Interspeech 2016

815 papers

Improved Multilingual Training of Stacked Neural Network Acoustic Models for Low Resource Languages

Tanel Alumäe, Stavros Tsakalidis, Richard Schwartz

Language Adaptive DNNs for Improved Low Resource Speech Recognition

Markus Müller, Sebastian Stüker, Alex Waibel

Improving Under-Resourced Language ASR Through Latent Subword Unit Space Discovery

Marzieh Razavi, Mathew Magimai-Doss

ASR for South Slavic Languages Developed in Almost Automated Way

Jan Nouza, Radek Safarik, Petr Cerva

Analysis of Mismatched Transcriptions Generated by Humans and Machines for Under-Resourced Languages

Van Hai Do, Nancy F. Chen, Boon Pang Lim, Mark Hasegawa-Johnson

An Investigation on Training Deep Neural Networks Using Probabilistic Transcriptions

Amit Das, Mark Hasegawa-Johnson

Multilingual Data Selection for Low Resource Speech Recognition

Samuel Thomas, Kartik Audhkhasi, Jia Cui, Brian Kingsbury, Bhuvana Ramabhadran

Semi-Supervised Training in Deep Learning Acoustic Model

Yan Huang, Yongqiang Wang, Yifan Gong

Semi-Supervised Speaker Adaptation for In-Vehicle Speech Recognition with Deep Neural Networks

Wonkyum Lee, Kyu J. Han, Ian Lane

Recurrent Models for Auditory Attention in Multi-Microphone Distant Speech Recognition

Suyoun Kim, Ian Lane

The Sheffield Wargame Corpus — Day Two and Day Three

Yulan Liu, Charles Fox, Madina Hasan, Thomas Hain

An Investigation on the Use of i-Vectors for Robust ASR

Dimitrios Dimitriadis, Samuel Thomas, Sriram Ganapathy

Microphone Distance Adaptation Using Cluster Adaptive Training for Robust Far Field Speech Recognition

Animesh Prasad, Khe Chai Sim

Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling

Yusuke Fujita, Ryoich Takashima, Takeshi Homma, Masahito Togami

Factorized Linear Input Network for Acoustic Model Adaptation in Noisy Conditions

Dung T. Tran, Marc Delroix, Atsunori Ogawa, Tomohiro Nakatani

Optimization of Speech Enhancement Front-End with Speech Recognition-Level Criterion

Takuya Higuchi, Takuya Yoshioka, Tomohiro Nakatani

Joint Optimization of Denoising Autoencoder and DNN Acoustic Model Based on Multi-Target Learning for Noisy Speech Recognition

Masato Mimura, Shinsuke Sakai, Tatsuya Kawahara

Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition

Erfan Loweimi, Jon Barker, Thomas Hain

Analytical Assessment of Dual-Stream Merging for Noise-Robust ASR

Louis ten Bosch, Bert Cranen, Yang Sun

On the Use of Gaussian Mixture Model Framework to Improve Speaker Adaptation of Deep Neural Network Acoustic Models

Natalia Tomashenko, Yuri Khokhlov, Yannick Estève

Coping with Unseen Data Conditions: Investigating Neural Net Architectures, Robust Features, and Information Fusion for Robust Speech Recognition

Vikramjit Mitra, Horacio Franco

A Novel Research to Artificial Bandwidth Extension Based on Deep BLSTM Recurrent Neural Networks and Exemplar-Based Sparse Representation

Bin Liu, Jianhua Tao

An Iterative Phase Recovery Framework with Phase Mask for Spectral Mapping with an Application to Speech Enhancement

