---
title: "SLT 2016 — all accepted papers with summaries and citations"
description: "All 105 papers of SLT 2016 · page 1 of 2, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [SLT](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/) / [2016](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/) / papers

# SLT 2016: all accepted papers

105 papers · page 1 of 2 · the most cited first · [← SLT 2016](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/)

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/page/2/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/page/2/)

1. **[Deep neural network-based speaker embeddings for end-to-end speaker verification ↗](https://doi.org/10.1109/slt.2016.7846260)**David Snyder, Pegah Ghahremani, Daniel Povey et al.*352 citations*
2. **[End-to-End attention based text-dependent speaker verification ↗](https://doi.org/10.1109/slt.2016.7846261)**Shi-Xiong Zhang, Zhuo Chen, Yong Hui Zhao et al.*155 citations*
3. **[Intent detection using semantically enriched word embeddings ↗](https://doi.org/10.1109/slt.2016.7846297)**Joo-Kyung Kim, Gökhan Tür, Aslı Çelikyılmaz et al.*100 citations*
4. **[Discriminative multiple sound source localization based on deep neural networks using independent location model ↗](https://doi.org/10.1109/slt.2016.7846325)**Ryu Takeda, Kazunori Komatani*93 citations*
5. **[Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting ↗](https://doi.org/10.1109/slt.2016.7846306)**Ming Sun, Anirudh Raju, George Tucker et al.*87 citations*
6. **[The MGB-2 challenge: Arabic multi-dialect broadcast media recognition](https://md.research.elamur.ai/free/en/papers/ali-2016-mgb-2-challenge-arabic-multi/)**Ahmed M. Abdelatty Ali, Peter Bell, James Glass et al.*87 citations · our summary*
7. **[Very deep convolutional neural networks for robust speech recognition ↗](https://doi.org/10.1109/slt.2016.7846307)**Yanmin Qian, Philip C. Woodland*82 citations*
8. **[An overview of end-to-end language understanding and dialog management for personal digital assistants ↗](https://doi.org/10.1109/slt.2016.7846294)**Ruhi Sarikaya, P. A. Crook, Alex Marin et al.*71 citations*
9. **[Discriminative acoustic word embeddings: Tecurrent neural network-based approaches ↗](https://doi.org/10.1109/slt.2016.7846310)**Shane Settle, Karen Livescu*68 citations*
10. **[Speech vs. text: A comparative analysis of features for depression detection systems ↗](https://doi.org/10.1109/slt.2016.7846256)**Michelle Renee Morales, Rivka Levitan*68 citations*
11. **[Speech enhancement using Long Short-Term Memory based recurrent Neural Networks for noise robust Speaker Verification ↗](https://doi.org/10.1109/slt.2016.7846281)**Morten Kolbæk, Zheng‐Hua Tan, Jesper Jensen*63 citations*
12. **[Recognizing emotions in spoken dialogue with hierarchically fused acoustic and lexical features ↗](https://doi.org/10.1109/slt.2016.7846319)**Leimin Tian, Johanna D. Moore, Catherine Lai*60 citations*
13. **[Syntax or semantics? knowledge-guided joint semantic frame parsing ↗](https://doi.org/10.1109/slt.2016.7846288)**Yun-Nung Chen, Dilek Hakanni-Tur, Gökhan Tür et al.*52 citations*
14. **[QCRI advanced transcription system (QATS) for the Arabic Multi-Dialect Broadcast media recognition: MGB-2 challenge ↗](https://doi.org/10.1109/slt.2016.7846279)**Sameer Khurana, Ahmed M. Abdelatty Ali*51 citations*
