- Date & Time: Thursday, September 6, 2012; 12:00 PM
Speaker: Dr. Daisuke Saito, The University of Tokyo
Research Area: Speech & Audio
Abstract - In voice conversion studies, realization of conversion from/to an arbitrary speaker's voice is one of the important objectives. For this purpose, eigenvoice conversion (EVC) based on an eigenvoice Gaussian mixture model (EV-GMM) was proposed. In the EVC, similarly to speaker recognition approaches, a speaker space is constructed based on GMM supervectors which are high-dimensional vectors derived by concatenating the mean vectors of each of the speaker GMMs. In the speaker space, each speaker is represented by a small number of weight parameters of eigen-supervectors. In this talk, we revisit construction of the speaker space by introducing the tensor analysis of training data set. In our approach, each speaker is represented as a matrix of which the row and the column respectively correspond to the Gaussian component and the dimension of the mean vector, and the speaker space is derived by the tensor analysis of the set of the matrices. Our approach can solve an inherent problem of supervector representation, and it improves the performance of voice conversion. Experimental results of one-to-many voice conversion demonstrate the effectiveness of the proposed approach.
-
- Date: March 31, 2012
Where: International Workshop on Statistical Machine Learning for Speech Processing (IWSML)
MERL Contact: Jonathan Le Roux
Research Area: Speech & Audio
Brief - The paper "Latent Dirichlet Reallocation for Term Swapping" by Heaukulani, C., Le Roux, J. and Hershey, J.R. was presented at the International Workshop on Statistical Machine Learning for Speech Processing (IWSML).
-
- Date: March 13, 2012
Where: Acoustical Society of Japan Spring Meeting (ASJ)
MERL Contact: Jonathan Le Roux
Research Area: Speech & Audio
Brief - The paper "Speech Enhancement by Indirect VTS" by Le Roux, J. and Hershey, J.R. was presented at the Acoustical Society of Japan Spring Meeting (ASJ).
-
- Date & Time: Wednesday, February 22, 2012; 11:00 AM
Speaker: Dr. Charles Cadieu, McGovern Institute for Brain Research, MIT
MERL Host: Jonathan Le Roux
Research Area: Speech & Audio
Abstract - The human visual system processes complex patterns of light into a rich visual representation where the objects and motions of our world are made explicit. This remarkable feat is performed through a hierarchically arranged series of cortical areas. Little is known about the details of the representations in the intermediate visual areas. Therefore, we ask the question: can we predict the detailed structure of the representations we might find in intermediate visual areas?
In pursuit of this question, I will present a model of intermediate-level visual representation that is based on learning invariances from movies of the natural environment and produces predictions about intermediate visual areas. The model is composed of two stages of processing: an early feature representation layer, and a second layer in which invariances are explicitly represented. Invariances are learned as the result of factoring apart the temporally stable and dynamic components embedded in the early feature representation. The structure contained in these components is made explicit in the activities of second-layer units that capture invariances in both form and motion. When trained on natural movies, the first-layer produces a factorization, or separation, of image content into a temporally persistent part representing local edge structure and a dynamic part representing local motion structure. The second-layer units are split into two populations according to the factorization in the first-layer. The form-selective units receive their input from the temporally persistent part (local edge structure) and after training result in a diverse set of higher-order shape features consisting of extended contours, multi-scale edges, textures, and texture boundaries. The motion-selective units receive their input from the dynamic part (local motion structure) and after training result in a representation of image translation over different spatial scales and directions, in addition to more complex deformations. These representations provide a rich description of dynamic natural images, provide testable hypotheses regarding intermediate-level representation in visual cortex, and may be useful representations for artificial visual systems.
-
- Date & Time: Thursday, October 20, 2011; 3:00 PM
Speaker: Dr. Cedric Fevotte, CNRS - Telecom ParisTech, Paris
MERL Host: Jonathan Le Roux
Research Area: Speech & Audio
-
- Date & Time: Thursday, October 20, 2011; 2:00 PM -5:00 PM
Location: MERL
MERL Contact: Jonathan Le Roux
Research Area: Speech & Audio
Brief - MERL is hosting a mini-symposium on audio and music signal processing, with three talks by eminent researchers in the field: Prof. Mark Plumbley, Dr. Cedric Fevotte and Prof. Nobutaka Ono.
-
- Date & Time: Thursday, October 20, 2011; 2:20 PM
Speaker: Prof. Mark Plumbley, Queen Mary, London
MERL Host: Jonathan Le Roux
Research Area: Speech & Audio
-
- Date & Time: Thursday, October 20, 2011; 3:40 PM
Speaker: Prof. Nobutaka Ono, National Institute of Informatics, Tokyo
MERL Host: Jonathan Le Roux
Research Area: Speech & Audio
-
- Date: June 27, 2011
Where: International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design
Research Area: Speech & Audio
Brief - The paper "Investigating HUDs or the Presentation of Choice Lists in Car navigation Systems" by Weinberg, G., Harsham, B. and Medenica, Z. was presented at the International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design.
