Interspeech 2017

844 papers

Online End-of-Turn Detection from Speech Based on Stacked Time-Asynchronous Sequential Networks

Ryo Masumura, Taichi Asami, Hirokazu Masataki, Ryo Ishii, Ryuichiro Higashinaka

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

Qingming Tang, Weiran Wang, Karen Livescu

Parallel Neural Network Features for Improved Tandem Acoustic Modeling

Zoltán Tüske, Wilfried Michel, Ralf Schlüter, Hermann Ney

An Efficient Phone N-Gram Forward-Backward Computation Using Dense Matrix Multiplication

Khe Chai Sim, Arun Narayanan

End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow

Ehsan Variani, Tom Bagby, Erik McDermott, Michiel Bacchiani

Node Pruning Based on Entropy of Weights and Node Activity for Small-Footprint Acoustic Model Based on Deep Neural Networks

Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani

Backstitch: Counteracting Finite-Sample Bias via Negative Steps

Yiming Wang, Vijayaditya Peddinti, Hainan Xu, XiaoHui Zhang, Daniel Povey

A Comparative Evaluation of GMM-Free State Tying Methods for ASR

Tamás Grósz, Gábor Gosztolya, László Tóth

Training Context-Dependent DNN Acoustic Models Using Probabilistic Sampling

Tamás Grósz, Gábor Gosztolya, László Tóth

Ensembles of Multi-Scale VGG Acoustic Models

Michael Heck, Masayuki Suzuki, Takashi Fukuda, Gakuto Kurata, Satoshi Nakamura

Deep Activation Mixture Model for Speech Recognition

Chunyang Wu, Mark J.F. Gales

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

Sercan Ö. Arık, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky

Forward-Backward Convolutional LSTM for Acoustic Modeling

Shigeki Karita, Atsunori Ogawa, Marc Delcroix, Tomohiro Nakatani

Unfolded Deep Recurrent Convolutional Neural Network with Jump Ahead Connections for Acoustic Modeling

Dung T. Tran, Marc Delcroix, Shigeki Karita, Michael Hentschel, Atsunori Ogawa

Residual LSTM: Design of a Deep Recurrent Architecture for Distant Speech Recognition

Jaeyoung Kim, Mostafa El-Khamy, Jungwon Lee

An Exploration of Dropout with LSTMs

Gaofeng Cheng, Vijayaditya Peddinti, Daniel Povey, Vimal Manohar, Sanjeev Khudanpur

Domain Mismatch Modeling of Out-Domain i-Vectors for PLDA Speaker Verification

Md. Hafizur Rahman, Ivan Himawan, David Dean, Sridha Sridharan

A Distribution Free Formulation of the Total Variability Model

Ruchir Travadi, Shrikanth S. Narayanan

Alternative Approaches to Neural Network Based Speaker Verification

Anna Silnova, Lukas Burget, Jan Černocký

Analysis of Score Normalization in Multilingual Speaker Recognition

Pavel Matějka, Ondřej Novotný, Oldřich Plchot, Lukas Burget, Mireia Diez Sánchez

i-Vector DNN Scoring and Calibration for Noise Robust Speaker Verification

Zhili Tan, Man-Wai Mak

Improving the Effectiveness of Speaker Verification Domain Adaptation with Inadequate In-Domain Data

Bengt J. Borgström, Elliot Singer, Douglas Reynolds, Seyed Omid Sadjadi

Extended Variability Modeling and Unsupervised Adaptation for PLDA Speaker Recognition

Alan McCree, Gregory Sell, Daniel Garcia-Romero

Duration Mismatch Compensation Using Four-Covariance Model and Deep Neural Network for Speaker Verification

Pierre-Michel Bousquet, Mickael Rouvier

Deep Speaker Feature Learning for Text-Independent Speaker Verification

Lantian Li, Yixiang Chen, Ying Shi, Zhiyuan Tang, Dong Wang

Speaker Verification via Estimating Total Variability Space Using Probabilistic Partial Least Squares

Chen Chen, Jiqing Han, Yilin Pan

Joint Training of Expanded End-to-End DNN for Text-Dependent Speaker Verification

