Afsaneh Asaei

Publication Activity (10 Years)

Years Active: 2008-2020
Publications (10 Years): 26

Top Topics

Spoken Term Detection

Speech Recognition

Distance Measurement

Acoustic Models

Top Venues

Publications

Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
On quantifying the quality of acoustic models in hybrid DNN-HMM ASR. Speech Commun. 119 (2020)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Low-rank and sparse subspace modeling of speech for DNN based acoustic modeling. Speech Commun. 109 (2019)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Far-Field ASR Using Low-Rank and Sparse Soft Targets from Parallel Data. SLT (2018)
Milos Cernak, Afsaneh Asaei, Alexandre Hyafil
Cognitive Speech Coding: Examining the Impact of Cognitive Speech Processing on Speech Compression. IEEE Signal Process. Mag. 35 (3) (2018)
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
Sparse Subspace Modeling for Query by Example Spoken Term Detection. IEEE ACM Trans. Audio Speech Lang. Process. 26 (6) (2018)
Afsaneh Asaei, Dhananjay Ram, Hervé Bourlard
Phonological Posterior Hashing for Query by Example Spoken Term Detection. INTERSPEECH (2018)
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
Phonetic subspace features for improved query by example spoken term detection. Speech Commun. 103 (2018)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Low-rank and sparse soft targets to learn better DNN acoustic models. ICASSP (2017)
Afsaneh Asaei, Milos Cernak, Hervé Bourlard
Perceptual Information Loss due to Impaired Speech Production. IEEE ACM Trans. Audio Speech Lang. Process. 25 (12) (2017)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Exploiting Eigenposteriors for Semi-Supervised Training of DNN Acoustic Models with Sequence Discrimination. INTERSPEECH (2017)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Sparse modeling of neural network posterior probabilities for exemplar-based speech recognition. Speech Commun. 76 (2016)
Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Low-rank and Sparse Soft Targets to Learn Better DNN Acoustic Models. CoRR (2016)
Milos Cernak, Afsaneh Asaei, Pierre-Edouard Honnet, Philip N. Garner, Hervé Bourlard
Sound Pattern Matching for Automatic Prosodic Event Detection. INTERSPEECH (2016)
Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei, Philip N. Garner
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding. CoRR (2016)
Gil Luyet, Pranay Dighe, Afsaneh Asaei, Hervé Bourlard
Low-Rank Representation of Nearest Neighbor Posterior Probabilities to Enhance DNN Based Acoustic Modeling. INTERSPEECH (2016)
Afsaneh Asaei, Gil Luyet, Milos Cernak, Hervé Bourlard
Phonetic and Phonological Posterior Search Space Hashing Exploiting Class-Specific Sparsity Structures. INTERSPEECH (2016)
Pranay Dighe, Gil Luyet, Afsaneh Asaei, Hervé Bourlard
Exploiting Low-dimensional Structures to Enhance DNN Based Acoustic Modeling in Speech Recognition. CoRR (2016)
Milos Cernak, Alexandros Lazaridis, Afsaneh Asaei, Philip N. Garner
Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding. IEEE ACM Trans. Audio Speech Lang. Process. 24 (12) (2016)
Afsaneh Asaei, Mohammad Javad Taghizadeh, Saeid Haghighatshoar, Bhiksha Raj, Hervé Bourlard, Volkan Cevher
Binary Sparse Coding of Convolutive Mixtures for Sound Localization and Separation via Spatialization. IEEE Trans. Signal Process. 64 (3) (2016)
Milos Cernak, Afsaneh Asaei, Hervé Bourlard
On Structured Sparsity of Phonological Posteriors for Linguistic Parsing. CoRR (2016)
José F. Velasco, Daniel Pizarro, Javier Macías Guarasa, Afsaneh Asaei
TDOA Matrices: Algebraic Properties and their Application to Robust Denoising with Missing Data. CoRR (2016)
Afsaneh Asaei, Hervé Bourlard, Mohammad Javad Taghizadeh, Volkan Cevher
Computational methods for underdetermined convolutive speech localization and separation via model-based sparse component analysis. Speech Commun. 76 (2016)
Dhananjay Ram, Afsaneh Asaei, Hervé Bourlard
Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection. INTERSPEECH (2016)
Pranay Dighe, Gil Luyet, Afsaneh Asaei, Hervé Bourlard
Exploiting low-dimensional structures to enhance DNN based acoustic modeling in speech recognition. ICASSP (2016)
José F. Velasco, Daniel Pizarro, Javier Macías Guarasa, Afsaneh Asaei
TDOA Matrices: Algebraic Properties and Their Application to Robust Denoising With Missing Data. IEEE Trans. Signal Process. 64 (20) (2016)
