9,297 Hits in 5.3 sec

The effect of part-of-speech on Mandarin speech recognition

Caixia Gong, Xiangang Li, Xihong Wu
2013 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference  
This paper concentrates on the effect of part-ofspeech on Mandarin speech recognition by incorporating it into language model and pronunciation dictionary.  ...  This work is motivated by the two benefits of part-of-speech, one is to reduce the lexical ambiguity in language model to some extent and the other is to provide some information about the pronunciation  ...  To answer these questions, this paper investigates the effects of part-of-speech for Mandarin speech recognition carefully.  ... 
doi:10.1109/apsipa.2013.6694172 dblp:conf/apsipa/GongLW13 fatcat:cf6dz235wrf6niuzk6xurdjndm

Effects of Semantic Context and Fundamental Frequency Contours on Mandarin Speech Recognition by Second Language Learners

Linjun Zhang, Yu Li, Han Wu, Xin Li, Hua Shu, Yang Zhang, Ping Li
2016 Frontiers in Psychology  
The masker speech was edited to be, on average, 500 ms longer than the target speech in order to ensure that no part of the speech target was unmasked.  ...  The contribution of F0 contours to Mandarin speech recognition by L2 learners might be attributed to the development of sensitivity to Mandarin-specific F0 patterns and reflect, at least in part, the acquisition  ...  SUPPLEMENTARY MATERIAL The Supplementary Material for this article can be found online at: 2016.00908  ... 
doi:10.3389/fpsyg.2016.00908 pmid:27378997 pmcid:PMC4905971 fatcat:tottc34fvvc43aout3niq6gi5e

The effect of language experience on perceptual normalization of Mandarin tones and non-speech pitch contours

Xin Luo, Krista B. Ashmore
2014 Journal of the Acoustical Society of America  
Contrastive context effects (more rising responses in the high-f0 context than in the low-f0 context) were found with both speech and non-speech stimuli for Mandarin listeners, but not for English listeners  ...  The role of language experience in tone normalization remains unclear.  ...  Research was supported in part by National Institutes of Health Grant No. R21-DC-011844. Carrell, T. D., Smith, L. B., and Pisoni, D. B. (1981).  ... 
doi:10.1121/1.4874619 pmid:24907821 pmcid:PMC4048445 fatcat:w2lcho2ezfgi7j3taob4iaeulm

TALCS: An Open-Source Mandarin-English Code-Switching Corpus and a Speech Recognition Baseline [article]

Chengfei Li, Shuhao Deng, Yaoping Wang, Guangjing Wang, Yaguang Gong, Changbin Chen, Jinfeng Bai
2022 arXiv   pre-print
This paper introduces a new corpus of Mandarin-English code-switching speech recognition--TALCS corpus, suitable for training and evaluating code-switching speech recognition systems.  ...  TALCS corpus is derived from real online one-to-one English teaching scenes in TAL education group, which contains roughly 587 hours of speech sampled at 16 kHz.  ...  These open source datasets effectively promote the development of Mandarin speech recognition.  ... 
arXiv:2206.13135v1 fatcat:rhldqph355a5bagwtfe55bzqw4

Comparing Speech and Keyboard Text Entry for Short Messages in Two Languages on Touchscreen Phones

Sherry Ruan, Jacob O. Wobbrock, Kenny Liou, Andrew Ng, James A. Landay
2018 Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies  
With the ubiquity of mobile touchscreen devices like smartphones, two widely used text entry methods have emerged: small touch-based keyboards and speech recognition.  ...  We found that with speech recognition, the English input rate was 2.93 times faster (153 vs. 52 WPM), and the Mandarin Chinese input rate was 2.87 times faster (123 vs. 43 WPM) than the keyboard for short  ...  ACKNOWLEDGMENTS The authors thank He Dang of Baidu's Speech Technology group, who performed a preliminary study that inspired this research project.  ... 
doi:10.1145/3161187 fatcat:gj5fh3vubjctlixxqr4hhfjswq

