Sorry, you need to enable JavaScript to visit this website.

Speech Analysis (SPE-ANLS)

Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data


Bidirectional long short-term memory (BLSTM) recurrent neural network (RNN) has achieved state-of-the-art performance in many sequence processing problems given its capability in capturing contextual information. However, for languages with limited amount of training data, it is still difficult to obtain a high quality BLSTM model for emphasis detection, the aim of which is to recognize the emphasized speech segments from natural speech.

Paper Details

Authors:
Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai
Submitted On:
4 March 2017 - 10:26am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2017-Poster presentation-horizontal-v2-nys.pptx

(56 downloads)

Keywords

Subscribe

[1] Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai, "Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1626. Accessed: Oct. 19, 2017.
@article{1626-17,
url = {http://sigport.org/1626},
author = {Yishuang Ning; Zhiyong Wu; Runnan Li; Jia Jia; Mingxing Xu; Helen Meng; Lianhong Cai },
publisher = {IEEE SigPort},
title = {Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data},
year = {2017} }
TY - EJOUR
T1 - Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data
AU - Yishuang Ning; Zhiyong Wu; Runnan Li; Jia Jia; Mingxing Xu; Helen Meng; Lianhong Cai
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1626
ER -
Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai. (2017). Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data. IEEE SigPort. http://sigport.org/1626
Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai, 2017. Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data. Available at: http://sigport.org/1626.
Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai. (2017). "Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data." Web.
1. Yishuang Ning, Zhiyong Wu, Runnan Li, Jia Jia, Mingxing Xu, Helen Meng, Lianhong Cai. Learning Cross-lingual Knowledge with Multilingual BLSTM for Emphasis Detection with Limited Training Data [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1626

DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS


Aphasia is an acquired communication disorder resulting from brain damage and impairs an individual’s ability to use, produce, and comprehend language. Loss of communication skills can be stressful and may result in depression, yet most stress and depression diagnostic tools are designed for adults without aphasia. This project is a research effort to predict stress and depression from acoustic profiles of adults with aphasia using linear support-vector regression. The labels were obtained through caregiver surveys (SADQ-10) or surveys not designed for adults with aphasia (PSS).

Paper Details

Authors:
Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan
Submitted On:
1 March 2017 - 11:29am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2017_poster_v1[1].pptx

(82 downloads)

Keywords

Subscribe

[1] Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan, "DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1558. Accessed: Oct. 19, 2017.
@article{1558-17,
url = {http://sigport.org/1558},
author = {Jacqueline Laures-Gore; Mathew Farina; Scott Russell; Yash-yee Logan },
publisher = {IEEE SigPort},
title = {DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS},
year = {2017} }
TY - EJOUR
T1 - DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS
AU - Jacqueline Laures-Gore; Mathew Farina; Scott Russell; Yash-yee Logan
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1558
ER -
Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan. (2017). DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS. IEEE SigPort. http://sigport.org/1558
Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan, 2017. DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS. Available at: http://sigport.org/1558.
Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan. (2017). "DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS." Web.
1. Jacqueline Laures-Gore, Mathew Farina, Scott Russell, Yash-yee Logan. DETECTING STRESS AND DEPRESSION IN ADULTS WITH APHASIA THROUGH SPEECH ANALYSIS [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1558

AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION


Automatic syllable stress detection is useful in assessing and diagnosing the quality of the pronunciation of second language (L2) learners in an automated way. Typically, the syllable stress depends on three prominence measures -- intensity level, duration, pitch -- around the sound unit with the highest sonority in the respective syllable. Stress detection is often formulated as a binary classification task using cues from the feature contours representing the prominence measures.

ICASSP17.pdf

PDF icon ICASSP17.pdf (52 downloads)

Paper Details

Authors:
Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh
Submitted On:
11 March 2017 - 8:49pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

ICASSP17.pdf

(52 downloads)

Keywords

Subscribe

[1] Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh, "AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1472. Accessed: Oct. 19, 2017.
@article{1472-17,
url = {http://sigport.org/1472},
author = {Chiranjeevi Yarra; Om D Deshmukh; Prasanta Kumar Ghosh },
publisher = {IEEE SigPort},
title = {AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION},
year = {2017} }
TY - EJOUR
T1 - AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION
AU - Chiranjeevi Yarra; Om D Deshmukh; Prasanta Kumar Ghosh
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1472
ER -
Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh. (2017). AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION. IEEE SigPort. http://sigport.org/1472
Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh, 2017. AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION. Available at: http://sigport.org/1472.
Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh. (2017). "AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION." Web.
1. Chiranjeevi Yarra, Om D Deshmukh, Prasanta Kumar Ghosh. AUTOMATIC DETECTION OF SYLLABLE STRESS USING SONORITY BASED PROMINENCE FEATURES FOR PRONUNCIATION EVALUATION [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1472

NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN


Nonnegative matrix factorization (NMF) has recently been applied to temporal decomposition (TD) of speech spectral envelopes represented by line spectral frequencies. A couple of inherent TD constraints, which are otherwise handled as ad hoc exceptions, has also been incorporated using NMF, including LSF ordering and monotonic event functions. Here, these constraints are analyzed and a third inherent constraint is incorporated into an NMF analysis.

