:facetid:toc:\"db/conf/asru/asru2017.bht\"OK:facetid:toc:db/conf/asru/asru2017.bhtMarkus Müller 0001Sebastian StükerAlex WaibelDBLSTM based multilingual articulatory feature extraction for language documentation.ASRU417-4232017Conference and Workshop Papersclosedconf/asru/0001SW1710.1109/ASRU.2017.8268966https://doi.org/10.1109/ASRU.2017.8268966https://dblp.org/rec/conf/asru/0001SW17URL#2879034Tuka AlhanaiRhoda AuJames R. GlassSpoken language biomarkers for detecting cognitive impairment.ASRU409-4162017Conference and Workshop Papersclosedconf/asru/AlhanaiAG1710.1109/ASRU.2017.8268965https://doi.org/10.1109/ASRU.2017.8268965https://dblp.org/rec/conf/asru/AlhanaiAG17URL#2879035Ahmed Ali 0002Preslav NakovPeter Bell 0001Steve RenalsWERD: Using social text spelling variants for evaluating dialectal speech recognition.ASRU141-1482017Conference and Workshop Papersclosedconf/asru/AliN0R1710.1109/ASRU.2017.8268928https://doi.org/10.1109/ASRU.2017.8268928https://dblp.org/rec/conf/asru/AliN0R17URL#2879036Ahmed Ali 0002Stephan VogelSteve RenalsSpeech recognition challenge in the wild: Arabic MGB-3.ASRU316-3222017Conference and Workshop Papersclosedconf/asru/AliVR1710.1109/ASRU.2017.8268952https://doi.org/10.1109/ASRU.2017.8268952https://dblp.org/rec/conf/asru/AliVR17URL#2879037T. K. AnsariRajath KumarSonali SinghSriram GanapathyDeep learning methods for unsupervised acoustic modeling - Leap submission to ZeroSpeech challenge 2017.ASRU754-7612017Conference and Workshop Papersclosedconf/asru/AnsariKSG1710.1109/ASRU.2017.8269013https://doi.org/10.1109/ASRU.2017.8269013https://dblp.org/rec/conf/asru/AnsariKSG17URL#2879038T. K. AnsariRajath KumarSonali SinghSriram GanapathyV. Susheela DeviUnsupervised HMM posteriograms for language independent acoustic modeling in zero resource conditions.ASRU762-7682017Conference and Workshop Papersclosedconf/asru/AnsariKSGD1710.1109/ASRU.2017.8269014https://doi.org/10.1109/ASRU.2017.8269014https://dblp.org/rec/conf/asru/AnsariKSGD17URL#2879039Shoko ArakiNobutaka OnoKeisuke KinoshitaMarc DelcroixMeeting recognition with asynchronous distributed microphone array.ASRU32-392017Conference and Workshop Papersclosedconf/asru/ArakiOKD1710.1109/ASRU.2017.8268913https://doi.org/10.1109/ASRU.2017.8268913https://dblp.org/rec/conf/asru/ArakiOKD17URL#2879040Pallavi BaljekarSai Krishna RallabandiAlan W. BlackThe CMU entry to blizzard machine learning challenge.ASRU644-6492017Conference and Workshop Papersclosedconf/asru/BaljekarRB1710.1109/ASRU.2017.8268997https://doi.org/10.1109/ASRU.2017.8268997https://dblp.org/rec/conf/asru/BaljekarRB17URL#2879041Eric BattenbergJitong ChenRewon ChildAdam Coates 0002Yashesh GaurYi LiHairong LiuSanjeev SatheeshAnuroop SriramZhenyao ZhuExploring neural transducers for end-to-end speech recognition.ASRU206-2132017Conference and Workshop Papersclosedconf/asru/BattenbergCCCGL1710.1109/ASRU.2017.8268937https://doi.org/10.1109/ASRU.2017.8268937https://dblp.org/rec/conf/asru/BattenbergCCCGL17URL#2879042Marcely Zanon BoitoAlexandre BerardAline VillavicencioLaurent BesacierUnwritten languages demand attention too! Word discovery with encoder-decoder models.ASRU458-4652017Conference and Workshop Papersclosedconf/asru/BoitoBVB1710.1109/ASRU.2017.8268972https://doi.org/10.1109/ASRU.2017.8268972https://dblp.org/rec/conf/asru/BoitoBVB17URL#2879043Ahmet Emin BulutQian Zhang 0019Chunlei ZhangFahimeh BahmaninezhadJohn H. L. HansenUTD-CRSS submission for MGB-3 Arabic dialect identification: Front-end and back-end advancements on broadcast speech.ASRU360-3672017Conference and Workshop Papersclosedconf/asru/BulutZZBH1710.1109/ASRU.2017.8268958https://doi.org/10.1109/ASRU.2017.8268958https://dblp.org/rec/conf/asru/BulutZZBH17URL#2879044Po-Chun ChenTa-Chung ChiShang-Yu SuYun-Nung ChenDynamic time-aware attention to speaker roles and contexts for spoken language understanding.ASRU554-5602017Conference and Workshop Papersclosedconf/asru/ChenCSC1710.1109/ASRU.2017.8268985https://doi.org/10.1109/ASRU.2017.8268985https://dblp.org/rec/conf/asru/ChenCSC17URL#2879045Pin-Jung ChenI-Hung HsuYi Yao HuangHung-yi LeeMitigating the impact of speech recognition errors on chatbot using sequence-to-sequence model.ASRU497-5032017Conference and Workshop Papersclosedconf/asru/ChenHHL1710.1109/ASRU.2017.8268977https://doi.org/10.1109/ASRU.2017.8268977https://dblp.org/rec/conf/asru/ChenHHL17URL#2879046Xie