Mandarin Speech Recognition for Nonnative Speakers Based on Pronunciation Dictionary Adaptation

Jian Yang, Peishan Wu, Dan Xu
2008 2008 6th International Symposium on Chinese Spoken Language Processing  
According typical pronunciation variations of these 3 accents, the more than one pronunciation for a part of words (i.e. tonal syllables or characters) have been inserted in the standard Mandarin pronunciation  ...  In this paper, we propose to analyze the regular pairs of the pronunciation variation of the nonnative Mandarin speech spoken by Dai, Lisu and Naxi speakers from Yunnan.  ...  ACKNOWLEDGEMENTS We gratefully acknowledge the supports from grants of The Applied Basic Research Programs of Yunnan Province  ... 
doi:10.1109/chinsl.2008.ecp.66 dblp:conf/iscslp/YangWX08 fatcat:7zpgpwnkpzc6telz2xjz7fqhxe

Multi-level Speech Emotion Recognition Based on HMM and ANN

Xia Mao, Lijiang Chen, Liqin Fu
2009 2009 WRI World Congress on Computer Science and Information Engineering  
The recognition result of the hybrid classification has been compared with the isolated HMMs by two speech corpora, Germany database and Mandarin database, and the average recognition rates have reached  ...  Speech emotion recognition, as a vital part of affective human computer interaction, has become a new challenge to speech processing.  ...  Emotion recognition of speech as a significant part has become a challenge to speech processing.  ... 
doi:10.1109/csie.2009.113 dblp:conf/csie/MaoCF09 fatcat:lytwsibvnzgjhetfwjtsdgca3a

Automatic visual feature extraction for Mandarin audio-visual speech recognition

Tsang-Long Pao, Wen-Yuan Liao, Tsan-Nung Wu, Ching-Yi Lin
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
The experimental results based on Mandarin databases demonstrate that the visual information is highly effective for improving the recognition performance.  ...  We present recognition performance using various visual features to explore their impact on the recognition accuracy. These features include the geometric and the motion of the lip.  ...  However, tones are probably the most difficult part of Mandarin. The combination of the initial, final and tone yields around 1,340 Mandarin sounds.  ... 
doi:10.1109/icsmc.2009.5346011 dblp:conf/smc/PaoLWL09 fatcat:f7tchwo5dbhjlo5t34twejnkrm

Utterance verification using prosodic information for Mandarin telephone speech keyword spotting

Yeou-Jiunn Chen, Chung-Hsien Wu, Gwo-Lang Yan
1999 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258)  
For keyword recognition, 59 context-independent subsyllables, i.e., 22 m s and 37 FINAL'S in Mandarin speech, and one backgroundkilence model, are used as the basic recognition units.  ...  In this paper, the prosodic information, a very special and important feature in Mandarin speech, is used for Mandarin telephone speech utterance verification.  ...  In recent years, the most popular configuration of Mandarin Chinese speech recognition consists of two subrecognizers. One is tone recognizer and the other is phoneme or syllable recognizer [3] .  ... 
doi:10.1109/icassp.1999.759762 dblp:conf/icassp/ChenWY99 fatcat:zwnnm36it5dfritpavak5qapxu

Tagging Tone for Mandarin Pinyin Based on Sequence Labelling

Zhaopeng Qian, Kejing Xiao
2021 DEStech Transactions on Environment Energy and Earth Science  
However, the Mandarin Electro-Laryngeal (EL) speech with fixed F0 has no tone information. Therefore, the tone recognition of Mandarin EL speech is so difficult.  ...  And the researches about tone recognition for Mandarin EL speech is insufficient.  ...  This study was supported by the Open Project Program of National Engineering Laboratory for Agriproduct Quality Traceability, (No. AQT-2018-YB4), and Beijing Natural Science Foundation (No. 4194079).  ... 
doi:10.12783/dteees/peees2020/35462 fatcat:zusa6v4n7ngl3ap7ixm26pegr4

