries': ['JP'], 'is_corresponding': False, 'raw_author_name': 'Masaki Naito', 'raw_affiliation_strings': ['ATR Interpreting Telecommunications Research Laboratories, Kyoto, 619‐0237 Japan'], 'affiliations': [{'raw_affiliation_string': 'ATR Interpreting Telecommunications Research Laboratories, Kyoto, 619‐0237 Japan', 'institution_ids': ['https://openalex.org/I4210104143']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5100671326', 'display_name': 'Li Deng', 'orcid': 'https://orcid.org/0000-0002-7140-0701'}, 'institutions': [{'id': 'https://openalex.org/I151746483', 'display_name': 'University of Waterloo', 'ror': 'https://ror.org/01aff2v68', 'country_code': 'CA', 'type': 'education', 'lineage': ['https://openalex.org/I151746483']}], 'countries': ['CA'], 'is_corresponding': False, 'raw_author_name': 'Li Deng', 'raw_affiliation_strings': ['Department of Electrical and Computer Engineering, Waterloo University, Waterloo, Ontario, N2L 3G1 Canada'], 'affiliations': [{'raw_affiliation_string': 'Department of Electrical and Computer Engineering, Waterloo University, Waterloo, Ontario, N2L 3G1 Canada', 'institution_ids': ['https://openalex.org/I151746483']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5045034259', 'display_name': 'Yoshinori Sagisaka', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I4210104143', 'display_name': 'Advanced Telecommunications Research Institute International', 'ror': 'https://ror.org/01pe1d703', 'country_code': 'JP', 'type': 'facility', 'lineage': ['https://openalex.org/I4210104143']}], 'countries': ['JP'], 'is_corresponding': False, 'raw_author_name': 'Yoshinori Sagisaka', 'raw_affiliation_strings': ['ATR Interpreting Telecommunications Research Laboratories, Kyoto, 619‐0237 Japan'], 'affiliations': [{'raw_affiliation_string': 'ATR Interpreting Telecommunications Research Laboratories, Kyoto, 619‐0237 Japan', 'institution_ids': ['https://openalex.org/I4210104143']}]}], 'countries_distinct_count': 2, 'institutions_distinct_count': 2, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 0.0, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 1, 'citation_normalized_percentile': {'value': 0.432753, 'is_in_top_1_percent': False, 'is_in_top_10_percent': False}, 'cited_by_percentile_year': {'min': 59, 'max': 67}, 'biblio': {'volume': '86', 'issue': '2', 'first_page': '45', 'last_page': '56'}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T10860', 'display_name': 'Speech Enhancement Techniques', 'score': 0.9995, 'subfield': {'id': 'https://openalex.org/subfields/1711', 'display_name': 'Signal Processing'}, '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/T10860', 'display_name': 'Speech Enhancement Techniques', 'score': 0.9995, 'subfield': {'id': 'https://openalex.org/subfields/1711', 'display_name': 'Signal Processing'}, '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 Technology', 'score': 0.9995, '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/T11309', 'display_name': 'Audio Signal Classification and Analysis', 'score': 0.9935, 'subfield': {'id': 'https://openalex.org/subfields/1711', 'display_name': 'Signal Processing'}, '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/vocal-tract', 'display_name': 'Vocal tract', 'score': 0.9219708}, {'id': 'https://openalex.org/keywords/normalization', 'display_name': 'Normalization (sociology)', 'score': 0.877395}, {'id': 'https://openalex.org/keywords/speaker-verification', 'display_name': 'Speaker Verification', 'score': 0.622915}, {'id': 'https://openalex.org/keywords/speaker-diarization', 'display_name': 'Speaker Diarization', 