Hee-soo Heo, Jee-weon Jung, IL-ho Yang, Sung-hyun Yoon, Ha-Jin Yu

Gain Compensation for Fast i-Vector Extraction Over Short Duration

Kong Aik Lee, Haizhou Li

Using Voice Quality Features to Improve Short-Utterance, Text-Independent Speaker Verification Systems

Soo Jin Park, Gary Yeung, Jody Kreiman, Patricia A. Keating, Abeer Alwan

Deep Speaker Embeddings for Short-Duration Speaker Verification

Gautam Bhattacharya, Jahangir Alam, Patrick Kenny

Time-Varying Autoregressions for Speaker Verification in Reverberant Conditions

Ville Vestman, Dhananjaya Gowda, Md. Sahidullah, Paavo Alku, Tomi Kinnunen

DNN i-Vector Speaker Verification with Short, Text-Constrained Test Utterances

Jinghua Zhong, Wenping Hu, Frank K. Soong, Helen Meng

Incorporating Local Acoustic Variability Information into Short Duration Speaker Verification

Jianbo Ma, Vidhyasaharan Sethu, Eliathamby Ambikairajah, Kong Aik Lee

What Does the Speaker Embedding Encode?

Shuai Wang, Yanmin Qian, Kai Yu

Adversarial Network Bottleneck Features for Noise Robust Speaker Verification

Hong Yu, Zheng-Hua Tan, Zhanyu Ma, Jun Guo

End-to-End Text-Independent Speaker Verification with Triplet Loss on Short Utterances

Chunlei Zhang, Kazuhito Koishida

Content Normalization for Text-Dependent Speaker Verification

Subhadeep Dey, Srikanth Madikeri, Petr Motlicek, Marc Ferras

A Generative Model for Score Normalization in Speaker Recognition

Albert Swart, Niko Brümmer

Hybrid Acoustic-Lexical Deep Learning Approach for Deception Detection

Gideon Mendels, Sarah Ita Levitan, Kai-Zhan Lee, Julia Hirschberg

The Sound of Deception — What Makes a Speaker Credible?

Anne Schröder, Simon Stone, Peter Birkholz

Transfer Learning Between Concepts for Human Behavior Modeling: An Application to Sincerity and Deception Prediction

Qinyi Luo, Rahul Gupta, Shrikanth S. Narayanan

Opinion Dynamics Modeling for Movie Review Transcripts Classification with Hidden Conditional Random Fields

Valentin Barriere, Chloé Clavel, Slim Essid

Exploring Dynamic Measures of Stance in Spoken Interaction

Gina-Anne Levow, Richard A. Wright

Inferring Stance from Prosody

Nigel G. Ward, Jason C. Carlson, Olac Fuentes, Diego Castan, Elizabeth E. Shriberg

Automatic Assessment of Non-Native Prosody by Measuring Distances on Prosodic Label Sequences

David Escudero-Mancebo, César González-Ferreras, Lourdes Aguilar, Eva Estebas-Vilaplana

Detection of Mispronunciations and Disfluencies in Children Reading Aloud

Jorge Proença, Carla Lopes, Michael Tjalve, Andreas Stolcke, Sara Candeias

Phonological Feature Based Mispronunciation Detection and Diagnosis Using Multi-Task DNNs and Active Learning

Vipul Arora, Aditi Lahiri, Henning Reetz

Off-Topic Spoken Response Detection Using Siamese Convolutional Neural Networks

Chong Min Lee, Su-Youn Yoon, Xihao Wang, Matthew Mulholland, Ikkyu Choi

Automatic Scoring of Shadowing Speech Based on DNN Posteriors and Their DTW

Junwei Yue, Fumiya Shiozawa, Shohei Toyama, Yutaka Yamauchi, Kayoko Ito

Bidirectional LSTM-RNN for Improving Automated Assessment of Non-Native Children’s Speech

Yao Qian, Keelan Evanini, Xinhao Wang, Chong Min Lee, Matthew Mulholland

The Formant Dynamics of Long Close Vowels in Three Varieties of Swedish

Otto Ewald, Eva Liina Asu, Susanne Schötz

On the Duration of Mandarin Tones

Jing Yang, Yu Zhang, Aijun Li, Li Xu

Phonological Complexity, Segment Rate and Speech Tempo Perception

Leendert Plug, Rachel Smith

Acoustic Properties of Canonical and Non-Canonical Stress in French, Turkish, Armenian and Brazilian Portuguese