Multi-Task Learning in Deep Neural Networks for Mandarin-English Code-Mixing Speech Recognition

Mengzhe CHEN, Jielin PAN, Qingwei ZHAO, Yonghong YAN
2016 IEICE transactions on information and systems  
Multi-task learning in deep neural networks has been proven to be effective for acoustic modeling in speech recognition.  ...  On the realworld Mandarin-English test corpus in mobile voice search, the proposed schemes enhanced the recognition on both languages and reduced the relative overall error rates by 3.5%, 3.8% and 5.8%  ...  Acknowledgments This work is partially supported by the National Nat-  ... 
doi:10.1587/transinf.2016sll0004 fatcat:rsoewvqt3jhmbfckaclfsks4pa

Statistical Analysis of Mandarin Acoustic Units and Automatic Extraction of Phonetically Rich Sentences Based Upon a very Large Chinese Text Corpus

Hsin-Min Wang
1998 International Journal of Computational Linguistics and Chinese Language Processing  
Because the Chinese language is not alphabetic and input of Chinese characters into computers is very difficult, Mandarin speech recognition is very highly desired.  ...  extract phonetically rich sentences from the text corpus to be used in training and evaluating a Mandarin speech recognition system.  ...  Thanks are also due to the three anonymous reviewers for their valuable suggestions.  ... 
dblp:journals/ijclclp/Wang98 fatcat:ujtunjbwcneqxetbaxlbbooezy

Mandarin Chinese Tone Recognition with an Artificial Neural Network

Xu Li, Zhang Wenle, Zhou Ning, Lee Chaoyang, Li Yongxin, Chen Xiuwu, Zhao Xiaoyan
2006 Journal of Otology  
Mandarin Chinese tone patterns vary in one of the four ways, i.e, (1) high level; (2) rising; (3) low falling and rising; and (4) high falling.  ...  All subjects were native Mandarin Chinese speakers. The fundamental frequencies (F0) of each monosyllabic word of the speech data were extracted with an autocorrelation method.  ...  The study was supported in part by NIH NIDCD Grant R03-DC006161.  ... 
doi:10.1016/s1672-2930(06)50005-4 fatcat:6nohl77cbbavdllquxhudvj6qi

Towards Language-Universal Mandarin-English Speech Recognition

Shiliang Zhang, Yuan Liu, Ming Lei, Bin Ma, Lei Xie
2019 Interspeech 2019  
Experimental results on a Mandarin-English code-switching test set show that it can achieve 11.8% and 17.9% relative error reduction on Mandarin and English parts, respectively.  ...  In this work, we jointly study multilingual and codeswitching problems, and present a language-universal bilingual system for Mandarin-English speech recognition.  ...  Particularly, we showcase the capability of our model on the bilingual Mandarin-English speech recognition.  ... 
doi:10.21437/interspeech.2019-1365 dblp:conf/interspeech/ZhangLLMX19 fatcat:a2jq5aa2arakrcsyh2gqhgjsji

An RNN-based preclassification method for fast continuous Mandarin speech recognition

Sin-Horng Chen, Yuan-Fu Liao, Song-Mao Chiang, Saga Chang
1998 IEEE Transactions on Speech and Audio Processing  
A novel recurrent neural network-based (RNN-based) frontend preclassification scheme for fast continuous Mandarin speech recognition is proposed in this paper.  ...  The decision is made based on examining whether the RNN discriminates well between classes.  ...  Effectiveness of the proposed method is thus demonstrated via incorporating it with a CDHMM-based continuous 411 Mandarin base-syllables recognizer.  ... 
doi:10.1109/89.650315 fatcat:okmw7hnxj5fxtilkbia3clhn2a
« Previous Showing results 1 — 15 out of 9,297 results