Publication Information

{'id': 'https://openalex.org/W2754746744', 'doi': 'https://doi.org/10.1109/icsse.2017.8030927', 'title': 'Speech/music discrimination using hybrid-based feature extraction for audio data indexing', 'display_name': 'Speech/music discrimination using hybrid-based feature extraction for audio data indexing', 'publication_year': 2017, 'publication_date': '2017-07-01', 'ids': {'openalex': 'https://openalex.org/W2754746744', 'doi': 'https://doi.org/10.1109/icsse.2017.8030927', 'mag': '2754746744'}, 'language': 'en', 'primary_location': {'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/icsse.2017.8030927', 'pdf_url': None, 'source': None, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}, 'type': 'article', 'type_crossref': 'proceedings-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/A5033706944', 'display_name': 'Kun-Ching Wang', 'orcid': 'https://orcid.org/0000-0001-6478-7277'}, 'institutions': [{'id': 'https://openalex.org/I14140830', 'display_name': 'Shih Chien University', 'ror': 'https://ror.org/01c3hyk82', 'country_code': 'TW', 'type': 'education', 'lineage': ['https://openalex.org/I14140830']}], 'countries': ['TW'], 'is_corresponding': False, 'raw_author_name': 'Kun-Ching Wang', 'raw_affiliation_strings': ['Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.'], 'affiliations': [{'raw_affiliation_string': 'Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.', 'institution_ids': ['https://openalex.org/I14140830']}]}, {'author_position': 'middle', 'author': {'id': 'https://openalex.org/A5008036341', 'display_name': 'Yung-Ming Yang', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I14140830', 'display_name': 'Shih Chien University', 'ror': 'https://ror.org/01c3hyk82', 'country_code': 'TW', 'type': 'education', 'lineage': ['https://openalex.org/I14140830']}], 'countries': ['TW'], 'is_corresponding': False, 'raw_author_name': 'Yung-Ming Yang', 'raw_affiliation_strings': ['Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.'], 'affiliations': [{'raw_affiliation_string': 'Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.', 'institution_ids': ['https://openalex.org/I14140830']}]}, {'author_position': 'last', 'author': {'id': 'https://openalex.org/A5009880703', 'display_name': 'Ying-Ru Yang', 'orcid': None}, 'institutions': [{'id': 'https://openalex.org/I14140830', 'display_name': 'Shih Chien University', 'ror': 'https://ror.org/01c3hyk82', 'country_code': 'TW', 'type': 'education', 'lineage': ['https://openalex.org/I14140830']}], 'countries': ['TW'], 'is_corresponding': False, 'raw_author_name': 'Ying-Ru Yang', 'raw_affiliation_strings': ['Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.'], 'affiliations': [{'raw_affiliation_string': 'Department of Information Technology & Communication, Shih Chien University, Kaohsiung, Taiwan, R.O.C.', 'institution_ids': ['https://openalex.org/I14140830']}]}], 'institution_assertions': [], 'countries_distinct_count': 1, 'institutions_distinct_count': 1, 'corresponding_author_ids': [], 'corresponding_institution_ids': [], 'apc_list': None, 'apc_paid': None, 'fwci': 0.93, 'has_fulltext': True, 'fulltext_origin': 'ngrams', 'cited_by_count': 5, 'citation_normalized_percentile': {'value': 0.538215, 'is_in_top_1_percent': False, 'is_in_top_10_percent': False}, 'cited_by_percentile_year': {'min': 80, 'max': 81}, 'biblio': {'volume': None, 'issue': None, 'first_page': None, 'last_page': None}, 'is_retracted': False, 'is_paratext': False, 'primary_topic': {'id': 'https://openalex.org/T11309', 'display_name': 'Audio Signal Classification and Analysis', 'score': 0.9999, '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/T11309', 'display_name': 'Audio Signal Classification and Analysis', 'score': 