Angeliki Athanasopoulou, Irene Vogel, Hossep Dolatian

Disambiguate or not? — The Role of Prosody in Unambiguous and Potentially Ambiguous Anaphora Production in Strictly Mandarin Parallel Structures

Luying Hou, Bert Le Bruyn, René Kager

Heather Kember, Ann-Kathrin Grohe, Katharina Zahner, Bettina Braun, Andrea Weber

Direct Modelling of Magnitude and Phase Spectra for Statistical Parametric Speech Synthesis

Felipe Espic, Cassia Valentini Botinhao, Simon King

Modeling Laryngeal Muscle Activation Noise for Low-Order Physiological Based Speech Synthesis

Rodrigo Manríquez, Sean D. Peterson, Pavel Prado, Patricio Orio, Matías Zañartu

Semi Parametric Concatenative TTS with Instant Voice Modification Capabilities

Alexander Sorin, Slava Shechtman, Asaf Rendel

Reducing Mismatch in Training of DNN-Based Glottal Excitation Models in a Statistical Parametric Text-to-Speech System

Lauri Juvela, Bajibabu Bollepalli, Junichi Yamagishi, Paavo Alku

Speaking Style Conversion from Normal to Lombard Speech Using a Glottal Vocoder and Bayesian GMMs

Ana Ramírez López, Shreyas Seshadri, Lauri Juvela, Okko Rasanen, Paavo Alku

A New Cosine Series Antialiasing Function and its Application to Aliasing-Free Glottal Source Models for Speech and Singing Synthesis

Hideki Kawahara, Ken-Ichi Sakakibara, Masanori Morise, Hideki Banno, Tomoki Toda

The 2016 NIST Speaker Recognition Evaluation

Seyed Omid Sadjadi, Timothée Kheyrkhah, Audrey Tong, Craig Greenberg, Douglas Reynolds

Analysis and Description of ABC Submission to NIST SRE 2016

Oldřich Plchot, Pavel Matějka, Anna Silnova, Ondřej Novotný, Mireia Diez Sánchez

UTD-CRSS Systems for 2016 NIST Speaker Recognition Evaluation

Chunlei Zhang, Fahimeh Bahmaninezhad, Shivesh Ranjan, Chengzhu Yu, Navid Shokouhi

Nuance - Politecnico di Torino’s 2016 NIST Speaker Recognition Evaluation System

Daniele Colibro, Claudio Vair, Emanuele Dalmasso, Kevin Farrell, Gennady Karvitsky

The MIT-LL, JHU and LRDE NIST 2016 Speaker Recognition Evaluation System

Pedro A. Torres-Carrasquillo, Fred Richardson, Shahan Nercessian, Douglas Sturim, William Campbell

The I4U Mega Fusion and Collaboration for NIST Speaker Recognition Evaluation 2016

Kong Aik Lee, SRE’16 I4U Group

Deep Learning-Based Telephony Speech Recognition in the Wild

Kyu J. Han, Seongjun Hahm, Byung-Hak Kim, Jungsuk Kim, Ian Lane

Frame and Segment Level Recurrent Neural Networks for Phone Classification

Martin Ratajczak, Sebastian Tschiatschek, Franz Pernkopf

Stochastic Recurrent Neural Network for Speech Recognition

Jen-Tzung Chien, Chen Shen

Improving Speech Recognition by Revising Gated Recurrent Units

Mirco Ravanelli, Philemon Brakel, Maurizio Omologo, Yoshua Bengio

Highway-LSTM and Recurrent Highway Networks for Speech Recognition

Golan Pundak, Tara N. Sainath

Recurrent Neural Aligner: An Encoder-Decoder Neural Network Model for Sequence to Sequence Mapping

Haşim Sak, Matt Shannon, Kanishka Rao, Françoise Beaufays

Siamese Autoencoders for Speech Style Extraction and Switching Applied to Voice Identification and Conversion

Seyed Hamidreza Mohammadi, Alexander Kain

A Mouth Opening Effect Based on Pole Modification for Expressive Singing Voice Transformation

