Xinhui Hu

Hubei University of Medicine

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Satoshi Nakamura

Nara Institute of Science and Technology

Hideki Kashioka

National Institute of Information and Communications Technology

Chiori Hori

Mitsubishi Electric (United States)

Ryosuke Isotani

The University of Tokyo

Xinkang Xu

Beijing Information Science & Technology University

Hisashi Kawai

National Institute of Information and Communications Technology

Shigeki Matsuda

Shiga University

Youzheng Wu

Harbin Institute of Technology

Jingguang Tian

Hirofumi Yamamoto

Osaka University

Cooperative Institutions

National Institute of Information and Communications Technology

Advanced Telecommunications Research Institute International

Kyoto University

Nagoya University

Chinese Academy of Sciences

Kyoto Seika University

NTT (Japan)

South China Normal University

The University of Tokyo

Sun Yat-sen University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Progress Report of SLP Spoken Document Processing Working Group

IEICE Technical Report; IEICE Tech. Rep. (2008)

Tomoyoshi Akiba Kiyoaki Aikawa Yoshiaki Itoh Kawahara Tatsuya Hiroaki Nanjo

Source

Cite

Citations (0)

Japanese Spontaneous Spoken Document Retrieval Using NMF-Based Topic Models

Lecture notes in computer science (2009)

Xinhui Hu Hideki Kashioka Ryosuke Isotani Satoshi Nakamura

Document Clustering

10.1007/978-3-642-04769-5_13

Cite

Citations (1)

A Myanmar large vocabulary continuous speech recognition system

Hay Mar Soe Naing Aye Mya Hlaing Win Pa Pa Xinhui Hu Ye Kyaw Thu

This paper presents a large vocabulary automatic speech recognition (ASR) system for Myanmar. To the best of our knowledge, this is the first such system for the Myanmar language. We will report main processes of developing the system, including data collection, pronunciation lexicon construction, effective acoustic features selection, acoustic and language modelings, and evaluation criteria. Considering the fact that Myanmar being a tonal language, the tonal features were incorporated to acoustic modeling and their effectiveness were verified. Differences between the word-based language model (LM) and syllable-based LM were investigated; the word-based LM was found superior to the syllable-based model. To disambiguate the definitions of Myanmar words and achieve high reliability on the recognition results, we explored the characteristics of the Myanmar language, and proposed the Syllable Error Rate (SER) as a suitable evaluation criterion for Myanmar ASR system. 3 kinds of acoustic models; 1 Gaussian Mixture Model (GMM) and 2 Deep Neural Networks (DNNs) were explored by only utilizing the developed phonemically-balanced corpus consisting of 4K sentences and 40 hours of speech. An open evaluation set containing 100 utterances, spoken by 25 speakers, were experimented. With respect to the sequence discriminative training DNN, the results reached up to 15.63% in word error rate (WER) or 10.87% in SER.

Pronunciation

Word error rate

Discriminative model

Spoken Language

Treebank

10.1109/apsipa.2015.7415529

Cite

Citations (31)

Collecting Colloquial and Spontaneous-like Sentences from Web Resources for Constructing Chinese Language Models of Speech Recognition

Journal of Information Processing (2013)

Xinhui Hu Shigeki Matsuda Chori Hori Hideki Kashioka

In this paper, we present our work on collecting training texts from the Web for constructing language models in colloquial and spontaneous Chinese automatic speech recognition systems. The selection involves two steps: first, web texts are selected using a perplexity-based approach in which the style-related words are strengthened by omitting infrequent topic words. Second, the selected texts are then clustered based on non-noun part-of-speech words and optimal clusters are chosen by referring to a set of spontaneous seed sentences. With the proposed method, we selected over 3.80M sentences. By qualitative analysis on the selected results, the colloquial and spontaneous-speech like texts are effectively selected. The effectiveness of the selection is also quantitatively verified by the speech recognition experiments. Using the language model interpolated with the one trained by these selected sentences and a baseline model, speech recognition evaluations were conducted on an open domain colloquial and spontaneous test set. We effectively reduced the character error rate 4.0% over the baseline model meanwhile the word coverage was also greatly increased. We also verified that the proposed method is superior to a conventional perplexity-based approach with a difference of 1.57% in character error rate.

