An analysis of vector Taylor series model compensation for non-stationary noise in speech recognition

An analysis of vector Taylor series model compensation for non-stationary noise in speech recognition

In this paper, we investigate a feature conditioning method for the VTS-based model compensation. The VTS is a technique that predicts noisy acoustic model from clean acoustic model and noise model. It is noted that most of the previous studies use a single Gaussian noise model, which is unable to m...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính:	Li, Haizhou, Nguyen, Duc Hoang Ha, Xiao, Xiong, Chng, Eng Siong
Tác giả khác:	School of Computer Engineering
Định dạng:	Conference Paper
Ngôn ngữ:	English
Được phát hành:	2013
Những chủ đề:	DRNTU::Engineering::Computer science and engineering
Truy cập trực tuyến:	https://hdl.handle.net/10356/97488 http://hdl.handle.net/10220/11868

Những quyển sách tương tự

Joint spectral and temporal normalization of features for robust recognition of noisy and reverberated speech
Bằng: Xiao, Xiong, et al.
Được phát hành: (2013)

Lasso environment model combination for robust speech recognition
Bằng: Xiao, Xiong, et al.
Được phát hành: (2013)

Feature Adaptation Using Linear Spectro-Temporal Transform for Robust Speech Recognition
Bằng: Nguyen, Duc Hoang Ha, et al.
Được phát hành: (2016)

An investigation of spoofing speech detection under additive noise and reverberant conditions
Bằng: Tian, Xiaohai, et al.
Được phát hành: (2019)

Cross-lingual phone mapping for large vocabulary speech recognition of under-resourced languages
Bằng: Do, Van Hai, et al.
Được phát hành: (2014)

Discriminative feature extraction for speech recognition using continuous output codes
Bằng: Dehzangi, Omid, et al.
Được phát hành: (2013)

Spoofing speech detection using temporal convolutional neural network
Bằng: Xiao, Xiong, et al.
Được phát hành: (2018)

A vector-based approach to broadcast audio database indexing and retrieval
Bằng: Wang, Lei, et al.
Được phát hành: (2013)

Speech dereverberation for enhancement and recognition using dynamic features constrained deep neural networks and feature adaptation
Bằng: Xiao, Xiong, et al.
Được phát hành: (2016)

Feature-based robust techniques for speech recognition
Bằng: Nguyen, Duc Hoang Ha
Được phát hành: (2017)

A first speech recognition system for Mandarin-English code-switch conversational speech
Bằng: Vu, Ngoc Thang, et al.
Được phát hành: (2013)

Domain adversarial training for speech enhancement
Bằng: Hou, Nana, et al.
Được phát hành: (2020)

The NNi Vietnamese speech recognition system for mediaeval 2016
Bằng: Xiao, Xiong, et al.
Được phát hành: (2019)

Mixture of factor analyzers using priors from non-parallel speech for voice conversion
Bằng: Wu, Zhizheng, et al.
Được phát hành: (2013)

Single channel speech separation with constrained utterance level permutation invariant training using grid LSTM
Bằng: Xu, Chenglin, et al.
Được phát hành: (2020)

Detecting synthetic speech using long term magnitude and phase information
Bằng: Tian, Xiaohai, et al.
Được phát hành: (2018)

Improving air traffic control speech intelligibility by reducing speaking rate effectively
Bằng: Hou, Nana, et al.
Được phát hành: (2020)

Multi-task learning for end-to-end noise-robust bandwidth extension
Bằng: Hou, Nana, et al.
Được phát hành: (2020)

Vulnerability of speaker verification systems against voice conversion spoofing attacks : the case of telephone speech
Bằng: Kinnunen, Tomi, et al.
Được phát hành: (2013)

Learning affective representations based on magnitude and dynamic relative phase information for speech emotion recognition
Bằng: Guo, Lili, et al.
Được phát hành: (2022)

Digital signal processing for voice enhancement recognition & search
Bằng: Chng, Eng Siong.
Được phát hành: (2009)

Real time noise-speech discrimination in time domain for speech recognition application
Bằng: Mokhtar, Norrima, et al.
Được phát hành: (2011)

Speaker and phoneme-aware speech bandwidth extension with residual dual-path network
Bằng: Hou, Nana, et al.
Được phát hành: (2020)

Context dependant phone mapping for cross-lingual acoustic modeling
Bằng: Do, Van Hai, et al.
Được phát hành: (2013)

Speech recognition based on front-end noise removal algorithms
Bằng: Dai, Peng
Được phát hành: (2015)

Speech enhancement method to reduce non-stationary noise /
Bằng: Farizah Yunus, 1985-, et al.
Được phát hành: (2009)

Collection and annotation of Malay conversational speech corpus
Bằng: Chong, Tze Yuang, et al.
Được phát hành: (2013)

Front-end noise reduction algorithms for automatic speech recognition
Bằng: Dai, Peng
Được phát hành: (2014)

Speech processing for makhraj recognition: The design of adaptive filter for noise canceller
Bằng: Nurul Wahidah, Arshad, et al.
Được phát hành: (2011)

Speech processing for makhraj recognition (design adaptive filter for noise removal)
Bằng: Siti Nurmaisarah, Abdul Aziz
Được phát hành: (2010)

Spoofing detection from a feature representation perspective
Bằng: Tian, Xiaohai, et al.
Được phát hành: (2018)

Applications of broad class knowledge for noise robust speech recognition
Bằng: Sainath, Tara N
Được phát hành: (2010)

Robust speech features and acoustic models for speech recognition
Bằng: Xiao, Xiong
Được phát hành: (2010)

Speech enhancement by modeling of stationary time-frequency regions
Bằng: Galarza, Rubén E. (Rubén Emiliano), 1974-
Được phát hành: (2013)

Non-Taylor series based positioning method for location based services
Bằng: Tan, Kim Geok, et al.
Được phát hành: (2008)

The Evaluation Of Controller Tracking Performance Based On Taylor’s Series Expansion Model
Bằng: Maziyah, Mat Noh, et al.
Được phát hành: (2015)

Speech enhancement method to reduce non-stationary noise [electronic resource] /
Bằng: Farizah Yunus, 1985-
Được phát hành: (2009)

Taylor series [filem]
Được phát hành: ([n.d)

Speech enhancement : identification and modeling of stationary time-frequency regions
Bằng: Yoo, Chang D. (Chang Dong)
Được phát hành: (2005)

Speech recognition and synthesis
Bằng: Kang, Yi Da
Được phát hành: (2023)