Luc Ardaillon, Axel Roebel

Sequence-to-Sequence Voice Conversion with Similarity Metric Learned Using Generative Adversarial Networks

Takuhiro Kaneko, Hirokazu Kameoka, Kaoru Hiramatsu, Kunio Kashino

Parallel-Data-Free Many-to-Many Voice Conversion Based on DNN Integrated with Eigenspace Using a Non-Parallel Speech Corpus

Tetsuya Hashimoto, Hidetsugu Uchida, Daisuke Saito, Nobuaki Minematsu

Learning Latent Representations for Speech Generation and Transformation

Wei-Ning Hsu, Yu Zhang, James Glass

Voice Conversion Using Sequence-to-Sequence Learning of Context Posterior Probabilities

Hiroyuki Miyoshi, Yuki Saito, Shinnosuke Takamichi, Hiroshi Saruwatari

Attentive Convolutional Neural Network Based Speech Emotion Recognition: A Study on the Impact of Input Features, Signal Length, and Acted Speech

Michael Neumann, Ngoc Thang Vu

Voice-to-Affect Mapping: Inferences on Language Voice Baseline Settings

Ailbhe Ni Chasaide, Irena Yanushevskaya, Christer Gobl

Capturing Long-Term Temporal Dependencies with Convolutional Networks for Continuous Emotion Recognition

Soheil Khorram, Zakaria Aldeneh, Dimitrios Dimitriadis, Melvin McInnis, Emily Mower Provost

An Investigation of Emotion Prediction Uncertainty Using Gaussian Mixture Regression

Ting Dang, Vidhyasaharan Sethu, Julien Epps, Eliathamby Ambikairajah

Adversarial Auto-Encoders for Speech Based Emotion Recognition

Saurabh Sahu, Rahul Gupta, Ganesh Sivaraman, Wael AbdAlmageed, Carol Espy-Wilson

Speech Emotion Recognition with Emotion-Pair Based Framework Considering Emotion Distribution Information in Dimensional Emotion Space

Xi Ma, Zhiyong Wu, Jia Jia, Mingxing Xu, Helen Meng

A New Model of Final Lowering in Spontaneous Monologue

Kikuo Maekawa

Pashto Intonation Patterns

Luca Rognoni, Judith Bishop, Miriam Corris

Mind the Peak: When Museum is Temporarily Understood as Musical in Australian English

Katharina Zahner, Heather Kember, Bettina Braun

Intonation Facilitates Prediction of Focus Even in the Presence of Lexical Tones

Martin Ho Kwan Ip, Anne Cutler

Comparing Languages Using Hierarchical Prosodic Analysis

Juraj Simko, Antti Suni, Katri Hiovain, Martti Vainio

The Vocative Chant and Beyond: German Calling Melodies Under Routine and Urgent Contexts

Sergio I. Quiroz, Marzena Żygis

Ideal Ratio Mask Estimation Using Deep Neural Networks for Monaural Speech Segregation in Noisy Reverberant Conditions

Xu Li, Junfeng Li, Yonghong Yan

Detecting Overlapped Speech on Short Timeframes Using Deep Learning

Valentin Andrei, Horia Cucu, Corneliu Burileanu

Variational Recurrent Neural Networks for Speech Separation

Jen-Tzung Chien, Kuan-Ting Kuo

Time-Frequency Masking for Blind Source Separation with Preserved Spatial Cues

Shadi Pirhosseinloo, Kostas Kokkinakis

Deep Clustering-Based Beamforming for Separation with Unknown Number of Sources

Takuya Higuchi, Keisuke Kinoshita, Marc Delcroix, Kateřina Žmolíková, Tomohiro Nakatani

A Maximum Likelihood Approach to Deep Neural Network Based Nonlinear Spectral Mapping for Single-Channel Speech Separation

Yannan Wang, Jun Du, Li-Rong Dai, Chin-Hui Lee

Modeling Categorical Perception with the Receptive Fields of Auditory Neurons

Chris Neufeld

Single-Ended Prediction of Listening Effort Based on Automatic Speech Recognition

Rainer Huber, Constantin Spille, Bernd T. Meyer