15. **[The fifth dialog state tracking challenge ↗](https://doi.org/10.1109/slt.2016.7846311)**Seokhwan Kim, Luis Fernando D’Haro, Rafael E. Banchs et al.*49 citations*
16. **[Jointly learning to align and convert graphemes to phonemes with neural attention models ↗](https://doi.org/10.1109/slt.2016.7846248)**Shubham Toshniwal, Karen Livescu*41 citations*
17. **[Further optimisations of constant Q cepstral processing for integrated utterance and text-dependent speaker verification ↗](https://doi.org/10.1109/slt.2016.7846262)**Héctor Delgado, Massimiliano Todisco, Md Sahidullah et al.*36 citations*
18. **[A prioritized grid long short-term memory RNN for speech recognition ↗](https://doi.org/10.1109/slt.2016.7846305)**Wei-Ning Hsu, Yu Zhang, James Glass*34 citations*
19. **[Punctuated transcription of multi-genre broadcasts using acoustic and lexical approaches ↗](https://doi.org/10.1109/slt.2016.7846300)**Ondřej Klejch, Peter Bell, Steve J. Renals*34 citations*
20. **[Modelling speaker and channel variability using deep neural networks for robust speaker verification ↗](https://doi.org/10.1109/slt.2016.7846264)**Gautam Bhattacharya, Jahangir Alam, Patrick Kenn et al.*31 citations*
21. **[A multichannel convolutional neural network for cross-language dialog state tracking ↗](https://doi.org/10.1109/slt.2016.7846318)**Hongjie Shi, Takashi Ushio, Mitsuru Endo et al.*30 citations*
22. **[Quaternion Neural Networks for Spoken Language Understanding ↗](https://doi.org/10.1109/slt.2016.7846290)**Titouan Parcollet, Mohamed Morchid, Pierre-Michel Bousquet et al.*30 citations*
23. **[Towards acoustic model unification across dialects ↗](https://doi.org/10.1109/slt.2016.7846328)**Mohamed G. Elfeky, Meysam Bastani, Xavier Velez et al.*30 citations*
24. **[Batch-normalized joint training for DNN-based distant speech recognition ↗](https://doi.org/10.1109/slt.2016.7846241)**Mirco Ravanelli, Philémon Brakel, Maurizio Omologo et al.*28 citations*
25. **[Look, listen, and decode: Multimodal speech recognition with images ↗](https://doi.org/10.1109/slt.2016.7846320)**Felix Sun, David F. Harwath, James Glass*26 citations*
26. **[Code-switching detection using multilingual DNNS ↗](https://doi.org/10.1109/slt.2016.7846326)**Emre Yılmaz, Henk van den Heuvel, David A. van Leeuwen*22 citations*
27. **[Development of the MIT ASR system for the 2016 Arabic Multi-genre Broadcast Challenge ↗](https://doi.org/10.1109/slt.2016.7846280)**Tuka Alhanai, Wei-Ning Hsu, James Glass*22 citations*
28. **[Optimizing neural network hyperparameters with Gaussian processes for dialog act classification ↗](https://doi.org/10.1109/slt.2016.7846296)**Franck Dernoncourt, Ji Young Lee*22 citations*
29. **[Dialog state tracking with attention-based sequence-to-sequence learning ↗](https://doi.org/10.1109/slt.2016.7846317)**Takaaki Hori, Hai Wang, Chiori Hori et al.*18 citations*
30. **[LIUM ASR systems for the 2016 Multi-Genre Broadcast Arabic challenge ↗](https://doi.org/10.1109/slt.2016.7846278)**Natalia Tomashenko, Kévin Vythelingum, Anthony Rousseau et al.*18 citations*
31. **[Learning utterance-level normalisation using Variational Autoencoders for robust automatic speech recognition ↗](https://doi.org/10.1109/slt.2016.7846243)**Shawn Tan, Khe Chai Sim*18 citations*
32. **[Phonetic content impact on Forensic Voice Comparison ↗](https://doi.org/10.1109/slt.2016.7846267)**Ajili. Moez, Jean-François Bonastre, Waad Ben Kheder et al.*18 citations*