'score': 0.621476}, {'id': 'https://openalex.org/keywords/acoustic-modeling', 'display_name': 'Acoustic Modeling', 'score': 0.594986}, {'id': 'https://openalex.org/keywords/speech-enhancement', 'display_name': 'Speech Enhancement', 'score': 0.592872}, {'id': 'https://openalex.org/keywords/automatic-speech-recognition', 'display_name': 'Automatic Speech Recognition', 'score': 0.58312}, {'id': 'https://openalex.org/keywords/smoothing', 'display_name': 'Smoothing', 'score': 0.5602515}, {'id': 'https://openalex.org/keywords/speaker-diarisation', 'display_name': 'Speaker diarisation', 'score': 0.5501037}, {'id': 'https://openalex.org/keywords/image-warping', 'display_name': 'Image warping', 'score': 0.46057224}], 'concepts': [{'id': 'https://openalex.org/C47401133', 'wikidata': 'https://www.wikidata.org/wiki/Q748953', 'display_name': 'Vocal tract', 'level': 2, 'score': 0.9219708}, {'id': 'https://openalex.org/C158215666', 'wikidata': 'https://www.wikidata.org/wiki/Q1414685', 'display_name': 'Formant', 'level': 3, 'score': 0.87802947}, {'id': 'https://openalex.org/C136886441', 'wikidata': 'https://www.wikidata.org/wiki/Q926129', 'display_name': 'Normalization (sociology)', 'level': 2, 'score': 0.877395}, {'id': 'https://openalex.org/C28490314', 'wikidata': 'https://www.wikidata.org/wiki/Q189436', 'display_name': 'Speech recognition', 'level': 1, 'score': 0.84333724}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.6266509}, {'id': 'https://openalex.org/C133892786', 'wikidata': 'https://www.wikidata.org/wiki/Q1145189', 'display_name': 'Speaker recognition', 'level': 2, 'score': 0.5954769}, {'id': 'https://openalex.org/C3770464', 'wikidata': 'https://www.wikidata.org/wiki/Q775963', 'display_name': 'Smoothing', 'level': 2, 'score': 0.5602515}, {'id': 'https://openalex.org/C149838564', 'wikidata': 'https://www.wikidata.org/wiki/Q7574248', 'display_name': 'Speaker diarisation', 'level': 3, 'score': 0.5501037}, {'id': 'https://openalex.org/C157202957', 'wikidata': 'https://www.wikidata.org/wiki/Q1659609', 'display_name': 'Image warping', 'level': 2, 'score': 0.46057224}, {'id': 'https://openalex.org/C153180895', 'wikidata': 'https://www.wikidata.org/wiki/Q7148389', 'display_name': 'Pattern recognition (psychology)', 'level': 2, 'score': 0.42403206}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.3055148}, {'id': 'https://openalex.org/C31972630', 'wikidata': 'https://www.wikidata.org/wiki/Q844240', 'display_name': 'Computer vision', 'level': 1, 'score': 0.07522559}, {'id': 'https://openalex.org/C2779581591', 'wikidata': 'https://www.wikidata.org/wiki/Q36244', 'display_name': 'Vowel', 'level': 2, 'score': 0.0}, {'id': 'https://openalex.org/C144024400', 'wikidata': 'https://www.wikidata.org/wiki/Q21201', 'display_name': 'Sociology', 'level': 0, 'score': 0.0}, {'id': 'https://openalex.org/C19165224', 'wikidata': 'https://www.wikidata.org/wiki/Q23404', 'display_name': 'Anthropology', 'level': 1, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1002/ecjb.10119', 'pdf_url': None, 'source': {'id': 'https://openalex.org/S4210198954', 'display_name': 'Electronics and Communications in Japan (Part II Electronics)', 'issn_l': '1520-6432', 'issn': ['1520-6432', '8756-663X'], 'is_oa': False, 'is_in_doaj': False, 'is_core': True, 'host_organization': 'https://openalex.org/P4310320595', 'host_organization_name': 'Wiley', 'host_organization_lineage': ['https://openalex.org/P4310320595'], 'host_organization_lineage_names': ['Wiley'], 'type': 'journal'}, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': None, 'sustainable_development_goals': [{'score': 