Chen 0001X. LiuAnton RagniY. WangMark J. F. GalesFuture word contexts in neural network language models.ASRU97-1032017Conference and Workshop Papersclosedconf/asru/ChenLRWG1710.1109/ASRU.2017.8268922https://doi.org/10.1109/ASRU.2017.8268922https://dblp.org/rec/conf/asru/ChenLRWG17URL#2879047Hongjie ChenCheung-Chi LeungLei Xie 0001Bin Ma 0001Haizhou Li 0001Multilingual bottle-neck feature learning from untranscribed speech.ASRU727-7332017Conference and Workshop Papersclosedconf/asru/ChenLXML1710.1109/ASRU.2017.8269009https://doi.org/10.1109/ASRU.2017.8269009https://dblp.org/rec/conf/asru/ChenLXML17URL#2879048Zhuo Chen 0006Jinyu Li 0001Xiong XiaoTakuya YoshiokaHuaming WangZhenghao WangYifan Gong 0001Cracking the cocktail party problem by multi-beam deep attractor network.ASRU437-4442017Conference and Workshop Papersclosedconf/asru/ChenLXYWWG1710.1109/ASRU.2017.8268969https://doi.org/10.1109/ASRU.2017.8268969https://dblp.org/rec/conf/asru/ChenLXYWWG17URL#2879049Jen-Tzung ChienKang-Ting PengAdversarial manifold learning for speaker recognition.ASRU599-6052017Conference and Workshop Papersclosedconf/asru/ChienP1710.1109/ASRU.2017.8268991https://doi.org/10.1109/ASRU.2017.8268991https://dblp.org/rec/conf/asru/ChienP17URL#2879050Shun-Po ChuangChia-Hung WanPang-Chi HuangChi-Yu YangHung-yi LeeSeeing and hearing too: Audio representation for video captioning.ASRU381-3882017Conference and Workshop Papersclosedconf/asru/ChuangWHYL1710.1109/ASRU.2017.8268961https://doi.org/10.1109/ASRU.2017.8268961https://dblp.org/rec/conf/asru/ChuangWHYL17URL#2879051Hoon ChungYun-Kyung LeeJeon Gue ParkGround truth estimation of spoken english fluency score using decorrelation penalized low-rank matrix factorization.ASRU445-4492017Conference and Workshop Papersclosedconf/asru/ChungLP1710.1109/ASRU.2017.8268970https://doi.org/10.1109/ASRU.2017.8268970https://dblp.org/rec/conf/asru/ChungLP17URL#2879052Berrak SismanHaizhou Li 0001Kay Chen TanSparse representation of phonetic features for voice conversion with and without parallel data.ASRU677-6842017Conference and Workshop Papersclosedconf/asru/CicmanLT1710.1109/ASRU.2017.8269002https://doi.org/10.1109/ASRU.2017.8269002https://dblp.org/rec/conf/asru/CicmanLT17URL#2879053Salil DeenaRaymond W. M. NgPranava Swaroop MadhyasthaLucia SpeciaThomas HainExploring the use of acoustic embeddings in neural machine translation.ASRU450-4572017Conference and Workshop Papersclosedconf/asru/DeenaNMSH1710.1109/ASRU.2017.8268971https://doi.org/10.1109/ASRU.2017.8268971https://dblp.org/rec/conf/asru/DeenaNMSH17URL#2879054Ewan DunbarXuan-Nga CaoJuan BenjumeaJulien KaradayiMathieu BernardLaurent BesacierXavier AngueraEmmanuel DupouxThe zero resource speech challenge 2017.ASRU323-3302017Conference and Workshop Papersclosedconf/asru/DunbarCBKBBAD1710.1109/ASRU.2017.8268953https://doi.org/10.1109/ASRU.2017.8268953https://dblp.org/rec/conf/asru/DunbarCBKBBAD17URL#2879055Ning GaoGregory SellDouglas W. OardMark DredzeLeveraging side information for speaker identification with the Enron conversational telephone speech collection.ASRU577-5832017Conference and Workshop Papersclosedconf/asru/GaoSOD1710.1109/ASRU.2017.8268988https://doi.org/10.1109/ASRU.2017.8268988https://dblp.org/rec/conf/asru/GaoSOD17URL#2879056Pegah GhahremaniVimal ManoharHossein HadianDaniel PoveySanjeev KhudanpurInvestigation of transfer learning for ASR using LF-MMI trained neural networks.ASRU279-2862017Conference and Workshop Papersclosedconf/asru/GhahremaniMHPK1710.1109/ASRU.2017.8268947https://doi.org/10.1109/ASRU.2017.8268947https://dblp.org/rec/conf/asru/GhahremaniMHPK17URL#2879057Matthew GibsonGary CookPuming ZhanSemi-supervised training strategies for deep neural networks.ASRU77-832017Conference and Workshop Papersclosedconf/asru/GibsonCZ1710.1109/ASRU.2017.8268919https://doi.org/10.1109/ASRU.2017.8268919https://dblp.org/rec/conf/asru/GibsonCZ17URL#2879058Adnan HaiderPhilip C. WoodlandSequence training of DNN acoustic models with natural gradient.ASRU178-1842017Conference and Workshop Papersclosedconf/asru/HaiderW1710.1109/ASRU.2017.8268933https://doi.org/10.1109/ASRU.2017.8268933https://dblp.org/rec/conf/asru/HaiderW17URL#2879059Tomoki HayashiAkira TamamoriKazuhiro KobayashiKazuya TakedaTomoki TodaAn investigation of multi-speaker training