Paper Details

Authors:
Miguel Arjona Ramírez
Submitted On:
27 February 2017 - 10:13pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

ICASSP2017marjonaramirezSP-P1.10

(105 downloads)

Keywords

Additional Categories

Subscribe

[1] Miguel Arjona Ramírez, "NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/1468. Accessed: Oct. 19, 2017.
@article{1468-17,
url = {http://sigport.org/1468},
author = {Miguel Arjona Ramírez },
publisher = {IEEE SigPort},
title = {NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN},
year = {2017} }
TY - EJOUR
T1 - NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN
AU - Miguel Arjona Ramírez
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/1468
ER -
Miguel Arjona Ramírez. (2017). NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN. IEEE SigPort. http://sigport.org/1468
Miguel Arjona Ramírez, 2017. NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN. Available at: http://sigport.org/1468.
Miguel Arjona Ramírez. (2017). "NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN." Web.
1. Miguel Arjona Ramírez. NON-NEGATIVE TEMPORAL DECOMPOSITION REGULARIZATION WITH AN AUGMENTED LAGRANGIAN [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/1468

RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH


In this paper, rich prosodic information of spontaneous Mandarin speech is explored. The joint prosody labeling and modeling algorithm proposed previously for read speech is extended to spontaneous-speech prosody modeling by additionally considering the modeling of disfluency speech parts. It trains a hierarchical prosodic model and performs prosody labeling from a large speech corpus automatically. Rich prosodic information is then explored via analyzing model parameters and labeling results.

Paper Details

Authors:
Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen
Submitted On:
12 October 2016 - 9:45pm
Short Link:
Type:
Event:
Document Year:
Cite

Document Files

42x36_ISCSLP2016_posters.pdf

(106 downloads)

Keywords

Subscribe

[1] Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen, "RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1164. Accessed: Oct. 19, 2017.
@article{1164-16,
url = {http://sigport.org/1164},
author = {Chung-Long You; Chen-Yu Chiang; Yih-Ru Wang; Sin-Horng Chen },
publisher = {IEEE SigPort},
title = {RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH},
year = {2016} }
TY - EJOUR
T1 - RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH
AU - Chung-Long You; Chen-Yu Chiang; Yih-Ru Wang; Sin-Horng Chen
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1164
ER -
Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen. (2016). RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH. IEEE SigPort. http://sigport.org/1164
Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen, 2016. RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH. Available at: http://sigport.org/1164.
Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen. (2016). "RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH." Web.
1. Chung-Long You, Chen-Yu Chiang, Yih-Ru Wang, Sin-Horng Chen. RICH PROSODIC INFORMATION EXPLORATION ON SPONTANEOUS MANDARIN SPEECH [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1164

High-Resolution Sinusoidal Modeling of Unvoiced Speech

Paper Details

Authors:
George P. Kafentzis, Yannis Stylianou
Submitted On:
10 April 2016 - 4:03am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

Kafentzis - ICASSP Presentation.pptx

(206 downloads)

Keywords

Subscribe

[1] George P. Kafentzis, Yannis Stylianou, "High-Resolution Sinusoidal Modeling of Unvoiced Speech", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1089. Accessed: Oct. 19, 2017.
@article{1089-16,
url = {http://sigport.org/1089},
author = {George P. Kafentzis; Yannis Stylianou },
publisher = {IEEE SigPort},
title = {High-Resolution Sinusoidal Modeling of Unvoiced Speech},
year = {2016} }
TY - EJOUR
T1 - High-Resolution Sinusoidal Modeling of Unvoiced Speech
AU - George P. Kafentzis; Yannis Stylianou
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1089
ER -
George P. Kafentzis, Yannis Stylianou. (2016). High-Resolution Sinusoidal Modeling of Unvoiced Speech. IEEE SigPort. http://sigport.org/1089
George P. Kafentzis, Yannis Stylianou, 2016. High-Resolution Sinusoidal Modeling of Unvoiced Speech. Available at: http://sigport.org/1089.
George P. Kafentzis, Yannis Stylianou. (2016). "High-Resolution Sinusoidal Modeling of Unvoiced Speech." Web.
1. George P. Kafentzis, Yannis Stylianou. High-Resolution Sinusoidal Modeling of Unvoiced Speech [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1089