Kehuang Li, Bo Wu, Chin-Hui Lee

SNR-Aware Convolutional Neural Network Modeling for Speech Enhancement

Szu-Wei Fu, Yu Tsao, Xugang Lu

A DNN-HMM Approach to Non-Negative Matrix Factorization Based Speech Enhancement

Ziteng Wang, Xu Li, Xiaofei Wang, Qiang Fu, Yonghong Yan

A priori SNR Estimation Using a Generalized Decision Directed Approach

Aleksej Chinaev, Reinhold Haeb-Umbach

Semi-Supervised Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech

Li Li, Hirokazu Kameoka, Takuya Higuchi, Hiroshi Saruwatari

HMM-Based Speech Enhancement Using Sub-Word Models and Noise Adaptation

Akihiro Kato, Ben Milner

Perception Optimized Deep Denoising AutoEncoders for Speech Enhancement

Prashanth Gurunath Shivakumar, Panayiotis Georgiou

Speech Enhancement in Multiple-Noise Conditions Using Deep Neural Networks

Anurag Kumar, Dinei Florencio

Robust Example Search Using Bottleneck Features for Example-Based Speech Enhancement

Atsunori Ogawa, Shogo Seki, Keisuke Kinoshita, Marc Delcroix, Takuya Yoshioka

A Class-Specific Speech Enhancement for Phoneme Recognition: A Dictionary Learning Approach

Nazreen P.M., A.G. Ramakrishnan, Prasanta Kumar Ghosh

Two-Stage Temporal Processing for Single-Channel Speech Enhancement

Suman Samui, Indrajit Chakrabarti, Soumya Kanti Ghosh

A Novel Risk-Estimation-Theoretic Framework for Speech Enhancement in Nonstationary and Non-Gaussian Noise Conditions

Jishnu Sadasivan, Chandra Sekhar Seelamantula

SNR-Based Progressive Learning of Deep Neural Network for Speech Enhancement

Tian Gao, Jun Du, Li-Rong Dai, Chin-Hui Lee

Novel Subband Autoencoder Features for Non-Intrusive Quality Assessment of Noise Suppressed Speech

Meet H. Soni, Hemant A. Patil

Toward High-Performance Language-Independent Query-by-Example Spoken Term Detection for MediaEval 2015: Post-Evaluation Analysis

Cheung-Chi Leung, Lei Wang, Haihua Xu, Jingyong Hou, Van Tung Pham

Rapid Update of Multilingual Deep Neural Network for Low-Resource Keyword Search

Chongjia Ni, Lei Wang, Cheung-Chi Leung, Feng Rao, Li Lu

Enhancing Data-Driven Phone Confusions Using Restricted Recognition

Mark Kane, Julie Carson-berndsen

Recurrent Neural Network-Based Phoneme Sequence Estimation Using Multiple ASR Systems’ Outputs for Spoken Term Detection

Naoki Sawada, Hiromitsu Nishizaki

Fusion Strategies for Robust Speech Recognition and Keyword Spotting for Channel- and Noise-Degraded Speech

Vikramjit Mitra, Julien VanHout, Wen Wang, Chris Bartels, Horacio Franco

Model Adaptation and Active Learning in the BBN Speech Activity Detection System for the DARPA RATS Program

Damianos Karakos, Scott Novotney, Le Zhang, Richard Schwartz

The SRI System for the NIST OpenSAD 2015 Speech Activity Detection Evaluation

Martin Graciarena, Luciana Ferrer, Vikramjit Mitra

Feature Learning with Raw-Waveform CLDNNs for Voice Activity Detection

Ruben Zazo, Tara N. Sainath, Gabor Simko, Carolina Parada

Robust DNN-Based VAD Augmented with Phone Entropy Based Rejection of Background Speech

Yuya Fujita, Ken-ichi Iso

Audio-Based Distributional Representations of Meaning Using a Fusion of Feature Encodings

Giannis Karamanolakis, Elias Iosif, Athanasia Zlatintsi, Aggelos Pikrakis, Alexandros Potamianos

Robust Audio Event Recognition with 1-Max Pooling Convolutional Neural Networks

Huy Phan, Lars Hertel, Marco Maass, Alfred Mertins

Noise and Metadata Sensitive Bottleneck Features for Improving Speaker Recognition with Non-Native Speech Input

Yao Qian, Jidong Tao, David Suendermann-Oeft, Keelan Evanini, Alexei V. Ivanov

Generalized Discriminant Analysis (GDA) for Improved i-Vector Based Speaker Recognition