for wavenet vocoder.ASRU712-7182017Conference and Workshop Papersclosedconf/asru/HayashiTKTT1710.1109/ASRU.2017.8269007https://doi.org/10.1109/ASRU.2017.8269007https://dblp.org/rec/conf/asru/HayashiTKTT17URL#2879060Yanzhang HeRohit PrabhavalkarKanishka RaoWei Li 0133Anton BakhtinIan McGrawStreaming small-footprint keyword spotting using sequence-to-sequence models.ASRU474-4812017Conference and Workshop Papersclosedconf/asru/HePRLBM1710.1109/ASRU.2017.8268974https://doi.org/10.1109/ASRU.2017.8268974https://dblp.org/rec/conf/asru/HePRLBM17URL#2879061Michael HeckSakriani SaktiSatoshi Nakamura 0001Feature optimized DPGMM clustering for unsupervised subword modeling: A contribution to zerospeech 2017.ASRU740-7462017Conference and Workshop Papersclosedconf/asru/HeckS01710.1109/ASRU.2017.8269011https://doi.org/10.1109/ASRU.2017.8269011https://dblp.org/rec/conf/asru/HeckS017URL#2879062Takuya HiguchiKeisuke KinoshitaMarc DelcroixTomohiro NakataniAdversarial training for data-driven speech enhancement without parallel corpus.ASRU40-472017Conference and Workshop Papersclosedconf/asru/HiguchiKDN1710.1109/ASRU.2017.8268914https://doi.org/10.1109/ASRU.2017.8268914https://dblp.org/rec/conf/asru/HiguchiKDN17URL#2879063Chiori HoriTakaaki HoriTim K. MarksJohn R. HersheyEarly and late integration of audio features for automatic video description.ASRU430-4362017Conference and Workshop Papersclosedconf/asru/HoriHMH1710.1109/ASRU.2017.8268968https://doi.org/10.1109/ASRU.2017.8268968https://dblp.org/rec/conf/asru/HoriHMH17URL#2879064Takaaki HoriShinji Watanabe 0001John R. HersheyMulti-level language modeling and decoding for open vocabulary end-to-end speech recognition.ASRU287-2932017Conference and Workshop Papersclosedconf/asru/HoriWH1710.1109/ASRU.2017.8268948https://doi.org/10.1109/ASRU.2017.8268948https://dblp.org/rec/conf/asru/HoriWH17URL#2879065Julien van HoutVikramjit MitraHoracio FrancoChris BartelsDimitra VergyriTackling unseen acoustic conditions in query-by-example search using time and frequency convolution for multilingual deep bottleneck features.ASRU48-542017Conference and Workshop Papersclosedconf/asru/HoutMFBV1710.1109/ASRU.2017.8268915https://doi.org/10.1109/ASRU.2017.8268915https://dblp.org/rec/conf/asru/HoutMFBV17URL#2879066Wei-Ning HsuYu Zhang 0033James R. GlassUnsupervised domain adaptation for robust speech recognition via variational autoencoder-based data augmentation.ASRU16-232017Conference and Workshop Papersclosedconf/asru/HsuZG1710.1109/ASRU.2017.8268911https://doi.org/10.1109/ASRU.2017.8268911https://dblp.org/rec/conf/asru/HsuZG17URL#2879067Ya-Jun HuLi-Juan LiuChuang DingZhen-Hua LingLi-Rong Dai 0001The USTC system for blizzard machine learning challenge 2017-ES2.ASRU650-6562017Conference and Workshop Papersclosedconf/asru/HuLDLD1710.1109/ASRU.2017.8268998https://doi.org/10.1109/ASRU.2017.8268998https://dblp.org/rec/conf/asru/HuLDLD17URL#2879068Herman KamperKaren LivescuSharon GoldwaterAn embedded segmental K-means model for unsupervised segmentation and clustering of speech.ASRU719-7262017Conference and Workshop Papersclosedconf/asru/KamperLG1710.1109/ASRU.2017.8269008https://doi.org/10.1109/ASRU.2017.8269008https://dblp.org/rec/conf/asru/KamperLG17URL#2879069Naoyuki KandaYusuke FujitaKenji NagamatsuInvestigation of lattice-free maximum mutual information-based acoustic models with sequence-level Kullback-Leibler divergence.ASRU69-762017Conference and Workshop Papersclosedconf/asru/KandaFN1710.1109/ASRU.2017.8268918https://doi.org/10.1109/ASRU.2017.8268918https://dblp.org/rec/conf/asru/KandaFN17URL#2879070Jian Kang 0006Wei-Qiang Zhang 0001Jia Liu 0001Gated convolutional networks based hybrid acoustic models for low resource speech recognition.ASRU157-1642017Conference and Workshop Papersclosedconf/asru/KangZ01710.1109/ASRU.2017.8268930https://doi.org/10.1109/ASRU.2017.8268930https://dblp.org/rec/conf/asru/KangZ017URL#2879071Young-Bum KimSungjin LeeRuhi SarikayaSpeaker-sensitive dual memory networks for multi-turn slot tagging.ASRU541-5462017Conference and Workshop Papersclosedconf/asru/KimLS1710.1109/ASRU.2017.8268983https://doi.org/10.1109/ASRU.2017.8268983https://dblp.org/rec/conf/asru/KimLS17URL#2879072Young-Bum KimSungjin LeeKarl StratosONENET: Joint domain, intent, slot prediction for spoken language understanding.ASRU547-5532017Conference