-
- Date: January 31, 2011
Where: IEEE Multimedia
Research Area: Speech & Audio
Brief - The article "Multimodal Input in the Car, Today and Tomorrow" by Mueller, C. and Weinberg, G. was published in IEEE Multimedia.
-
- Date: September 26, 2010
Where: Interspeech
Research Area: Speech & Audio
Brief - The paper "Vocabulary Independent Spoken Query: a Case for Subword Units" by Gouvea, E. and Ezzat, T. was presented at Interspeech.
-
- Date: September 26, 2010
Where: Annual Conference of the International Speech Communication Association
Research Area: Speech & Audio
Brief - The paper "Ungrounded Independent Non-Negative Factor Analysis" by Raj, B., Wilson, K.W., Krueger, A. and Haeb-Umbach, R. was presented at the Annual Conference of the International Speech Communication Association.
-
- Date: September 7, 2010
Where: International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI)
Research Area: Speech & Audio
Brief - The paper "Contextual Push-to-talk: Shortening Voice Dialogs to Improve Driving Performance" by Weinberg, G., Harsham, B., Forlines, C. and Medenica, Z. was presented at the International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI).
-
- Date: September 7, 2010
Where: Speech in Mobile and Pervasive Environments (SiMPE)
Research Area: Speech & Audio
Brief - The paper "Object-Oriented Multimodality for Safer-In-Vehicle Interfaces" by Weinberg, G. and Harsham, B. was presented at Speech in Mobile and Pervasive Environments (SiMPE).
-
- Date: May 12, 2010
Where: Accident Analysis & Prevention
Research Area: Speech & Audio
Brief - The article "Evaluation of Different Speech and Touch Interfaces to In-vehicle Music Retrieval Systems" by Garay-Vega, L., Pradhan, A.K., Weinberg, G.L., Schmidt-Nielsen, B.K., Harsham, B.A., Shen, Y., Divekar, G., Romoser, M., Knodler, M. and Fisher, D.L. was published in Accident Analysis & Prevention.
-
- Date: September 21, 2009
Where: International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI)
Research Area: Speech & Audio
Brief - The paper "Developing a Low-Cost Driving Simulator for the Evaluation of In-Vehicle Technologies" by Weinberg, G.L. and Harsham, B.A. was presented at the International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI).
-
- Date: September 15, 2009
Where: International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI)
Research Area: Speech & Audio
Brief - The paper "Contextual Push-to-Talk: A New Technique for Reducing Voice Dialog Duration" by Weinberg, G.L. was presented at the International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI).
-
- Date: April 6, 2009
Where: European Conference on Informaiton Retrieval (ECIR)
Research Area: Speech & Audio
Brief - The paper "Word Particles Applied to Information Retrieval" by Gouvea, E.V. and Raj, B. was presented at the European Conference on Informaiton Retrieval (ECIR).
-
- Date: March 2, 2009
Where: Voice Search Conference
Research Area: Speech & Audio
Brief - The paper "Voice Search While Driving: Is it Safe?" by Wittenburg, K. was presented at the Voice Search Conference.
-
- Date: September 22, 2008
Where: Interspeech
Research Area: Speech & Audio
Brief - The paper "Regularized Non-negative Matrix Factorization with Temporal Dependencies for Speech Denoising" by Wilson, K. W., Raj, B. and Smaragdis, P. was presented at Interspeech.
-
- Date: July 25, 2008
Where: IADIS International Conference Interfaces and Human Computer Interaction (IHCI)
Research Area: Speech & Audio
Brief - The paper "Display Style Considerations for In-Car Multimodal Music Search" by Weinberg, G. and Kondili, D. was presented at the IADIS International Conference Interfaces and Human Computer Interaction (IHCI).
-
- Date: February 15, 2008
Where: Handbook of Research on User Interface Design and Evaluation for Mobile Technology
Research Area: Speech & Audio
Brief - The article "Speech-Based UI Design for the Automobile" by Schmidt-Nielsen, B., Harsham, B., Raj, B. and Forlines, C. was published in the book Handbook of Research on User Interface Design and Evaluation for Mobile Technology.
-
- Date: October 21, 2007
Where: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)
Research Area: Speech & Audio
Brief - The paper "Example-Driven Bandwidth Expansion" by Smaragdis, P. and Raj, B. was presented at the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA).
-
- Date: October 1, 2007
Where: IEEE Signal Processing Letters
Research Area: Speech & Audio
Brief - The article "Ultrasonic Doppler Sensor for Voice Activity Detection" by Kalgaonkar, K., Hu, R. and Raj, B. was published in IEEE Signal Processing Letters.
-
- Date: August 1, 2007
Where: IEEE Transactions on Audio, Speech and Language Processing
Research Area: Speech & Audio
Brief - The article "Soft Mask Methods for Single-Channel Speaker Separation" by Reddy, A.M. and Raj, B. was published in IEEE Transactions on Audio, Speech and Language Processing.
-