33. **[Voice search language model adaptation using contextual information ↗](https://doi.org/10.1109/slt.2016.7846273)**Justin Scheiner, Ian Williams, Petar S. Aleksic*18 citations*
34. **[Performance monitoring for automatic speech recognition in noisy multi-channel environments ↗](https://doi.org/10.1109/slt.2016.7846244)**Bernd T. Meyer, Sri Harish Mallidi, Angel Mario Castro Martínez et al.*17 citations*
35. **[Contextual language model adaptation using dynamic classes ↗](https://doi.org/10.1109/slt.2016.7846301)**Lucy Vasserman, Ben Haynor, Petar S. Aleksic*16 citations*
36. **[Speaker independent diarization for child language environment analysis using deep neural networks ↗](https://doi.org/10.1109/slt.2016.7846253)**Maryam Najafian, John H. L. Hansen*16 citations*
37. **[F0 transformation techniques for statistical voice conversion with direct waveform modification with spectral differential ↗](https://doi.org/10.1109/slt.2016.7846338)**Kazuhiro Kobayashi, Tomoki Toda, Satoshi Nakamura*15 citations*
38. **[Hierarchical attention model for improved machine comprehension of spoken content ↗](https://doi.org/10.1109/slt.2016.7846270)**Wei Fang, Juei-Yang Hsu, Hung-yi Lee et al.*15 citations*
39. **[Multilingual BLSTM and speaker-specific vector adaptation in 2016 but babel system ↗](https://doi.org/10.1109/slt.2016.7846330)**Martin Karafiát, Murali Karthick Baskar, Pavel Matějka et al.*15 citations*
40. **[Automatic turn segmentation for Movie & TV subtitles ↗](https://doi.org/10.1109/slt.2016.7846272)**Pierre Lison, Raveesh Meena*14 citations*
41. **[Neural dialog state tracker for large ontologies by attention mechanism ↗](https://doi.org/10.1109/slt.2016.7846314)**Youngsoo Jang, Jiyeon Ham, Byung-Jun Lee et al.*14 citations*
42. **[Automated structure discovery and parameter tuning of neural network language model based on evolution strategy ↗](https://doi.org/10.1109/slt.2016.7846334)**Tomohiro Tanaka, Takafumi Moriya, Takahiro Shinozaki et al.*13 citations*
43. **[Toward human-assisted lexical unit discovery without text resources ↗](https://doi.org/10.1109/slt.2016.7846246)**Chris D. Bartels, Wen Wang, Vikramjit Mitra et al.*13 citations*
44. **[DialPort: Connecting the spoken dialog research community to real user data ↗](https://doi.org/10.1109/slt.2016.7846249)**Tiancheng Zhao, Kyusong Lee, Maxine Eskénazi*12 citations*
45. **[Iterative training of a DPGMM-HMM acoustic unit recognizer in a zero resource scenario ↗](https://doi.org/10.1109/slt.2016.7846245)**Michael C. Heck, Sakriani Sakti, Satoshi Nakamura*12 citations*
46. **[Audio-visual speech activity detection in a two-speaker scenario incorporating depth information from a profile or frontal view ↗](https://doi.org/10.1109/slt.2016.7846321)**Spyridon Thermos, Gerasimos Potamianos*11 citations*
47. **[Blind speech segmentation using spectrogram image-based features and Mel cepstral coefficients ↗](https://doi.org/10.1109/slt.2016.7846324)**Adriana Stan, Cassia Valentini-Botinhao, Bogdan Orza et al.*11 citations*
48. **[Extractive speech summarization leveraging convolutional neural network techniques ↗](https://doi.org/10.1109/slt.2016.7846259)**Chun-I Tsai, Hsiao-Tsung Hung, Kuan‐Yu Chen et al.*11 citations*