Fahimeh Bahmaninezhad, John H.L. Hansen

Probabilistic Approach Using Joint Clean and Noisy i-Vectors Modeling for Speaker Recognition

Waad Ben Kheder, Driss Matrouf, Moez Ajili, Jean-Francois Bonastre

The IBM Speaker Recognition System: Recent Advances and Error Analysis

Seyed Omid Sadjadi, Jason W. Pelecanos, Sriram Ganapathy

Articulation Rate Filtering of CQCC Features for Automatic Speaker Verification

Massimiliano Todisco, Héctor Delgado, Nicholas Evans

On the Influence of Text Content on Pass-Phrase Strength for Short-Duration Text-Dependent Automatic Speaker Authentication

Giacomo Valenti, Adrien Daniel, Nicholas Evans

On the Correlation and Transferability of Features Between Automatic Speech Recognition and Speech Emotion Recognition

Haytham M. Fayek, Margaret Lech, Lawrence Cavedon

Analysis of Multi-Lingual Emotion Recognition Using Auditory Attention Features

Ozlem Kalinli

Multilingual Speech Emotion Recognition System Based on a Three-Layer Model

Xingfeng Li, Masato Akagi

Representation Learning for Speech Emotion Recognition

Sayan Ghosh, Eugene Laksana, Louis-Philippe Morency, Stefan Scherer

Defining Emotionally Salient Regions Using Qualitative Agreement Method

Srinivas Parthasarathy, Carlos Busso

Facing Realism in Spontaneous Emotion Recognition from Speech: Feature Enhancement by Autoencoder with LSTM Neural Networks

Zixing Zhang, Fabien Ringeval, Jing Han, Jun Deng, Erik Marchi

Bayesian Modeling in Speech Motor Control: A Principled Structure for the Integration of Various Constraints

Jean-François Patri, Pascal Perrier, Julien Diard

Experimental Validation of Sound Generated from Flow in Simplified Vocal Tract Model of Sibilant /s/

Tsukasa Yoshinaga, Kazunori Nozaki, Shigeo Wada

Uncontrolled Manifolds in Vowel Production: Assessment with a Biomechanical Model of the Tongue

Andrew Szabados, Pascal Perrier

A New Model for Acoustic Wave Propagation and Scattering in the Vocal Tract

Jianguo Wei, Wendan Guan, Darcy Q. Hou, Dingyi Pan, Wenhuan Lu

Using a Biomechanical Model and Articulatory Data for the Numerical Production of Vowels

Saeed Dabbaghchian, Marc Arnela, Olov Engwall, Oriol Guasch, Ian Stavness

A New Model of Speech Motor Control Based on Task Dynamics and State Feedback

Vikram Ramanarayanan, Benjamin Parrell, Louis Goldstein, Srikantan Nagarajan, John Houde

The Effect of Postlexical Deletion on Automatic Speech Recognition in Fast Spontaneously Spoken Zulu

Ewald van der Westhuizen, Thomas Niesler

Part-of-Speech Tagging and Chunking in Text-to-Speech Synthesis for South African Languages

Georg I. Schlünz, Nkosikhona Dlamini, Rynhardt P. Kruger

CNN-Based Phone Segmentation Experiments in a Less-Represented Language

Céline Manenti, Thomas Pellegrini, Julien Pinquier

Unsupervised Phoneme Segmentation of Previously Unseen Languages

Marco Vetter, Markus Müller, Fatima Hamlaoui, Graham Neubig, Satoshi Nakamura

Preliminary Experiments on Unsupervised Word Discovery in Mboshi

Pierre Godard, Gilles Adda, Martine Adda-Decker, Alexandre Allauzen, Laurent Besacier

Improving the Lwazi ASR Baseline

Charl van Heerden, Neil Kleynhans, Marelie Davel

Speed Perturbation and Vowel Duration Modeling for ASR in Hausa and Wolof Languages

Elodie Gauthier, Laurent Besacier, Sylvie Voisin

Automatic Speech Recognition Using Probabilistic Transcriptions in Swahili, Amharic, and Dinka

