Search Results - "2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"

Multi-speaker modeling and speaker adaptation for DNN-based TTS synthesis by Yuchen Fan, Yao Qian, Soong, Frank K., Lei He

“…In DNN-based TTS synthesis, DNNs hidden layers can be viewed as deep transformation for linguistic features and the output layers as representation of acoustic…”
Get full text

Librispeech: An ASR corpus based on public domain audio books by Panayotov, Vassil, Guoguo Chen, Povey, Daniel, Khudanpur, Sanjeev

“…This paper introduces a new corpus of read English speech, suitable for training and evaluating speech recognition systems. The LibriSpeech corpus is derived…”
Get full text

Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks by Sainath, Tara N., Vinyals, Oriol, Senior, Andrew, Sak, Hasim

“…Both Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) have shown improvements over Deep Neural Networks (DNNs) across a wide variety of…”
Get full text

Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks by Erdogan, Hakan, Hershey, John R., Watanabe, Shinji, Le Roux, Jonathan

“…Separation of speech embedded in non-stationary interference is a challenging problem that has recently seen dramatic improvements using deep network-based…”
Get full text

Compressed sensing based multi-user millimeter wave systems: How many measurements are needed? by Alkhateeb, Ahmed, Leus, Geert, Heath, Robert W.

“…Millimeter wave (mmWave) systems will likely employ directional beamforming with large antenna arrays at both the transmitters and receivers. Acquiring channel…”
Get full text

A learning-based approach to direction of arrival estimation in noisy and reverberant environments by Xiong Xiao, Shengkui Zhao, Xionghu Zhong, Jones, Douglas L., Eng Siong Chng, Haizhou Li

“…This paper presents a learning-based approach to the task of direction of arrival estimation (DOA) from microphone array input. Traditional signal processing…”
Get full text

Deep neural networks employing Multi-Task Learning and stacked bottleneck features for speech synthesis by Zhizheng Wu, Valentini-Botinhao, Cassia, Watts, Oliver, King, Simon

“…Deep neural networks (DNNs) use a cascade of hidden representations to enable the learning of complex mappings from input to output features. They are able to…”
Get full text

Deep multimodal learning for Audio-Visual Speech Recognition by Mroueh, Youssef, Marcheret, Etienne, Goel, Vaibhava

“…In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR)…”
Get full text

Robust sound event recognition using convolutional neural networks by Haomin Zhang, McLoughlin, Ian, Yan Song

“…Traditional sound event recognition methods based on informative front end features such as MFCC, with back end sequencing methods such as HMM, tend to perform…”
Get full text

Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition by Xiangang Li, Xihong Wu

“…Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks…”
Get full text

Malware classification with recurrent networks by Pascanu, Razvan, Stokes, Jack W., Sanossian, Hermineh, Marinescu, Mady, Thomas, Anil

“…Attackers often create systems that automatically rewrite and reorder their malware to avoid detection. Typical machine learning approaches, which learn a…”
Get full text

Voice conversion using deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks by Lifa Sun, Shiyin Kang, Kun Li, Meng, Helen

“…This paper investigates the use of Deep Bidirectional Long Short-Term Memory based Recurrent Neural Networks (DBLSTM-RNNs) for voice conversion. Temporal…”
Get full text

Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis by Heiga Zen, Sak, Hasim

“…Long short-term memory recurrent neural networks (LSTM-RNNs) have been applied to various speech applications including acoustic modeling for statistical…”
Get full text

Fixed point optimization of deep convolutional neural networks for object recognition by Anwar, Sajid, Kyuyeon Hwang, Wonyong Sung

“…Deep convolutional neural networks have shown promising results in image and speech recognition applications. The learning capability of the network improves…”
Get full text

Speech acoustic modeling from raw multichannel waveforms by Hoshen, Yedid, Weiss, Ron J., Wilson, Kevin W.

“…Standard deep neural network-based acoustic models for automatic speech recognition (ASR) rely on hand-engineered input features, typically log-mel filterbank…”
Get full text

A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks by Marchi, Erik, Vesperini, Fabio, Eyben, Florian, Squartini, Stefano, Schuller, Bjorn

“…Acoustic novelty detection aims at identifying abnormal/novel acoustic signals which differ from the reference/normal data that the system was trained with. In…”
Get full text

Query-by-example keyword spotting using long short-term memory networks by Guoguo Chen, Parada, Carolina, Sainath, Tara N.

“…We present a novel approach to query-by-example keyword spotting (KWS) using a long short-term memory (LSTM) recurrent neural network-based feature extractor…”
Get full text

Advances in deep neural network approaches to speaker recognition by McLaren, Mitchell, Yun Lei, Ferrer, Luciana

“…The recent application of deep neural networks (DNN) to speaker identification (SID) has resulted in significant improvements over current state-of-the-art on…”
Get full text

Learning acoustic frame labeling for speech recognition with recurrent neural networks by Sak, Hasim, Senior, Andrew, Rao, Kanishka, Irsoy, Ozan, Graves, Alex, Beaufays, Francoise, Schalkwyk, Johan

“…We explore alternative acoustic modeling techniques for large vocabulary speech recognition using Long Short-Term Memory recurrent neural networks. For an…”
Get full text

Unsupervised feature learning for urban sound classification by Salamon, Justin, Bello, Juan Pablo

“…Recent studies have demonstrated the potential of unsupervised feature learning for sound classification. In this paper we further explore the application of…”
Get full text