49. **[High quality agreement-based semi-supervised training data for acoustic modeling ↗](https://doi.org/10.1109/slt.2016.7846323)**Félix de Chaumont Quitry, Asa Oines, Pedro J. Moreno et al.*11 citations*
50. **[A robust diarization system for measuring dominance in Peer-Led Team Learning groups ↗](https://doi.org/10.1109/slt.2016.7846283)**Harishchandra Dubey, Abhijeet Sangwan, John H. L. Hansen*10 citations*
51. **[Automatic optimization of data perturbation distributions for multi-style training in speech recognition ↗](https://doi.org/10.1109/slt.2016.7846240)**Mortaza Doulaty, Richard Cameron Rose, Olivier Siohan*10 citations*
52. **[Dynamic adjustment of language models for automatic speech recognition using word similarity ↗](https://doi.org/10.1109/slt.2016.7846299)**Anna Currey, Irina Illina, Dominique Fohr*10 citations*
53. **[Environmentally robust audio-visual speaker identification ↗](https://doi.org/10.1109/slt.2016.7846282)**Lea Schönherr, Dennis Orth, Martin Heckmann et al.*10 citations*
54. **[Parallel Long Short-Term Memory for multi-stream classification ↗](https://doi.org/10.1109/slt.2016.7846268)**Mohamed Bouaziz, Mohamed Morchid, Richard Dufour et al.*10 citations*
55. **[Approaches for language identification in mismatched environments ↗](https://doi.org/10.1109/slt.2016.7846286)**Shahan C. Nercessian, Pedro A. Torres‐Carrasquillo, Gabriel Martinez-Montes*9 citations*
56. **[Unsupervised context learning for speech recognition ↗](https://doi.org/10.1109/slt.2016.7846302)**Assaf Hurwitz Michaely, Mohammadreza Ghodsi, Zelin Wu et al.*9 citations*
57. **[Automatic plagiarism detection for spoken responses in an assessment of English language proficiency ↗](https://doi.org/10.1109/slt.2016.7846254)**Xinhao Wang, Keelan Evanini, James V. Bruno et al.*8 citations*
58. **[Deep neural network driven mixture of PLDA for robust i-vector speaker verification ↗](https://doi.org/10.1109/slt.2016.7846263)**Na Li, Man‐Wai Mak, Jen‐Tzung Chien*8 citations*
59. **[Analysis of the DNN-based SRE systems in multi-language conditions ↗](https://doi.org/10.1109/slt.2016.7846265)**Ondřej Novotný, Pavel Matějka, Ondřej Glembek et al.*7 citations*
60. **[Deep learning with maximal figure-of-merit cost to advance multi-label speech attribute detection ↗](https://doi.org/10.1109/slt.2016.7846308)**Ivan Kukanov, Ville Hautamäki, Sabato Marco Siniscalchi et al.*7 citations*
61. **[End-to-end training approaches for discriminative segmental models ↗](https://doi.org/10.1109/slt.2016.7846309)**Hao Tang, Weiran Wang, Kevin Gimpel et al.*7 citations*
62. **[Abstractive headline generation for spoken content by attentive recurrent neural networks with ASR error modeling ↗](https://doi.org/10.1109/slt.2016.7846258)**Lang-Chi Yu, Hung-yi Lee, Lin-shan Lee*6 citations*
63. **[DNN adaptation for recognition of children speech through automatic utterance selection ↗](https://doi.org/10.1109/slt.2016.7846331)**Marco Matassoni, Daniele Falavigna, Diego Giuliani*6 citations*
64. **[Multimodal deep neural nets for detecting humor in TV sitcoms ↗](https://doi.org/10.1109/slt.2016.7846293)**Dario Bertero, Pascale Fung*6 citations*
65. **[Semantic model for fast tagging of word lattices ↗](https://doi.org/10.1109/slt.2016.7846295)**Leonid Velikovich*6 citations*
66. **[A study of speech distortion conditions in real scenarios for speech processing applications ↗](https://doi.org/10.1109/slt.2016.7846239)**Dayana Ribas, Emmanuel Vincent A, José Ramón Calvo*5 citations*