0.9999, '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/T10860', 'display_name': 'Speech Enhancement Techniques', 'score': 0.9993, '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': 0.9965, '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/environmental-sound-recognition', 'display_name': 'Environmental Sound Recognition', 'score': 0.60538}, {'id': 'https://openalex.org/keywords/audio-signal-classification', 'display_name': 'Audio Signal Classification', 'score': 0.602162}, {'id': 'https://openalex.org/keywords/audio-visual-speech-recognition', 'display_name': 'Audio-Visual Speech Recognition', 'score': 0.599295}, {'id': 'https://openalex.org/keywords/audio-event-detection', 'display_name': 'Audio Event Detection', 'score': 0.597864}, {'id': 'https://openalex.org/keywords/music-information-retrieval', 'display_name': 'Music Information Retrieval', 'score': 0.55135}, {'id': 'https://openalex.org/keywords/audio-mining', 'display_name': 'Audio mining', 'score': 0.48465043}, {'id': 'https://openalex.org/keywords/database-index', 'display_name': 'Database index', 'score': 0.4260527}, {'id': 'https://openalex.org/keywords/feature', 'display_name': 'Feature (linguistics)', 'score': 0.4186352}], 'concepts': [{'id': 'https://openalex.org/C75165309', 'wikidata': 'https://www.wikidata.org/wiki/Q2258979', 'display_name': 'Search engine indexing', 'level': 2, 'score': 0.8181829}, {'id': 'https://openalex.org/C41008148', 'wikidata': 'https://www.wikidata.org/wiki/Q21198', 'display_name': 'Computer science', 'level': 0, 'score': 0.8005048}, {'id': 'https://openalex.org/C52622490', 'wikidata': 'https://www.wikidata.org/wiki/Q1026626', 'display_name': 'Feature extraction', 'level': 2, 'score': 0.71372414}, {'id': 'https://openalex.org/C28490314', 'wikidata': 'https://www.wikidata.org/wiki/Q189436', 'display_name': 'Speech recognition', 'level': 1, 'score': 0.60789096}, {'id': 'https://openalex.org/C157968479', 'wikidata': 'https://www.wikidata.org/wiki/Q3079876', 'display_name': 'Audio mining', 'level': 4, 'score': 0.48465043}, {'id': 'https://openalex.org/C154945302', 'wikidata': 'https://www.wikidata.org/wiki/Q11660', 'display_name': 'Artificial intelligence', 'level': 1, 'score': 0.47610223}, {'id': 'https://openalex.org/C59276292', 'wikidata': 'https://www.wikidata.org/wiki/Q580427', 'display_name': 'Database index', 'level': 3, 'score': 0.4260527}, {'id': 'https://openalex.org/C2776401178', 'wikidata': 'https://www.wikidata.org/wiki/Q12050496', 'display_name': 'Feature (linguistics)', 'level': 2, 'score': 0.4186352}, {'id': 'https://openalex.org/C153180895', 'wikidata': 'https://www.wikidata.org/wiki/Q7148389', 'display_name': 'Pattern recognition (psychology)', 'level': 2, 'score': 0.40477327}, {'id': 'https://openalex.org/C61328038', 'wikidata': 'https://www.wikidata.org/wiki/Q3358061', 'display_name': 'Speech processing', 'level': 2, 'score': 0.24895051}, {'id': 'https://openalex.org/C155635449', 'wikidata': 'https://www.wikidata.org/wiki/Q4674699', 'display_name': 'Acoustic model', 'level': 3, 'score': 0.2105256}, {'id': 'https://openalex.org/C41895202', 'wikidata': 'https://www.wikidata.org/wiki/Q8162', 'display_name': 'Linguistics', 'level': 1, 'score': 0.0}, {'id': 'https://openalex.org/C138885662', 'wikidata': 'https://www.wikidata.org/wiki/Q5891', 'display_name': 'Philosophy', 'level': 0, 'score': 0.0}], 'mesh': [], 'locations_count': 1, 'locations': [{'is_oa': False, 'landing_page_url': 'https://doi.org/10.1109/icsse.2017.8030927', 'pdf_url': None, 'source': None, 'license': None, 'license_id': None, 'version': None, 'is_accepted': False, 'is_published': False}], 'best_oa_location': None, 'sustainable_development_goals': [{'display_name': 'Reduced inequalities', 'score': 