Milos Cernak, Afsaneh Asaei, Hervé Bourlard
On structured sparsity of phonological posteriors for linguistic parsing. Speech Commun. 84 (2016)
Afsaneh Asaei, Nasser Mohammadiha, Mohammad Javad Taghizadeh, Simon Doclo, Hervé Bourlard
On application of non-negative matrix factorization for ad hoc microphone array calibration from incomplete noisy distances. ICASSP (2015)
Mohammad Javad Taghizadeh, Saeid Haghighatshoar, Afsaneh Asaei, Philip N. Garner, Hervé Bourlard
Robust microphone placement for source localization from noisy distance measurements. ICASSP (2015)
Afsaneh Asaei, Milos Cernak, Hervé Bourlard
On compressibility of neural network phonological features for low bit rate speech coding. INTERSPEECH (2015)
José F. Velasco, Mohammad Javad Taghizadeh, Afsaneh Asaei, Hervé Bourlard, Carlos Julian Martín-Arguedas, Javier Macías Guarasa, Daniel Pizarro
Novel GCC-PHAT model in diffuse sound field for microphone array pairwise distance based calibration. ICASSP (2015)
Mohammad Javad Taghizadeh, Afsaneh Asaei, Saeid Haghighatshoar, Philip N. Garner, Hervé Bourlard
Spatial Sound Localization via Multipath Euclidean Distance Matrix Recovery. IEEE J. Sel. Top. Signal Process. 9 (5) (2015)
Mohammad Javad Taghizadeh, Reza Parhizkar, Philip N. Garner, Hervé Bourlard, Afsaneh Asaei
Ad hoc microphone array calibration: Euclidean distance matrix completion algorithm and theoretical guarantees. Signal Process. 107 (2015)
Dhananjay Ram, Afsaneh Asaei, Pranay Dighe, Hervé Bourlard
Sparse modeling of posterior exemplars for keyword detection. INTERSPEECH (2015)
Sara Bahaadini, Afsaneh Asaei, David Imseng, Hervé Bourlard
Posterior-based sparse representation for automatic speech recognition. INTERSPEECH (2014)
Mohammad Javad Taghizadeh, Reza Parhizkar, Philip N. Garner, Hervé Bourlard, Afsaneh Asaei
Ad Hoc Microphone Array Calibration: Euclidean Distance Matrix Completion Algorithm and Theoretical Guarantees. CoRR (2014)
Afsaneh Asaei, Mohammad Golbabaee, Hervé Bourlard, Volkan Cevher
Structured Sparsity Models for Reverberant Speech Separation. IEEE ACM Trans. Audio Speech Lang. Process. 22 (3) (2014)
Michael B. McCoy, Volkan Cevher, Quoc Tran-Dinh, Afsaneh Asaei, Luca Baldassarre
Convexity in Source Separation : Models, geometry, and algorithms. IEEE Signal Process. Mag. 31 (3) (2014)
Afsaneh Asaei, Hervé Bourlard, Mohammad Javad Taghizadeh, Volkan Cevher
Model-based sparse component analysis for reverberant speech localization. ICASSP (2014)
Mohammad Javad Taghizadeh, Afsaneh Asaei, Philip N. Garner, Hervé Bourlard
Ad-hoc microphone array calibration from partial distance measurements. HSCMA (2014)
Baran Gozcu, Afsaneh Asaei, Volkan Cevher
Manifold sparse beamforming. CAMSAP (2013)
Michael B. McCoy, Volkan Cevher, Quoc Tran-Dinh, Afsaneh Asaei, Luca Baldassarre
Convexity in source separation: Models, geometry, and algorithms. CoRR (2013)
Afsaneh Asaei, Bhiksha Raj, Hervé Bourlard, Volkan Cevher
Structured sparse coding for microphone array location calibration. SAPA@INTERSPEECH (2012)
Afsaneh Asaei, Mohammad Golbabaee, Hervé Bourlard, Volkan Cevher
Structured Sparsity Models for Multiparty Speech Recovery from Reverberant Recordings CoRR (2012)
Afsaneh Asaei, Michael E. Davies, Hervé Bourlard, Volkan Cevher
Computational methods for structured sparse component analysis of convolutive speech mixtures. ICASSP (2012)
Afsaneh Asaei, Mohammad Javad Taghizadeh, Hervé Bourlard, Volkan Cevher
Multi-Party Speech Recovery Exploiting Structured Sparsity Models. INTERSPEECH (2011)
Afsaneh Asaei, Hervé Bourlard, Volkan Cevher
Model-based compressive sensing for multi-party distant speech recognition. ICASSP (2011)
Afsaneh Asaei, Hervé Bourlard, Philip N. Garner
Sparse component analysis for speech recognition in multi-speaker environment. INTERSPEECH (2010)
Afsaneh Asaei, Benjamin Picart, Hervé Bourlard
Analysis of phone posterior feature space exploiting class-specific sparsity and MLP-based similarity measure. ICASSP (2010)
Afsaneh Asaei, Mohammad Javad Taghizadeh, Marjan Bahrololum, Mohammed Ghanbari
Verified speaker localization utilizing voicing level in split-bands. Signal Process. 89 (6) (2009)
Afsaneh Asaei, Mohammad Javad Taghizadeh, Hossein Sameti
Far-field continuous speech recognition system based on speaker Localization and sub-band Beamforming. AICCSA (2008)