and Workshop Papersclosedconf/asru/KimLS17a10.1109/ASRU.2017.8268984https://doi.org/10.1109/ASRU.2017.8268984https://dblp.org/rec/conf/asru/KimLS17aURL#2879073Shankar KumarMichael NirschlDaniel Niels Holtmann-RiceHank LiaoAnanda Theertha SureshFelix X. YuLattice rescoring strategies for long short term memory language models in speech recognition.ASRU165-1722017Conference and Workshop Papersclosedconf/asru/KumarNHLSY1710.1109/ASRU.2017.8268931https://doi.org/10.1109/ASRU.2017.8268931https://dblp.org/rec/conf/asru/KumarNHLSY17URL#2879074Ken'ichi KumataniSankaran PanchapagesanMinhua WuMinjae KimNikko StromGautam TiwariArindam MandalDirect modeling of raw audio with DNNS for wake word detection.ASRU252-2572017Conference and Workshop Papersclosedconf/asru/KumataniPWKSTM1710.1109/ASRU.2017.8268943https://doi.org/10.1109/ASRU.2017.8268943https://dblp.org/rec/conf/asru/KumataniPWKSTM17URL#2879075Gakuto KurataBhuvana RamabhadranGeorge SaonAbhinav SethyLanguage modeling with highway LSTM.ASRU244-2512017Conference and Workshop Papersclosedconf/asru/KurataRSS1710.1109/ASRU.2017.8268942https://doi.org/10.1109/ASRU.2017.8268942https://dblp.org/rec/conf/asru/KurataRSS17URL#2879076Kenneth LeidalDavid HarwathJames R. GlassLearning modality-invariant representations for speech and images.ASRU424-4292017Conference and Workshop Papersclosedconf/asru/LeidalHG1710.1109/ASRU.2017.8268967https://doi.org/10.1109/ASRU.2017.8268967https://dblp.org/rec/conf/asru/LeidalHG17URL#2879077Sheng Li 0010Xugang LuPeng ShenRyoichi TakashimaTatsuya KawaharaHisashi KawaiIncremental training and constructing the very deep convolutional residual network acoustic models.ASRU222-2272017Conference and Workshop Papersclosedconf/asru/LiLSTKK1710.1109/ASRU.2017.8268939https://doi.org/10.1109/ASRU.2017.8268939https://dblp.org/rec/conf/asru/LiLSTKK17URL#2879078Jinyu Li 0001Guoli YeRui Zhao 0017Jasha DroppoYifan Gong 0001Acoustic-to-word model without OOV.ASRU111-1172017Conference and Workshop Papersclosedconf/asru/LiYZDG1710.1109/ASRU.2017.8268924https://doi.org/10.1109/ASRU.2017.8268924https://dblp.org/rec/conf/asru/LiYZDG17URL#2879079Zih-Wei LinTzu-Wei SungHung-yi LeeLin-Shan LeePersonalized word representations carrying personalized semantics learned from social network posts.ASRU533-5402017Conference and Workshop Papersclosedconf/asru/LinSLL1710.1109/ASRU.2017.8268982https://doi.org/10.1109/ASRU.2017.8268982https://dblp.org/rec/conf/asru/LinSLL17URL#2879080Li-Juan LiuChuang DingYa-Jun HuZhen-Hua LingYuan Jiang 0006Ming ZhouSi WeiThe iFLYTEK system for blizzard machine learning challenge 2017-ES1.ASRU657-6642017Conference and Workshop Papersclosedconf/asru/LiuDHLJZW1710.1109/ASRU.2017.8268999https://doi.org/10.1109/ASRU.2017.8268999https://dblp.org/rec/conf/asru/LiuDHLJZW17URL#2879081Yi Liu 0049Liang He 0003Yao TianZhuzi ChenJia Liu 0001Michael T. JohnsonComparison of multiple features and modeling methods for text-dependent speaker verification.ASRU629-6362017Conference and Workshop Papersclosedconf/asru/LiuHTCLJ1710.1109/ASRU.2017.8268995https://doi.org/10.1109/ASRU.2017.8268995https://dblp.org/rec/conf/asru/LiuHTCLJ17URL#2879082Bing Liu 0024Ian R. LaneIterative policy learning in end-to-end trainable task-oriented neural dialog models.ASRU482-4892017Conference and Workshop Papersclosedconf/asru/LiuL1710.1109/ASRU.2017.8268975https://doi.org/10.1109/ASRU.2017.8268975https://dblp.org/rec/conf/asru/LiuL17URL#2879083Qi Liu 0018Yanmin QianKai Yu 0004Future vector enhanced LSTM language model for LVCSR.ASRU104-1102017Conference and Workshop Papersclosedconf/asru/LiuQ01710.1109/ASRU.2017.8268923https://doi.org/10.1109/ASRU.2017.8268923https://dblp.org/rec/conf/asru/LiuQ017URL#2879084Tien-Hong LoYing-Wen ChenKuan-Yu ChenHsin-Min WangBerlin ChenNeural relevance-aware query modeling for spoken document retrieval.ASRU466-4732017Conference and Workshop Papersclosedconf/asru/LoCCWC1710.1109/ASRU.2017.8268973https://doi.org/10.1109/ASRU.2017.8268973https://dblp.org/rec/conf/asru/LoCCWC17URL#2879085Timo LohrenzTim FingscheidtTurbo fusion of magnitude and phase information for DNN-based phoneme recognition.ASRU118-1252017Conference and Workshop Papersclosedconf/asru/LohrenzF1710.1109/ASRU.2017.8268925https://doi.org/10.1109/ASRU.2017.8268925https://dblp.org/rec/conf/asru/LohrenzF17URL#2879086Andrey