0.6, 'id': 'https://metadata.un.org/sdg/10'}], 'grants': [], 'datasets': [], 'versions': [], 'referenced_works_count': 11, 'referenced_works': ['https://openalex.org/W1502874967', 'https://openalex.org/W1833279920', 'https://openalex.org/W1966311970', 'https://openalex.org/W2015011382', 'https://openalex.org/W2077662469', 'https://openalex.org/W2106055371', 'https://openalex.org/W2124864596', 'https://openalex.org/W2128838222', 'https://openalex.org/W2545845972', 'https://openalex.org/W4233736617', 'https://openalex.org/W65148590'], 'related_works': ['https://openalex.org/W4301000806', 'https://openalex.org/W4237510188', 'https://openalex.org/W2527247821', 'https://openalex.org/W2185250746', 'https://openalex.org/W2131156500', 'https://openalex.org/W2118916824', 'https://openalex.org/W2059878404', 'https://openalex.org/W2048379072', 'https://openalex.org/W1562055306', 'https://openalex.org/W1505866794'], 'abstract_inverted_index': {'In': [0, 43, 142], 'this': [1], 'paper,': [2], 'we': [3], 'present': [4], 'a': [5, 145], 'speech/music': [6, 92], 'discrimination': [7, 93, 157], '(SMD)': [8, 94], 'using': [9], 'hybrid': [10], 'manner': [11], 'of': [12, 31, 99, 164], 'feature': [13], 'extraction': [14], 'to': [15, 39, 71, 131, 154, 160, 211], 'discriminate': [16], 'the': [17, 29, 45, 73, 106, 122, 128, 156, 162, 174, 183, 207], 'noisy': [18, 46, 74, 118, 133], 'audio': [19, 47, 68, 75, 111, 119, 134, 165, 184], 'signal': [20, 33, 76], 'into': [21, 67, 77, 114, 136, 182], 'speech': [22, 54, 137], 'and': [23, 35, 80, 95, 101, 117, 139, 159], 'music.': [24], 'The': [25, 58, 82, 187], 'hybrid-based': [26, 60, 123, 176], 'SMD': [27, 61, 124, 177], 'performs': [28], 'combination': [30], '1D': [32], 'processing': [34, 38], '2D': [36], 'image': [37], 'extract': [40], 'multiple': [41], 'features.': [42], 'general,': [44], 'segment': [48], 'can': [49, 179, 202], 'be': [50, 150, 192], 'regarded': [51, 104, 126], 'as': [52, 105, 127], 'music,': [53], 'or': [55], 'noise': [56], '(silence).': [57], 'proposed': [59, 175], 'approach': [62, 83, 178], 'has': [63], 'been': [64], 'successfully': [65, 180], 'applied': [66, 151], 'data': [69, 166, 185], 'indexing': [70], 'classify': [72, 132], 'speech,': [78], 'music': [79, 140], 'noise.': [81], 'includes': [84], 'three': [85], 'main': [86], 'stages:': [87], 'pre-processing/voice': [88], 'activity': [89], 'detection': [90], '(VAD),': [91], 'rule-based': [96, 146], 'post-processing.': [97], 'Both': [98], 'pre-processing': [100], 'VAD': [102], 'are': [103], 'first': [107], 'stage': [108, 130], 'for': [109, 206], 'discriminating': [110], 'recording': [112], 'stream': [113], 'noise-only': [115], 'segments': [116, 135, 138], 'segments.': [120, 141], 'Next,': [121], 'is': [125, 214], 'second': [129], 'third': [143], 'stage,': [144], 'post-filtering': [147], 'method': [148], 'will': [149, 171, 191], 'in': [152, 167], 'order': [153], 'improve': [155], 'accuracy': [158, 190], 'reflect': [161], 'continuity': [163], 'time.': [168], 'Experimental': [169], 'results': [170, 201], 'show': [172], 'that': [173], 'apply': [181], 'indexing.': [186], 'overall': [188], 'system': [189], 'evaluated': [193], 'on': [194], 'radio': [195], 'recordings': [196], 'from': [197], 'various': [198], 'sources.': [199], 'Performance': [200], 'provide': [203], 'significant': [204], 'classification': [205], 'envisaged': [208], 'tasks': [209], 'compared': [210], 'existing': [212], 'methods': [213], 'given.': [215]}, 'cited_by_api_url': 'https://api.openalex.org/works?filter=cites:W2754746744', 'counts_by_year': [{'year': 2020, 'cited_by_count': 2}, {'year': 2019, 'cited_by_count': 1}, {'year': 2018, 'cited_by_count': 2}], 'updated_date': '2024-09-24T21:05:17.597306', 'created_date': '2017-09-25'}