Amit Das, Preethi Jyothi, Mark Hasegawa-Johnson

LSTM, GRU, Highway and a Bit of Attention: An Empirical Overview for Language Modeling in Speech Recognition

Kazuki Irie, Zoltán Tüske, Tamer Alkhouli, Ralf Schlüter, Hermann Ney

Word-Phrase-Entity Recurrent Neural Networks for Language Modeling

Michael Levit, Sarangarajan Parthasarathy, Shuangyu Chang

Sequential Recurrent Neural Networks for Language Modeling

Youssef Oualil, Clayton Greenberg, Mittul Singh, Dietrich Klakow

Recurrent Neural Network Language Model with Incremental Updated Context Information Generated Using Bag-of-Words Representation

Md. Akmal Haidar, Mikko Kurimo

NN-Grams: Unifying Neural Network and n-Gram Language Models for Speech Recognition

Babak Damavandi, Shankar Kumar, Noam Shazeer, Antoine Bruguier

Compositional Neural Network Language Models for Agglutinative Languages

Ebru Arisoy, Murat Saraclar

Computational Approaches to Linguistic Code Switching

Mona Diab, Pascale Fung, Julia Hirschberg, Thamar Solorio

Speaker Normalization Through Feature Shifting of Linearly Transformed i-Vector

Jahyun Goo, Younggwan Kim, Hyungjun Lim, Hoirin Kim

Multi-Attribute Factorized Hidden Layer Adaptation for DNN Acoustic Models

Lahiru Samarakoon, Khe Chai Sim

DNNs for Unsupervised Extraction of Pseudo FMLLR Features Without Explicit Adaptation Data

Neethu Mariam Joy, Murali Karthick Baskar, S. Umesh, Basil Abraham

A Framework for Practical Multistream ASR

Sri Harish Mallidi, Hynek Hermansky

Automatic Correction of ASR Outputs by Using Machine Translation

Luis Fernando D’Haro, Rafael E. Banchs

ASR Confidence Estimation with Speaker-Adapted Recurrent Neural Networks

Miguel Ángel del-Agua, Santiago Piqueras, Adrià Giménez, Alberto Sanchis, Jorge Civera

Pitch-Adaptive Front-End Features for Robust Children’s ASR

S. Shahnawazuddin, Abhishek Dey, Rohit Sinha

Improving Large Vocabulary Accented Mandarin Speech Recognition with Attribute-Based I-Vectors

Hao Zheng, Shanshan Zhang, Liwei Qiao, Jianping Li, Wenju Liu

Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling

Gil Luyet, Pranay Dighe, Afsaneh Asaei, Hervé Bourlard

Triphone State-Tying via Deep Canonical Correlation Analysis

Weiran Wang, Hao Tang, Karen Livescu

Distilling Knowledge from Ensembles of Neural Networks for Speech Recognition

Yevgen Chebotar, Austin Waters

Acoustic Modelling from the Signal Domain Using CNNs

Pegah Ghahremani, Vimal Manohar, Daniel Povey, Sanjeev Khudanpur

Advances in Very Deep Convolutional Neural Networks for LVCSR

Tom Sercu, Vaibhava Goel

Towards Online-Recognition with Deep Bidirectional LSTM Acoustic Models

Albert Zeyer, Ralf Schlüter, Hermann Ney

Multidimensional Residual Learning Based on Recurrent Neural Networks for Acoustic Modeling

Yuanyuan Zhao, Shuang Xu, Bo Xu

Open-Domain Audio-Visual Speech Recognition: A Deep Learning Approach

Yajie Miao, Florian Metze

GMM-Free Flat Start Sequence-Discriminative DNN Training

Gábor Gosztolya, Tamás Grósz, László Tóth

On Online Attention-Based Speech Recognition and Joint Mandarin Character-Pinyin Training

William Chan, Ian Lane

Hybrid Accelerated Optimization for Speech Recognition

Jen-Tzung Chien, Pei-Wen Huang, Tan Lee

Future Context Attention for Unidirectional LSTM Based Acoustic Model

Jian Tang, Shiliang Zhang, Si Wei, Li-Rong Dai