{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:45:24Z","timestamp":1725551124489},"publisher-location":"Berlin, Heidelberg","reference-count":58,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642123481"},{"type":"electronic","value":"9783642123498"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-12349-8_13","type":"book-chapter","created":{"date-parts":[[2010,3,24]],"date-time":"2010-03-24T15:47:01Z","timestamp":1269445621000},"page":"221-237","source":"Crossref","is-referenced-by-count":6,"title":["Speech Recognition on Mobile Devices"],"prefix":"10.1007","author":[{"given":"Zheng-Hua","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"B\u00f8rge","family":"Lindberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"volume-title":"Automatic Speech Recognition on Mobile Devices and Over Communication Networks","year":"2008","key":"13_CR1","unstructured":"Tan, Z.-H., Lindberg, B. (eds.): Automatic Speech Recognition on Mobile Devices and Over Communication Networks. Springer, London (2008)"},{"key":"13_CR2","unstructured":"Bailey, A.: Challenges and Opportunities for Intearction on Mobile Devices. In: Proc. COLING 2004 Robust and adaptive information processing for mobile speech interfaces, Geneva, Switzerland, August 2004, pp. 9\u201314 (2004)"},{"key":"13_CR3","unstructured":"Tan, Z.-H., Novak, M.: Speech Recognition on Mobile Devices: Distributed and Embedded Solutions. In: Tutorial at Interspeech 2008, Brisbane, Australia (September 2008)"},{"issue":"8","key":"13_CR4","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1109\/TSA.2002.804548","volume":"10","author":"I. Varga","year":"2002","unstructured":"Varga, I., Aalburg, S., Andrassy, B., Astrov, S., Bauer, J.G., Beaugeant, C., Geissler, C., Hoge, H.: ASR in Mobile Phones - an Industrial Approach. IEEE Transactions on Speech and Audio Processing\u00a010(8), 562\u2013569 (2002)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Novak, M.: Towards Large Vocabulary ASR on Embedded Platforms. In: Proc. ICSLP, Jeju Island, Korea (2004)","DOI":"10.21437\/Interspeech.2004-683"},{"issue":"5","key":"13_CR6","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1109\/89.928920","volume":"9","author":"H.K. Kim","year":"2001","unstructured":"Kim, H.K., Cox, R.V.: A Bitstream-Based Front-End for Wireless Speech Recognition on IS-136 Communications System. IEEE Trans. Speech and Audio Processing\u00a09(5), 558\u2013568 (2001)","journal-title":"IEEE Trans. Speech and Audio Processing"},{"issue":"2","key":"13_CR7","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/6046.923820","volume":"3","author":"C. Pel\u00e1ez-Moreno","year":"2001","unstructured":"Pel\u00e1ez-Moreno, C., Gallardo-Antol\u00edn, A., D\u00edaz-de-Mar\u00eda, F.: Recognizing Voice over IP Networks: a Robust Front-End for Speech Recognition on the world wide web. IEEE Transactions on Multimedia\u00a03(2), 209\u2013218 (2001)","journal-title":"IEEE Transactions on Multimedia"},{"key":"13_CR8","unstructured":"Pearce, D.: Robustness to Transmission Channel \u2013 the DSR Approach. In: Proc. COST278 & ISCA Research Workshop on Robustness Issues in Conversational Interaction, Norwich, UK (2004)"},{"issue":"1-2","key":"13_CR9","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.specom.2005.05.007","volume":"47","author":"Z.-H. Tan","year":"2005","unstructured":"Tan, Z.-H., Dalsgaard, P., Lindberg, B.: Automatic Speech Recognition over Error-Prone Wireless Networks. Speech Communication\u00a047(1-2), 220\u2013242 (2005)","journal-title":"Speech Communication"},{"issue":"5","key":"13_CR10","first-page":"14","volume":"3","author":"J. Cohen","year":"2004","unstructured":"Cohen, J.: Is Embedded Speech Recognition Disruptive Technology? Information Quarterly\u00a03(5), 14\u201317 (2004)","journal-title":"Information Quarterly"},{"key":"13_CR11","unstructured":"http:\/\/www.vlingo.com\/ (accesed July 4, 2009)"},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Cohen, J.: Embedded Speech Recognition Applications in Mobile Phones: Status, Trends, and Challenges. In: Proceedings of ICASSP 2008, Las Vegas, USA (2008)","DOI":"10.1109\/ICASSP.2008.4518869"},{"key":"13_CR13","unstructured":"http:\/\/www.nuance.com\/mobilesearch\/ (accessed July 4, 2009)"},{"key":"13_CR14","unstructured":"http:\/\/www.thefreelibrary.com\/ (accessed July 4, 