0.58, 'id': 'https://metadata.un.org/sdg/5', 'display_name': 'Gender equality'}], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 7, 'referenced_works': ['https://openalex.org/W2045007407', 'https://openalex.org/W2068970468', 'https://openalex.org/W2104663520', 'https://openalex.org/W2140567543', 'https://openalex.org/W2157590573', 'https://openalex.org/W2165871906', 'https://openalex.org/W357399442'], 'related_works': ['https://openalex.org/W4254341835', 'https://openalex.org/W2894697037', 'https://openalex.org/W2131046383', 'https://openalex.org/W2086580720', 'https://openalex.org/W2061217898', 'https://openalex.org/W2046073792', 'https://openalex.org/W2045900265', 'https://openalex.org/W2001425423', 'https://openalex.org/W1909584822', 'https://openalex.org/W1748856376'], 'abstract_inverted_index': {'Abstract': [0], 'A': [1], 'speaker': [2, 17, 63, 162, 178], 'normalization': [3, 94, 146], 'method': [4, 135, 155], 'using': [5, 114, 123, 170, 180], 'a': [6, 20, 47, 124, 181], 'speech': [7, 84, 98, 104], 'generation': [8], 'model': [9, 45, 126], 'is': [10, 34, 99, 127, 147, 156], 'proposed': [11, 134, 154, 192], 'in': [12, 106, 132, 209], 'order': [13], 'to': [14, 141, 159], 'achieve': [15], 'high‐performance': [16, 177], 'adaptation': [18, 24, 163, 179, 185], 'with': [19, 51], 'small': [21, 182], 'amount': [22, 183], 'of': [23, 46, 55, 59, 70, 83, 95, 143, 152, 161, 184], 'data.': [25], 'The': [26, 73, 149], 'speaker‐': [27], 'and': [28, 93, 136], 'phoneme‐dependent': [29], 'vocal': [30], 'tract': [31], 'area': [32, 39, 89], 'function': [33, 40], 'approximated': [35], 'by': [36, 42, 101, 129, 164, 190], 'the': [37, 43, 56, 60, 67, 80, 87, 96, 103, 107, 120, 133, 153, 191], 'corresponding': [38], 'produced': [41], 'articulatory': [44], 'standard': [48], 'speaker,': [49], 'combined': [50], 'phoneme‐independent': [52], 'feature': [53], 'quantities': [54], 'vocal‐tract': [57, 88, 144], 'shape': [58], 'normalized': [61], 'target': [62], 'as': [64], 'estimated': [65], 'from': [66, 79, 86], 'formant': [68, 81], 'frequencies': [69, 82], 'two': [71], 'vowels.': [72], 'frequency': [74], 'warping': [75], 'functions': [76, 90], 'are': [77], 'determined': [78], 'calculated': [85], 'thus': [91], 'obtained,': [92], 'uttered': [97], 'performed': [100], 'stretching': [102], 'spectrum': [105], 'frequency‐axis': [108], 'direction.': [109], 'Continuous': [110], 'phoneme': [111, 115], 'recognition': [112, 121, 138, 150], 'experiments': [113], 'connection': [116], 'rules': [117], 'show': [118], 'that': [119, 137, 142, 160, 176], 'error': [122], 'gender‐dependent': [125], 'reduced': [128], 'about': [130], '30%': [131], 'performance': [139, 151], 'superior': [140], 'length': [145], 'obtained.': [148], 'also': [157], 'equivalent': [158], 'moving': [165], 'vector': [166], 'field': [167], 'smoothing': [168], '(VFS)': [169], '10': [171], 'phonetically': [172], 'balanced': [173], 'sentences,': [174], 'showing': [175], 'data': [186], 'can': [187], 'be': [188], 'achieved': [189], 'method.': [193], '©': [194], '2003': [195], 'Wiley': [196, 210], 'Periodicals,': [197], 'Inc.': [198], 'Electron': [199], 'Comm': [200], 'Jpn': [201], 'Pt': [202], '2,': [203], '86(2):': [204], '45–56,': [205], '2003;': [206], 'Published': [207], 'online': [208], 'InterScience': [211], '(': [212], 'www.interscience.wiley.com': [213], ').': [214], 'DOI': [215], '10.1002/ecjb.10119': [216]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2067459736', 'counts_by_year': [{'year': 2016, 'cited_by_count': 1}], 'updated_date': '2024-09-09T16:58:02.957938', 'created_date': '2016-06-24'}