MalininKate KnillMark J. F. GalesA hierarchical attention based model for off-topic spontaneous spoken response detection.ASRU397-4032017Conference and Workshop Papersclosedconf/asru/MalininKG1710.1109/ASRU.2017.8268963https://doi.org/10.1109/ASRU.2017.8268963https://dblp.org/rec/conf/asru/MalininKG17URL#2879087Vimal ManoharDaniel PoveySanjeev KhudanpurJHU Kaldi system for Arabic MGB-3 ASR challenge using diarization, audio-transcript alignment and transfer learning.ASRU346-3522017Conference and Workshop Papersclosedconf/asru/ManoharPK1710.1109/ASRU.2017.8268956https://doi.org/10.1109/ASRU.2017.8268956https://dblp.org/rec/conf/asru/ManoharPK17URL#2879088Takashi MasukoComputational cost reduction of long short-term memory based on simultaneous compression of input and hidden state.ASRU126-1332017Conference and Workshop Papersclosedconf/asru/Masuko1710.1109/ASRU.2017.8268926https://doi.org/10.1109/ASRU.2017.8268926https://dblp.org/rec/conf/asru/Masuko17URL#2879089Zhong MengZhuo Chen 0006Vadim MazalovJinyu Li 0001Yifan Gong 0001Unsupervised adaptation with domain separation networks for robust speech recognition.ASRU214-2212017Conference and Workshop Papersclosedconf/asru/MengCMLG1710.1109/ASRU.2017.8268938https://doi.org/10.1109/ASRU.2017.8268938https://dblp.org/rec/conf/asru/MengCMLG17URL#2879090Anjali MenonChanwoo Kim 0001Umpei KurokawaRichard M. SternBinaural processing for robust recognition of degraded speech.ASRU24-312017Conference and Workshop Papersclosedconf/asru/MenonKKS1710.1109/ASRU.2017.8268912https://doi.org/10.1109/ASRU.2017.8268912https://dblp.org/rec/conf/asru/MenonKKS17URL#2879091Assaf Hurwitz MichaelyXuedong ZhangGabor SimkoCarolina ParadaPetar S. AleksicKeyword spotting for Google assistant using contextual speech recognition.ASRU272-2782017Conference and Workshop Papersclosedconf/asru/MichaelyZSPA1710.1109/ASRU.2017.8268946https://doi.org/10.1109/ASRU.2017.8268946https://dblp.org/rec/conf/asru/MichaelyZSPA17URL#2879092Masato MimuraShinsuke SakaiTatsuya KawaharaCross-domain speech recognition using nonparallel corpora with cycle-consistent adversarial networks.ASRU134-1402017Conference and Workshop Papersclosedconf/asru/MimuraSK1710.1109/ASRU.2017.8268927https://doi.org/10.1109/ASRU.2017.8268927https://dblp.org/rec/conf/asru/MimuraSK17URL#2879093Maryam NajafianWei-Ning HsuAhmed Ali 0002James R. GlassAutomatic speech recognition of Arabic multi-genre broadcast media.ASRU353-3592017Conference and Workshop Papersclosedconf/asru/NajafianHAG1710.1109/ASRU.2017.8268957https://doi.org/10.1109/ASRU.2017.8268957https://dblp.org/rec/conf/asru/NajafianHAG17URL#2879094Keisuke NakamuraRandy GomezImproving separation of overlapped speech for meeting conversations using uncalibrated microphone array.ASRU55-622017Conference and Workshop Papersclosedconf/asru/NakamuraG1710.1109/ASRU.2017.8268916https://doi.org/10.1109/ASRU.2017.8268916https://dblp.org/rec/conf/asru/NakamuraG17URL#2879095Karan NathwaniEmmanuel Vincent 0001Irina IllinaConsistent DNN uncertainty training and decoding for robust ASR.ASRU185-1922017Conference and Workshop Papersclosedconf/asru/NathwaniVI1710.1109/ASRU.2017.8268934https://doi.org/10.1109/ASRU.2017.8268934https://dblp.org/rec/conf/asru/NathwaniVI17URL#2879096Axel H. NgKyle GormanRichard SproatMinimally supervised written-to-spoken text normalization.ASRU665-6702017Conference and Workshop Papersclosedconf/asru/NgGS1710.1109/ASRU.2017.8269000https://doi.org/10.1109/ASRU.2017.8269000https://dblp.org/rec/conf/asru/NgGS17URL#2879097Takuma OkamotoKentaro TachibanaTomoki TodaYoshinori ShigaHisashi KawaiSubband wavenet with overlapped single-sideband filterbanks.ASRU698-7042017Conference and Workshop Papersclosedconf/asru/OkamotoTTSK1710.1109/ASRU.2017.8269005https://doi.org/10.1109/ASRU.2017.8269005https://dblp.org/rec/conf/asru/OkamotoTTSK17URL#2879098Youssef OualilDietrich KlakowGyörgy SzaszákAjay SrinivasamurthyHartmut HelmkePetr MotlícekA context-aware speech recognition and understanding system for air traffic control domain.ASRU404-4082017Conference and Workshop Papersclosedconf/asru/OualilKSSHM1710.1109/ASRU.2017.8268964https://doi.org/10.1109/ASRU.2017.8268964https://dblp.org/rec/conf/asru/OualilKSSHM17URL#2879099Titouan ParcolletMohamed MorchidGeorges LinarèsDeep quaternion neural networks for spoken language