2009)"},{"issue":"4","key":"13_CR15","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1109\/TASL.2007.894524","volume":"15","author":"M.D. Wachter","year":"2007","unstructured":"Wachter, M.D., Matton, M., Demuynck, K., Wambacq, P., Cools, R., Compernolle, D.V.: Template-Based Continuous Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing\u00a015(4), 1377\u20131390 (2007)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"2","key":"13_CR16","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L.R. Rabiner","year":"1989","unstructured":"Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE\u00a077(2), 257\u2013286 (1989)","journal-title":"Proceedings of the IEEE"},{"key":"13_CR17","unstructured":"http:\/\/www.nuance.com\/devicecontrol\/ (accessed July 4, 2009)"},{"key":"13_CR18","unstructured":"http:\/\/www.gartner.com\/ (accessed July 4, 2009)"},{"key":"13_CR19","unstructured":"Delaney, B.: Reduced Energy Consumption and Improved Accuracy for Distributed Speech Recognition in Wireless Environments. Ph.D. Thesis, Georgia Institute of Technology (2004)"},{"issue":"1","key":"13_CR20","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1145\/371127.371166","volume":"8","author":"B. Suhm","year":"2001","unstructured":"Suhm, B., Myers, B., Waibel, A.: Multi-Modal Error Correction for Speech User Interfaces. ACM Transactions on Computer Human Interaction\u00a08(1), 60\u201398 (2001)","journal-title":"ACM Transactions on Computer Human Interaction"},{"key":"13_CR21","doi-asserted-by":"crossref","unstructured":"Zhou, B., Dechelotte, D., Gao, Y.: Two-Way Speech-to-Speech Translation on Handheld Devices. In: Proceedings of ICSLP 2004, Jeju Island, Korea (2004)","DOI":"10.21437\/Interspeech.2004-55"},{"key":"13_CR22","unstructured":"Hsu, B.-J., Mahajan, M., Acero, A.: Multimodal Text Entry on Mobile Devices. In: Automatic Speech Recognition and Understanding (ASRU), San Juan, Puerto Rico (2005)"},{"key":"13_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-1-84800-143-5_1","volume-title":"Automatic Speech Recognition on Mobile Devices and Over Communication Networks","author":"Z.-H. Tan","year":"2008","unstructured":"Tan, Z.-H., Varga, I.: Networked, Distributed and Embedded Speech Recognition: An Overview. In: Tan, Z.-H., Lindberg, B. (eds.) Automatic Speech Recognition on Mobile Devices and Over Communication Networks, pp. 1\u201323. Springer, London (2008)"},{"key":"13_CR24","doi-asserted-by":"publisher","DOI":"10.1002\/0470024720","volume-title":"Speech Recognition Over Digital Channels","author":"A. Peinado","year":"2006","unstructured":"Peinado, A., Segura, J.C.: Speech Recognition Over Digital Channels. Wiley, Chichester (2006)"},{"issue":"8","key":"13_CR25","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1109\/TSA.2002.808141","volume":"10","author":"A. Bernard","year":"2002","unstructured":"Bernard, A., Alwan, A.: Low-Bitrate Distributed Speech Recognition for Packet-Based and Wireless Communication. IEEE Trans. on Speech and Audio Processing\u00a010(8), 570\u2013579 (2002)","journal-title":"IEEE Trans. on Speech and Audio Processing"},{"key":"13_CR26","doi-asserted-by":"publisher","first-page":"1435","DOI":"10.1016\/j.specom.2006.03.007","volume":"48","author":"V. Ion","year":"2006","unstructured":"Ion, V., Haeb-Umbach, R.: Uncertainty Decoding for Distributed Speech Recognition over Error-Prone Networks. Speech Communication\u00a048, 1435\u20131446 (2006)","journal-title":"Speech Communication"},{"key":"13_CR27","doi-asserted-by":"crossref","unstructured":"James, A.B., Milner, B.P.: An Analysis of Interleavers for Robust Speech Recognition in Burst-Like Packet Loss. In: Proc. ICASSP, Montreal, Canada (2004)","DOI":"10.1109\/ICASSP.2004.1326120"},{"issue":"4","key":"13_CR28","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1109\/TASL.2006.889799","volume":"15","author":"Z.-H. Tan","year":"2007","unstructured":"Tan, Z.