67. **[Evaluation and calibration of Lombard effects in speaker verification ↗](https://doi.org/10.1109/slt.2016.7846266)**Finnian Kelly, John H. L. Hansen*5 citations*
68. **[Multi-lingual deep neural networks for language recognition ↗](https://doi.org/10.1109/slt.2016.7846285)**Luis Murphy Marcos, Frederick Richardson*5 citations*
69. **[Analysis of user behavior with multimodal virtual customer service agents ↗](https://doi.org/10.1109/slt.2016.7846322)**Ian Beaver, Cynthia Freeman*4 citations*
70. **[Automated optimization of decoder hyper-parameters for online LVCSR ↗](https://doi.org/10.1109/slt.2016.7846303)**Akshay Chandrashekaran, Ian Richard Lane*4 citations*
71. **[Deep bottleneck features and sound-dependent i-vectors for simultaneous recognition of speech and environmental sounds ↗](https://doi.org/10.1109/slt.2016.7846242)**Sakriani Sakti, Seiji Kawanishi, Graham Neubig et al.*4 citations*
72. **[Entropy-based pruning of hidden units to reduce DNN parameters ↗](https://doi.org/10.1109/slt.2016.7846335)**Gautam Mantena, Khe Chai Sim*4 citations*
73. **[Pre-filtered dynamic time warping for posteriorgram based keyword search ↗](https://doi.org/10.1109/slt.2016.7846292)**Gözde Çetinkaya, Batuhan Gündoğdu, Murat Saraçlar*4 citations*
74. **[Recurrent convolutional neural networks for structured speech act tagging ↗](https://doi.org/10.1109/slt.2016.7846312)**Takashi Ushio, Hongjie Shi, Mitsuru Endo et al.*4 citations*
75. **[Sequence training and adaptation of highway deep neural networks ↗](https://doi.org/10.1109/slt.2016.7846304)**Liang Lu*4 citations*
76. **[The NDSC transcription system for the 2016 multi-genre broadcast challenge ↗](https://doi.org/10.1109/slt.2016.7846276)**Xukui Yang, Dan Qu, Wenlin Zhang et al.*4 citations*
77. **[Towards a virtual personal assistant based on a user-defined portfolio of multi-domain vocal applications ↗](https://doi.org/10.1109/slt.2016.7846252)**Tatiana Ekeinhor-Komi, Jean-Léon Bouraoui, Romain Laroche et al.*4 citations*
78. **[Weakly supervised user intent detection for multi-domain dialogues ↗](https://doi.org/10.1109/slt.2016.7846250)**Ming Sun, Aasish Pappu, Yun-Nung Chen et al.*4 citations*
79. **[Attribute based shared hidden layers for cross-language knowledge transfer ↗](https://doi.org/10.1109/slt.2016.7846327)**Vipul Arora, Aditi Lahiri, Henning Reet*3 citations*
80. **[Deep neural network based acoustic model parameter reduction using manifold regularized low rank matrix factorization ↗](https://doi.org/10.1109/slt.2016.7846333)**Hoon Chung, Jeom Ja Kang, Ki Young Park et al.*3 citations*
81. **[I-Vector estimation as auxiliary task for Multi-Task Learning based acoustic modeling for automatic speech recognition ↗](https://doi.org/10.1109/slt.2016.7846237)**Gueorgui Pironkov, Stéphane Dupont, Thierry Dutoit*3 citations*
82. **[Influence of corpus size and content on the perceptual quality of a unit selection MaryTTS voice ↗](https://doi.org/10.1109/slt.2016.7846336)**Florian Hinterleitner, Benjamin Weiß, Sebastian Möller*3 citations*
83. **[Low-rank bases for factorized hidden layer adaptation of DNN acoustic models ↗](https://doi.org/10.1109/slt.2016.7846332)**Lahiru Samarakoon, Khe Chai Sim*3 citations*
84. **[Median-based generation of synthetic speech durations using a non-parametric approach ↗](https://doi.org/10.1109/slt.2016.7846337)**Srikanth Ronanki, Oliver Watts, Simon King et al.*3 citations*