understanding.ASRU504-5112017Conference and Workshop Papersclosedconf/asru/ParcolletML1710.1109/ASRU.2017.8268978https://doi.org/10.1109/ASRU.2017.8268978https://dblp.org/rec/conf/asru/ParcolletML17URL#2879100Yao QianKeelan EvaniniPatrick L. LangeRobert A. PughRutuja UbaleFrank K. SoongImproving native language (L1) identifation with better VAD and TDNN trained separately on native and non-native English corpora.ASRU606-6132017Conference and Workshop Papersclosedconf/asru/QianELPUS1710.1109/ASRU.2017.8268992https://doi.org/10.1109/ASRU.2017.8268992https://dblp.org/rec/conf/asru/QianELPUS17URL#2879101Yao QianRutuja UbaleVikram RamanarayananPatrick L. LangeDavid Suendermann-OeftKeelan EvaniniEugene TsuprunExploring ASR-free end-to-end modeling to improve spoken language understanding in a cloud-based dialog system.ASRU569-5762017Conference and Workshop Papersclosedconf/asru/QianURLSET1710.1109/ASRU.2017.8268987https://doi.org/10.1109/ASRU.2017.8268987https://dblp.org/rec/conf/asru/QianURLSET17URL#2879102Zhongdi QuParisa HaghaniEugene WeinsteinPedro J. Moreno 0001Syllable-based acoustic modeling with CTC-SMBR-LSTM.ASRU173-1772017Conference and Workshop Papersclosedconf/asru/QuHWM1710.1109/ASRU.2017.8268932https://doi.org/10.1109/ASRU.2017.8268932https://dblp.org/rec/conf/asru/QuHWM17URL#2879103Rachel RakovAndrew RosenbergInvestigating native and non-native English classification and transfer effects using Legendre polynomial coefficient clustering.ASRU637-6432017Conference and Workshop Papersclosedconf/asru/RakovR1710.1109/ASRU.2017.8268996https://doi.org/10.1109/ASRU.2017.8268996https://dblp.org/rec/conf/asru/RakovR17URL#2879104Kanishka RaoHasim SakRohit PrabhavalkarExploring architectures, data and units for streaming end-to-end speech recognition with RNN-transducer.ASRU193-1992017Conference and Workshop Papersclosedconf/asru/RaoSP1710.1109/ASRU.2017.8268935https://doi.org/10.1109/ASRU.2017.8268935https://dblp.org/rec/conf/asru/RaoSP17URL#2879105Abhinav RastogiDilek Hakkani-TürLarry P. HeckScalable multi-domain dialogue state tracking.ASRU561-5682017Conference and Workshop Papersclosedconf/asru/RastogiHH1710.1109/ASRU.2017.8268986https://doi.org/10.1109/ASRU.2017.8268986https://dblp.org/rec/conf/asru/RastogiHH17URL#2879106Joanna RownickaSteve RenalsPeter Bell 0001Simplifying very deep convolutional neural network architectures for robust speech recognition.ASRU236-2432017Conference and Workshop Papersclosedconf/asru/RownickaR01710.1109/ASRU.2017.8268941https://doi.org/10.1109/ASRU.2017.8268941https://dblp.org/rec/conf/asru/RownickaR017URL#2879107David RybachMichael Riley 0001Johan SchalkwykOn lattice generation for large vocabulary speech recognition.ASRU228-2352017Conference and Workshop Papersclosedconf/asru/RybachRS1710.1109/ASRU.2017.8268940https://doi.org/10.1109/ASRU.2017.8268940https://dblp.org/rec/conf/asru/RybachRS17URL#2879108Lahiru SamarakoonBrian MakUnsupervised adaptation of student DNNS learned from teacher RNNS for improved ASR performance.ASRU200-2052017Conference and Workshop Papersclosedconf/asru/SamarakoonM1710.1109/ASRU.2017.8268936https://doi.org/10.1109/ASRU.2017.8268936https://dblp.org/rec/conf/asru/SamarakoonM17URL#2879109Kei SawadaKeiichi TokudaSimon King 0001Alan W. BlackThe blizzard machine learning challenge 2017.ASRU331-3372017Conference and Workshop Papersclosedconf/asru/SawadaTKB1710.1109/ASRU.2017.8268954https://doi.org/10.1109/ASRU.2017.8268954https://dblp.org/rec/conf/asru/SawadaTKB17URL#2879110Lea SchonherrSteffen ZeilerDorothea KolossaSpoofing detection via simultaneous verification of audio-visual synchronicity and transcription.ASRU591-5982017Conference and Workshop Papersclosedconf/asru/SchonherrZK1710.1109/ASRU.2017.8268990https://doi.org/10.1109/ASRU.2017.8268990https://dblp.org/rec/conf/asru/SchonherrZK17URL#2879111Imran A. SheikhDominique FohrIrina IllinaTopic segmentation in ASR transcripts using bidirectional RNNS for change detection.ASRU512-5182017Conference and Workshop Papersclosedconf/asru/SehikhFI1710.1109/ASRU.2017.8268979https://doi.org/10.1109/ASRU.2017.8268979https://dblp.org/rec/conf/asru/SehikhFI17URL#2879112Bowen ShiKaren LivescuMultitask training with unlabeled data for end-to-end sign language fingerspelling recognition.ASRU389-3962017Conference and Workshop