-H., Dalsgaard, P., Lindberg, B.: Exploiting Temporal Correlation of Speech for Error-Robust and Bandwidth-Flexible Distributed Speech Recognition. IEEE Transactions on Audio, Speech and Language Processing\u00a015(4), 1391\u20131403 (2007)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"1","key":"13_CR29","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/TASL.2006.876880","volume":"15","author":"B. Milner","year":"2007","unstructured":"Milner, B., Shao, X.: Prediction of Fundamental Frequency and Voicing from Mel-Frequency Cepstral Coefficients for Unconstrained Speech Reconstruction. IEEE Transactions on Audio, Speech and Language Processing\u00a015(1), 24\u201333 (2007)","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"13_CR30","unstructured":"ETSI Standard ES 201 108; Distributed Speech Recognition; Front-end Feature Extraction Algorithm; Compression Algorithm, v1.1.2 (2000)"},{"key":"13_CR31","unstructured":"ETSI Standard ES 202 050: Distributed Speech Recognition; Advanced Front-End Feature Extraction Algorithm; Compression Algorithm (2002)"},{"key":"13_CR32","unstructured":"ETSI Standard ES 202 211: Distributed Speech Recognition; Extended Front-End Feature Extraction Algorithm; Compression Algorithm, Back-End Speech Reconstruction Algorithm (2003)"},{"key":"13_CR33","unstructured":"ETSI Standard ES 202 212: Distributed Speech Recognition; Extended Advanced Front-End Feature Extraction Algorithm; Compression Algorithm, Back-End Speech Reconstruction Algorithm (2003)"},{"key":"13_CR34","unstructured":"3GPP TS 26.243: ANSI C Code for the Fixed-Point Distributed Speech Recognition Extended Advanced Front-End (2004)"},{"key":"13_CR35","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/j.specom.2009.01.010","volume":"51","author":"L. Zouari","year":"2009","unstructured":"Zouari, L., Chollet, G.: Efficient Codebooks for Fast and Accurate Low Resource ASR Systems. Speech Communication\u00a051, 732\u2013743 (2009)","journal-title":"Speech Communication"},{"key":"13_CR36","doi-asserted-by":"crossref","unstructured":"Huggins-Daines, D., Kumar, M., Chan, A., Black, A.W., Ravishankar, M., Rudnicky, A.I.: POCKETSPHINX: A Free, Real-Time Continuous Speech Recognition System for Hand-Held Devices. In: Proc. ICASSP 2006, Toulouse, France (May 2006)","DOI":"10.1109\/ICASSP.2006.1659988"},{"key":"13_CR37","unstructured":"Etoh, M.: Cellular Phones as Information Hubs. In: Proc. Of ACM SIGIR Workshop on Mobile Information Retrieval, Singapore (2008)"},{"key":"13_CR38","volume-title":"Digital Signal Processing for In-Vehicle and Mobile Systems 2","author":"H. Xu","year":"2006","unstructured":"Xu, H., Tan, Z.-H., Dalsgaard, P., Mattethat, R., Lindberg, B.: A Configurable Distributed Speech Recognition System. In: Abut, H., Hansen, J.H.L., Takeda, K. (eds.) Digital Signal Processing for In-Vehicle and Mobile Systems 2. Springer, New York (2006)"},{"key":"13_CR39","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-540-69369-7_17","volume-title":"Perception in Multimodal Dialogue Systems","author":"D. Zaykovskiy","year":"2008","unstructured":"Zaykovskiy, D., Schmitt, A.: Deploying DSR Technology on Today\u2019s Mobile Phones: A Feasibility Study. In: Andr\u00e9, E., Dybkj\u00e6r, L., Minker, W., Neumann, H., Pieraccini, R., Weber, M. (eds.) PIT 2008. LNCS (LNAI), vol.\u00a05078, pp. 145\u2013155. Springer, Heidelberg (2008)"},{"key":"13_CR40","doi-asserted-by":"crossref","unstructured":"Lamere, P., Kwok, P., Walker, W., Gouvea, E., Singh, R., Raj, B., Wolf, P.P.: Design of the CMU Sphinx-4 Decoder. In: Proc. of Eurospeech (2003)","DOI":"10.21437\/Eurospeech.2003-382"},{"key":"13_CR41","unstructured":"http:\/\/www.voicesearchconference.com\/ (accessed July 4, 2009)"},{"key":"13_CR42","doi-asserted-by":"crossref","unstructured":"James, C.L., Reischel, K.M.: Text Input for Mobile Devices: Comparing Model Prediction to Actual Performance. In: Proceedings of the SIGCHI conference on Human factors in computing systems (2001)","DOI":"10.1145\/365024.365300"},{"key":"13_CR43","unstructured":"Kolsch, M., Turk, M.: Keyboards without Keyboards: A Survey of Virtual Keyboards. University of California at Santa Barbara Technical Report (2002)"},{"key":"13_CR44","doi-asserted-by":"crossref","unstructured":"Vertanen, K., Kristensson, P.O.: Parakeet: a continuous speech recognition system for mobile touch-screen devices. In: ACM IUI 2009, Sanibel Island, Florida, USA (2009)","DOI":"10.1145\/1502650.1502685"},{"issue":"2","key":"13_CR45","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1207\/S15327051HCI172&3_2","volume":"17","author":"I.S. MacKenzie","year":"2002","unstructured":"MacKenzie, I.S., Soukoreff, R.W.: Text Entry for Mobile Computing: Models and Methods, Theory and Practice. Human Computer Interaction\u00a017(2), 147\u2013198 (2002)","journal-title":"Human Computer Interaction"},{"key":"13_CR46","doi-asserted-by":"crossref","unstructured":"Silfverberg, M., MacKenzie, I.S., Korhonen, P.: Predicting Text Entry Speed on Mobile Phones. In: Proceedings of the CHI 2000 Conference on Human Factors in Computing Systems (2000)","DOI":"10.1145\/332040.332044"},{"key":"13_CR47","volume-title":"Human-computer interface design guidelines","author":"C.M. Brown","year":"1988","unstructured":"Brown, C.M.: Human-computer interface design guidelines. Ablex Publishing, Norwood (1988)"},{"key":"13_CR48","doi-asserted-by":"crossref","unstructured":"Karat, C.M., Halverson, C., Horn, D., Karat, J.: Patterns of Entry and Correction in Large Vocabulary Continuous Speech Recognition Systems. In: CHI 1999 Conference Proceedings, pp. 568\u2013575 (1999)","DOI":"10.1145\/302979.303160"},{"key":"13_CR49","doi-asserted-by":"crossref","unstructured":"Besacier, L., Bergamini, C., Vaufreydaz, D., Castelli, E.: The Effect of Speech and Audio Compression on Speech Recognition Performance. In: IEEE Multimedia Signal Processing Workshop, Cannes, France (2001)","DOI":"10.1109\/MMSP.2001.962750"},{"key":"13_CR50","unstructured":"Hirsch, H.G., Pearce, D.: The Aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditions. In: ISCA ITRW ASR 2000, Paris, France (2000)"},{"key":"13_CR51","doi-asserted-by":"crossref","unstructured":"Kiss, I.: A Comparison of Distributed and Network Speech Recognition for Mobile Communication Systems. In: Proc. ICSLP, Beijing, China (2000)","DOI":"10.21437\/ICSLP.2000-798"},{"issue":"5","key":"13_CR52","doi-asserted-by":"publisher","first-page":"1047","DOI":"10.1109\/TASL.2008.925879","volume":"16","author":"V. Ion","year":"2008","unstructured":"Ion, V., Haeb-Umbach, R.: A Novel Uncertainty Decoding Rule with Applications to Transaction Error Robust Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing\u00a016(5), 1047\u20131060 (2008)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"issue":"4","key":"13_CR53","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1109\/TASL.2008.920891","volume":"16","author":"C.-Y. Wan","year":"2008","unstructured":"Wan, C.-Y., Lee, L.-S.: Histogram-Based Quantization for Robust and\/or Distributed Speech Recognition. IEEE Transactions on Audio, Speech, and Language Processing\u00a016(4), 859\u2013873 (2008)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"13_CR54","doi-asserted-by":"crossref","unstructured":"Tan, Z.-H., Lindberg, B.: A Posteriori SNR Weighted Energy Based Variable Frame Rate Analysis for Speech Recognition. In: Proc. Interspeech, Brisbane, Australia (2008)","DOI":"10.21437\/Interspeech.2008-297"},{"key":"13_CR55","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/S0167-6393(03)00048-7","volume":"41","author":"A. Peinado","year":"2003","unstructured":"Peinado, A., Sanchez, V., Perez-Cordoba, J., de la Torre, A.: HMM-based channel error mitigation and its application to distributed speech recognition. Speech Communication\u00a041, 549\u2013561 (2003)","journal-title":"Speech Communication"},{"issue":"3","key":"13_CR56","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1109\/TCE.2006.1706471","volume":"52","author":"H. Chung","year":"2006","unstructured":"Chung, H., Chung, I.: Memory Efficient and Fast Speech Recognition System for Low Resource Mobile Devices. IEEE Transactions on Consumer Electronics\u00a052(3), 792\u2013796 (2006)","journal-title":"IEEE Transactions on Consumer Electronics"},{"key":"13_CR57","unstructured":"Giammarini, M., Orcioni, S., Conti, M.: Computational Complexity Estimate of a DSR Front-End compliant to ETSI Standard ES 202 212. In: WISES 2009, Seventh Workshop on Intelligent Solutions in Embedded Systems, Ancona, Italy (2009)"},{"key":"13_CR58","doi-asserted-by":"crossref","unstructured":"Bacchiani, M., Beaufays, F., Schalkwyk, J., Schuster, M., Strope, B.: Deploying GOOG-411: Early Lessons in Data, Measurement, and Testing. In: Proceedings of ICASSP 2008, Las Vegas, USA (2008)","DOI":"10.1109\/ICASSP.2008.4518846"}],"container-title":["Lecture Notes in Computer Science","Mobile Multimedia Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-12349-8_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T05:59:06Z","timestamp":1685512746000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-12349-8_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642123481","9783642123498"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-12349-8_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}