Perplexity

Word error rate

Baseline (sea)

10.2197/ipsjjip.21.168

Cite

Citations (1)

Spoken document retrieval using topic models

Xinhui Hu Ryosuke Isotani Satoshi Nakamura

In this paper, we propose a document topic model (DTM) based on the non-negative matrix factorization (NMF) approach to explore spontaneous spoken document retrieval. The model uses latent semantic indexing to detect underlying semantic relationships within documents. Each document is interpreted as a generative topic model belonging to many topics. The relevance of a document to a query is expressed by the probability of a query being generated by the model. The term-document matrix used for NMF is built stochastically from the speech recognition N-best results, so that multiple recognition hypotheses can be utilized to compensate for the word recognition errors. Using this approach, experiments are conducted on a test collection from the Corpus of Spontaneous Japanese (CSJ), with 39 queries for over 600 hours of spontaneous Japanese speech. The retrieval performance of this model is proved to be superior to the conventional vector space model (VSM) when the dimension or topic number exceeds a certain threshold. Moreover, whether from the viewpoint of retrieval performance or the ability of topic expression, the NMF-based topic model is verified to surpass another latent indexing method that is based on the singular value decomposition (SVD). The extent to which this topic model can resist speech recognition error, which is a special problem of spoken document retrieval, is also investigated.

Vector space model

Non-negative Matrix Factorization

Relevance

Document Clustering

10.1145/1667780.1667862

Cite

Citations (2)

Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition

Interspeech 2022 (2006)

Xinhui Hu Hirofumi Yamamoto Genichiro Kikui Yoshinori Sagisaka

Chinese language

10.21437/interspeech.2006-516

Cite

Citations (1)

Progress Report of Spoken Document Processing Working Group

Scientific Programming (2011)

Kiyoaki Aikawa Tomoyoshi Akiba Yoshiaki Ito Tatsuya Kawahara Seiichi Nakagawa

Source

Cite

Citations (0)

Learning Unsupervised SVM Classifier for Answer Selection in Web Question Answering

Empirical Methods in Natural Language Processing (2007)

Youzheng Wu Ruiqiang Zhang Xinhui Hu Hideki Kashioka

Previous machine learning techniques for answer selection in question answering (QA) have required question-answer training pairs. It has been too expensive and labor-intensive, however, to collect these training pairs. This paper presents a novel unsupervised support vector machine (USVM) classifier for answer selection, which is independent of language and does not require hand-tagged training pairs. The key ideas are the following: 1. unsupervised learning of training data for the classifier by clustering web search results; and 2. selecting the correct answer from the candidates by classifying the question. The comparative experiments demonstrate that the proposed approach significantly outperforms the retrieval-based model (Retrieval-M), the supervised SVM classifier (S-SVM), and the pattern-based model (Pattern-M) for answer selection. Moreover, the cross-model comparison showed that the performance ranking of these models was: U-SVM > PatternM > S-SVM > Retrieval-M.

Ranking SVM

Source

Cite

Citations (11)

Collecting sentences from web resources for constructing spontaneous Chinese language model

Xinhui Hu Youzheng Wu Shigeki Matsuda Chiori Hori Hideki Kashioka

In this paper, we present our work on collecting spontaneous texts from the Web for constructing a language model in a Chinese speech recognition system. The selection of spontaneous-like texts involves two steps: First, word-segmented web texts are selected using a perplexity-based approach in which the style-related words are strengthened by omitting infrequent topic words from similarity measurements. Second, the selected texts are then clustered based on non-noun part-of-speech (POS) words and optimal clusters are chosen by referring to a set of spontaneous seed sentences. Using the language model interpolated with the one trained by the selected sentences and a baseline model, speech recognition evaluations were conducted on an open domain spontaneous test set. We effectively reduced the character error rate (CER), with 1.64% absolute (or 6.5% relative) reduction by comparison with the baseline model. We also verified that the proposed method is superior to the conventional perplexity-based approach with about 1% absolute (or 4.0% relative) reduction in CER.

Perplexity

Word error rate

Baseline (sea)

10.1109/iscslp.2012.6423548

Cite

Citations (1)

Mandarin speech recognition using convolution neural network with augmented tone features

Xinhui Hu Xugang Lu Chiori Hori

Due to its ability of reducing spectral variations and modeling spectral correlations existed in speech signals, the convolutional neural network (CNN) has been shown effective in modeling speech compared to deep neural network (DNN). In this study, we explore applying CNN to Mandarin speech recognitions. Besides exploring appropriate CNN architecture for recognition performance, focuses are on investigating the effective acoustic features, and effectivenesses of applying tonal information which have been verified helpful in other types of acoustic models to the acoustic features in the CNN. We conduct speech recognition experiments on Mandarin broadcast speech recognition to test the effectivenesses of the proposed approaches. The CNN shows its clear superiority to the DNN, with relative reductions of character error rate (CER) among 7.7-13.1% for broadcast news speech (BN), and 5.4-9.9% for broadcast conversation speech (BC). Like in the Gaussian Mixture Model (GMM) and DNN systems, the tonal information characterized by the fundamental frequency (F ₀ ) and fundamental frequency variations (FFV) are found still helpful in CNN models, they achieve relative CER reductions over 6.7% for BN and 4.3% for BC respectively when compared with the baseline Mel-filter bank feature.

Mandarin Chinese

Tone (literature)

Convolution (computer science)

10.1109/iscslp.2014.6936674

Cite

Citations (10)