Papersclosedconf/asru/ShiL1710.1109/ASRU.2017.8268962https://doi.org/10.1109/ASRU.2017.8268962https://dblp.org/rec/conf/asru/ShiL17URL#2879113Ziqiang ShiLiu LiuMengjiao Wang 0001Rujie LiuMulti-view (Joint) probability linear discrimination analysis for J-vector based text dependent speaker verification.ASRU614-6202017Conference and Workshop Papersclosedconf/asru/ShiLWL1710.1109/ASRU.2017.8268993https://doi.org/10.1109/ASRU.2017.8268993https://dblp.org/rec/conf/asru/ShiLWL17URL#2879114Hayato ShibataTaku KatoTakahiro ShinozakiShinji Watanabe 0001Composite embedding systems for ZeroSpeech2017 Track1.ASRU747-7532017Conference and Workshop Papersclosedconf/asru/ShibataKSW1710.1109/ASRU.2017.8269012https://doi.org/10.1109/ASRU.2017.8269012https://dblp.org/rec/conf/asru/ShibataKSW17URL#2879115Suwon ShonAhmed Ali 0002James R. GlassMIT-QCRI Arabic dialect identification system for the 2017 multi-genre broadcast challenge.ASRU374-3802017Conference and Workshop Papersclosedconf/asru/ShonAG1710.1109/ASRU.2017.8268960https://doi.org/10.1109/ASRU.2017.8268960https://dblp.org/rec/conf/asru/ShonAG17URL#2879116Aditya SiddhantPreethi JyothiSriram GanapathyLeveraging native language speech for accent identification using deep Siamese networks.ASRU621-6282017Conference and Workshop Papersclosedconf/asru/SiddhantJG1710.1109/ASRU.2017.8268994https://doi.org/10.1109/ASRU.2017.8268994https://dblp.org/rec/conf/asru/SiddhantJG17URL#2879117Khe Chai SimArun NarayananTom BagbyTara N. SainathMichiel BacchianiImproving the efficiency of forward-backward algorithm using batched computation in TensorFlow.ASRU258-2642017Conference and Workshop Papersclosedconf/asru/SimNBSB1710.1109/ASRU.2017.8268944https://doi.org/10.1109/ASRU.2017.8268944https://dblp.org/rec/conf/asru/SimNBSB17URL#2879118Peter SmitSiva Reddy GangireddySeppo EnarviSami VirpiojaMikko KurimoCharacter-based units for unlimited vocabulary continuous speech recognition.ASRU149-1562017Conference and Workshop Papersclosedconf/asru/SmitGEVK1710.1109/ASRU.2017.8268929https://doi.org/10.1109/ASRU.2017.8268929https://dblp.org/rec/conf/asru/SmitGEVK17URL#2879119Peter SmitSiva Reddy GangireddySeppo EnarviSami VirpiojaMikko KurimoAalto system for the 2017 Arabic multi-genre broadcast challenge.ASRU338-3452017Conference and Workshop Papersclosedconf/asru/SmitGEVK17a10.1109/ASRU.2017.8268955https://doi.org/10.1109/ASRU.2017.8268955https://dblp.org/rec/conf/asru/SmitGEVK17aURL#2879120Hagen SoltauHank LiaoHasim SakReducing the computational complexity for whole word models.ASRU63-682017Conference and Workshop Papersclosedconf/asru/SoltauLS1710.1109/ASRU.2017.8268917https://doi.org/10.1109/ASRU.2017.8268917https://dblp.org/rec/conf/asru/SoltauLS17URL#2879121Eunwoo SongFrank K. SoongHong-Goo KangPerceptual quality and modeling accuracy of excitation parameters in DLSTM-based speech synthesis systems.ASRU671-6762017Conference and Workshop Papersclosedconf/asru/SongSK1710.1109/ASRU.2017.8269001https://doi.org/10.1109/ASRU.2017.8269001https://dblp.org/rec/conf/asru/SongSK17URL#2879122Komei SugiuraHisashi KawaiGrounded language understanding for manipulation instructions using GAN-based classification.ASRU519-5242017Conference and Workshop Papersclosedconf/asru/SugiuraK1710.1109/ASRU.2017.8268980https://doi.org/10.1109/ASRU.2017.8268980https://dblp.org/rec/conf/asru/SugiuraK17URL#2879123Andros TjandraSakriani SaktiSatoshi Nakamura 0001Listening while speaking: Speech chain by deep learning.ASRU301-3082017Conference and Workshop Papersclosedconf/asru/TjandraS01710.1109/ASRU.2017.8268950https://doi.org/10.1109/ASRU.2017.8268950https://dblp.org/rec/conf/asru/TjandraS017URL#2879124Andros TjandraSakriani SaktiSatoshi Nakamura 0001Attention-based Wav2Text with feature transfer learning.ASRU309-3152017Conference and Workshop Papersclosedconf/asru/TjandraS017a10.1109/ASRU.2017.8268951https://doi.org/10.1109/ASRU.2017.8268951https://dblp.org/rec/conf/asru/TjandraS017aURL#2879125Emiru TsunooOndrej KlejchPeter Bell 0001Steve RenalsHierarchical recurrent neural network for story segmentation using fusion of lexical and acoustic features.ASRU525-5322017Conference and Workshop Papersclosedconf/asru/TsunooK0R1710.1109/ASRU.2017.8268981https://doi.org/10.1109/ASRU.2017.8268981https://dblp.org/rec/conf/asru/TsunooK0R17URL#2879126Karel VeselýMurali Karthick BaskarMireia DíezKarel BenesMGB-3 but system: Low-resource