Fast and Statistically Efficient Fundamental Frequency Estimation

Paper Details

Authors:
Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen
Submitted On:
22 March 2016 - 3:12am
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

master.pdf

(170 downloads)

Keywords

Subscribe

[1] Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen, "Fast and Statistically Efficient Fundamental Frequency Estimation", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/958. Accessed: Oct. 19, 2017.
@article{958-16,
url = {http://sigport.org/958},
author = {Jesper Kjær Nielsen; Tobias Lindstrøm Jensen; Jesper Rindom Jensen; Mads Græsbøll Christensen; and Søren Holdt Jensen },
publisher = {IEEE SigPort},
title = {Fast and Statistically Efficient Fundamental Frequency Estimation},
year = {2016} }
TY - EJOUR
T1 - Fast and Statistically Efficient Fundamental Frequency Estimation
AU - Jesper Kjær Nielsen; Tobias Lindstrøm Jensen; Jesper Rindom Jensen; Mads Græsbøll Christensen; and Søren Holdt Jensen
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/958
ER -
Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen. (2016). Fast and Statistically Efficient Fundamental Frequency Estimation. IEEE SigPort. http://sigport.org/958
Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen, 2016. Fast and Statistically Efficient Fundamental Frequency Estimation. Available at: http://sigport.org/958.
Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen. (2016). "Fast and Statistically Efficient Fundamental Frequency Estimation." Web.
1. Jesper Kjær Nielsen, Tobias Lindstrøm Jensen, Jesper Rindom Jensen, Mads Græsbøll Christensen, and Søren Holdt Jensen. Fast and Statistically Efficient Fundamental Frequency Estimation [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/958

Iterative estimation of phase using complex cepstrum representation

Paper Details

Authors:
Ranniery Maia, Yannis Stylianou
Submitted On:
21 March 2016 - 7:30pm
Short Link:
Type:
Event:
Presenter's Name:
Paper Code:
Document Year:
Cite

Document Files

MaiaStylianou_icassp2016_pres.pdf

(199 downloads)

Keywords

Subscribe

[1] Ranniery Maia, Yannis Stylianou, "Iterative estimation of phase using complex cepstrum representation", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/940. Accessed: Oct. 19, 2017.
@article{940-16,
url = {http://sigport.org/940},
author = {Ranniery Maia; Yannis Stylianou },
publisher = {IEEE SigPort},
title = {Iterative estimation of phase using complex cepstrum representation},
year = {2016} }
TY - EJOUR
T1 - Iterative estimation of phase using complex cepstrum representation
AU - Ranniery Maia; Yannis Stylianou
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/940
ER -
Ranniery Maia, Yannis Stylianou. (2016). Iterative estimation of phase using complex cepstrum representation. IEEE SigPort. http://sigport.org/940
Ranniery Maia, Yannis Stylianou, 2016. Iterative estimation of phase using complex cepstrum representation. Available at: http://sigport.org/940.
Ranniery Maia, Yannis Stylianou. (2016). "Iterative estimation of phase using complex cepstrum representation." Web.
1. Ranniery Maia, Yannis Stylianou. Iterative estimation of phase using complex cepstrum representation [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/940

EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA

Paper Details

Authors:
Elliot Moore, Jacqueline Laures-Gore, Matthew Farina
Submitted On:
15 March 2016 - 12:00am
Short Link:
Type:
Event:
Presenter's Name:
Document Year:
Cite

Document Files

ICASSP2016_poster_Gillespie.pdf

(184 downloads)

Keywords

Subscribe

[1] Elliot Moore, Jacqueline Laures-Gore, Matthew Farina, "EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/684. Accessed: Oct. 19, 2017.
@article{684-16,
url = {http://sigport.org/684},
author = {Elliot Moore; Jacqueline Laures-Gore; Matthew Farina },
publisher = {IEEE SigPort},
title = {EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA},
year = {2016} }
TY - EJOUR
T1 - EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA
AU - Elliot Moore; Jacqueline Laures-Gore; Matthew Farina
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/684
ER -
Elliot Moore, Jacqueline Laures-Gore, Matthew Farina. (2016). EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA. IEEE SigPort. http://sigport.org/684
Elliot Moore, Jacqueline Laures-Gore, Matthew Farina, 2016. EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA. Available at: http://sigport.org/684.
Elliot Moore, Jacqueline Laures-Gore, Matthew Farina. (2016). "EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA." Web.
1. Elliot Moore, Jacqueline Laures-Gore, Matthew Farina. EXPLORATORY ANALYSIS OF SPEECH FEATURES RELATED TO DEPRESSION IN ADULTS WITH APHASIA [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/684