85. **[Robust utterance classification using multiple classifiers in the presence of speech recognition errors ↗](https://doi.org/10.1109/slt.2016.7846291)**Takeshi Homma, Kazuaki Shima, Takuya Matsumoto*3 citations*
86. **[The MSIIP system for dialog state tracking challenge 5 ↗](https://doi.org/10.1109/slt.2016.7846313)**Ying Su, Miao Li, Ji Yi Wu*3 citations*
87. **[Adaptation of SVM for MIL for inferring the polarity of movies and movie reviews ↗](https://doi.org/10.1109/slt.2016.7846274)**Joana Correia, Isabel M. Trancoso, Bhiksha Raj*2 citations*
88. **[BBN technologies' OpenSAD system ↗](https://doi.org/10.1109/slt.2016.7846238)**Scott Novotney, Damianos Karakos, Jan Silovský et al.*2 citations*
89. **[Boosting performance on low-resource languages by standard corpora: An analysis ↗](https://doi.org/10.1109/slt.2016.7846329)**František Grézl, Martin Karafiát*2 citations*
90. **[Comparing speaker independent and speaker adapted classification for word prominence detection ↗](https://doi.org/10.1109/slt.2016.7846271)**Andrea Schnall, Martin Heckmann*2 citations*
91. **[Incrementally learn the relevance of words in a dictionary for spoken language acquisition ↗](https://doi.org/10.1109/slt.2016.7846257)**Vincent Renkens, Vikrant Singh Tomar, Hugo Van hamme*2 citations*
92. **[Tracking dialog states using an Author-Topic based representation ↗](https://doi.org/10.1109/slt.2016.7846316)**Richard Dufour, Mohamed Morchid, Titouan Parcollet*2 citations*
93. **[A factor analysis model of sequences for language recognition ↗](https://doi.org/10.1109/slt.2016.7846287)**Mohamed Kamal Omar*1 citation*
94. **[A log-linear weighting approach in the Word2vec space for spoken language understanding ↗](https://doi.org/10.1109/slt.2016.7846289)**Killian Janod, Mohamed Morchid, Richard Dufour et al.*1 citation*
95. **[An unsupervised vocabulary selection technique for Chinese automatic speech recognition ↗](https://doi.org/10.1109/slt.2016.7846298)**Yike Zhang, Pengyuan Zhang, Li Ta et al.*1 citation*
96. **[Improving multi-stream classification by mapping sequence-embedding in a high dimensional space ↗](https://doi.org/10.1109/slt.2016.7846269)**Mohamed Bouaziz, Mohamed Morchid, Richard Dufour et al.*1 citation*
97. **[Learning dialogue dynamics with the method of moments ↗](https://doi.org/10.1109/slt.2016.7846251)**Merwan Barlier, Romain Laroche, Olivier Pietquin*1 citation*
98. **[Unsupervised k-means clustering based out-of-set candidate selection for robust open-set language recognition ↗](https://doi.org/10.1109/slt.2016.7846284)**Qian Zhang, John H. L. Hansen*1 citation*
99. **[A nonparametric Bayesian approach for automatic discovery of a lexicon and acoustic units ↗](https://doi.org/10.1109/slt.2016.7846247)**Amir Hossein Harati Nejad Torbati, Joseph Picone
100. **[Improved prediction of the accent gap between speakers of English for individual-based clustering of World Englishes ↗](https://doi.org/10.1109/slt.2016.7846255)**Shiozawa Fumiya, Daisuke Saito, Nobuaki Minematsu

**1** [2](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/page/2/) [next →](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/papers/page/2/)

- [← back to](https://md.research.elamur.ai/free/en/venues/ieee-spoken-language-technology-workshop-slt/2016/) — SLT 2016