ASR on Egyptian YouTube data.ASRU368-3732017Conference and Workshop Papersclosedconf/asru/VeselyBDB1710.1109/ASRU.2017.8268959https://doi.org/10.1109/ASRU.2017.8268959https://dblp.org/rec/conf/asru/VeselyBDB17URL#2879127Miroslav VodolánFilip JurcícekDenotation extraction for interactive learning in dialogue systems.ASRU490-4962017Conference and Workshop Papersclosedconf/asru/VodolanJ1710.1109/ASRU.2017.8268976https://doi.org/10.1109/ASRU.2017.8268976https://dblp.org/rec/conf/asru/VodolanJ17URL#2879128Kévin VythelingumYannick EstèveOlivier RosecError detection of grapheme-to-phoneme conversion in text-to-speech synthesis using speech signal and lexical context.ASRU692-6972017Conference and Workshop Papersclosedconf/asru/VythelingumER1710.1109/ASRU.2017.8269004https://doi.org/10.1109/ASRU.2017.8269004https://dblp.org/rec/conf/asru/VythelingumER17URL#2879129Moquan WanGilles DegottexMark J. F. GalesIntegrated speaker-adaptive speech synthesis.ASRU705-7112017Conference and Workshop Papersclosedconf/asru/WanDG1710.1109/ASRU.2017.8269006https://doi.org/10.1109/ASRU.2017.8269006https://dblp.org/rec/conf/asru/WanDG17URL#2879130Bin Wang 0042Zhijian OuLanguage modeling with neural trans-dimensional random fields.ASRU294-3002017Conference and Workshop Papersclosedconf/asru/WangO1710.1109/ASRU.2017.8268949https://doi.org/10.1109/ASRU.2017.8268949https://dblp.org/rec/conf/asru/WangO17URL#2879131Shinji Watanabe 0001Takaaki HoriJohn R. HersheyLanguage independent end-to-end architecture for joint language identification and speech recognition.ASRU265-2712017Conference and Workshop Papersclosedconf/asru/WatanabeHH1710.1109/ASRU.2017.8268945https://doi.org/10.1109/ASRU.2017.8268945https://dblp.org/rec/conf/asru/WatanabeHH17URL#2879132Jeremy Heng Meng WongMark J. F. GalesMulti-task ensembles with teacher-student training.ASRU84-902017Conference and Workshop Papersclosedconf/asru/WongG1710.1109/ASRU.2017.8268920https://doi.org/10.1109/ASRU.2017.8268920https://dblp.org/rec/conf/asru/WongG17URL#2879133Shan YangLei Xie 0001Xiao ChenXiaoyan LouXuan ZhuDongyan HuangHaizhou Li 0001Statistical parametric speech synthesis using generative adversarial networks under a multi-task learning framework.ASRU685-6912017Conference and Workshop Papersclosedconf/asru/YangXCLZHL1710.1109/ASRU.2017.8269003https://doi.org/10.1109/ASRU.2017.8269003https://dblp.org/rec/conf/asru/YangXCLZHL17URL#2879134Emre Yilmaz 0001Julien van HoutHoracio FrancoNoise-robust exemplar matching for rescoring query-by-example search.ASRU1-72017Conference and Workshop Papersclosedconf/asru/YilmazHF1710.1109/ASRU.2017.8268909https://doi.org/10.1109/ASRU.2017.8268909https://dblp.org/rec/conf/asru/YilmazHF17URL#2879135Emre Yilmaz 0001Mitchell McLarenHenk van den HeuvelDavid A. van LeeuwenLanguage diarization for semi-supervised bilingual acoustic model training.ASRU91-962017Conference and Workshop Papersclosedconf/asru/YilmazMHL1710.1109/ASRU.2017.8268921https://doi.org/10.1109/ASRU.2017.8268921https://dblp.org/rec/conf/asru/YilmazMHL17URL#2879136Yougen YuanCheung-Chi LeungLei Xie 0001Hongjie ChenBin Ma 0001Haizhou Li 0001Extracting bottleneck features and word-like pairs from untranscribed speech for feature representation.ASRU734-7392017Conference and Workshop Papersclosedconf/asru/YuanLXCML1710.1109/ASRU.2017.8269010https://doi.org/10.1109/ASRU.2017.8269010https://dblp.org/rec/conf/asru/YuanLXCML17URL#2879137Chunlei ZhangKazuhito KoishidaEnd-to-end text-independent speaker verification with flexibility in utterance duration.ASRU584-5902017Conference and Workshop Papersclosedconf/asru/ZhangK1710.1109/ASRU.2017.8268989https://doi.org/10.1109/ASRU.2017.8268989https://dblp.org/rec/conf/asru/ZhangK17URL#2879138Katerina ZmolíkováMarc DelcroixKeisuke KinoshitaTakuya HiguchiAtsunori OgawaTomohiro NakataniLearning speaker representation for neural network based multichannel speaker extraction.ASRU8-152017Conference and Workshop Papersclosedconf/asru/ZmolikovaDKHON1710.1109/ASRU.2017.8268910https://doi.org/10.1109/ASRU.2017.8268910https://dblp.org/rec/conf/asru/ZmolikovaDKHON17URL#28791392017 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2017, Okinawa, Japan, December 16-20, 2017ASRUIEEE2017Editorshipconf/asru/2017https://ieeexplore.ieee.org/xpl/conhome/8260578/proceedinghttps://dblp.org/rec/conf/asru/2017URL#3034150