We present a multichannel speech enhancement method based on MAP speech spectral magnitude estimation using a generalized gamma model of speech prior distribution, where the model parameters are adapted from actual noisy speech in a frame-by-frame manner. The utilization of a more general prior distribution with its online adaptive estimation is shown to be effective for speech spectral estimation in noisy environments. Furthermore, the multi-channel information in terms of cross-channel statistics are shown to be useful to better adapt the prior distribution parameters to the actual observation, resulting in better performance of speech enhancement algorithm. We tested the proposed algorithm in an in-car speech database and obtained significant improvements of the speech recognition performance, particularly under non-stationary noise conditions such as music, air-conditioner and open window.

Complex speech analysis for an analytic speech signal can accurately estimate the spectrum in low frequencies since the analytic signal provides spectrum only over positive frequencies. The remarkable feature makes it possible to realize more accurate F0 estimation using complex residual signal extracted by complex-valued speech analysis. We have already proposed F0 estimation using complex LPC residual, in which the autocorrelation function weighted by AMDF was adopted as the criterion. The method adopted MMSE-based complex LPC analysis and it has been reported that it can estimate more accurate F0 for IRS filtered speech corrupted by white Gauss noise although it can not work better for the IRS filtered speech corrupted by pink noise. In this paper, robust complex speech analysis based on ELS (Extended Least Square) method is introduced in order to overcome the drawback. The experimental results for additive white Gauss or pink noise demonstrate that the proposed algorithm based on robust ELS-based complex AR analysis can perform better than other methods.

Chinese is a representative tonal language, and it has been an attractive topic of how to process tone information in the state-of-the-art large vocabulary speech recognition system. This paper presents a novel way to derive an efficient phoneme set of tone-dependent units to build a recognition system, by iteratively merging a pair of tone-dependent units according to the principle of minimal loss of the Mutual Information (MI). The mutual information is measured between the word tokens and their phoneme transcriptions in a training text corpus, based on the system lexical and language model. The approach has a capability to keep discriminative tonal (and phoneme) contrasts that are most helpful for disambiguating homophone words due to lack of tones, and merge those tonal (and phoneme) contrasts that are not important for word disambiguation for the recognition task. This enables a flexible selection of phoneme set according to a balance between the MI information amount and the number of phonemes. We applied the method to traditional phoneme set of Initial/Finals, and derived several phoneme sets with different number of units. Speech recognition experiments using the derived sets showed its effectiveness.

We present a new framework for checking safety failures. The approach is based on the conservative inference of the internal states of a system by the observation of the interaction with its environment. It is based on two similar mechanisms : forward implication, which performs the analysis of the consequences of an input applied to the system, and backward implication, that performs the same task for an output transition. While being a very simple approach, it is general and we believe it can yield efficient algorithms in different safety-failure checking problems. As a case study, we have applied this framework to an existing problem, the hazard checking in (speed-independent) asynchronous circuits. Our new methodology yields an efficient algorithm that performs better or as well as all existing algorithms, while being more general than the fastest one.

An effective feature compensation method is developed for reliable speech recognition in real-life in-vehicle environments. The CU-Move corpus, used for evaluation, contains a range of speech and noise signals collected for a number of speakers under actual driving conditions. PCGMM-based feature compensation, considered in this paper, utilizes parallel model combination to generate noise-corrupted speech model by combining clean speech and the noise model. In order to address unknown time-varying background noise, an interpolation method of multiple environmental models is employed. To alleviate computational expenses due to multiple models, an Environment Transition Model is employed, which is motivated from Noise Language Model used in Environmental Sniffing. An environment dependent scheme of mixture sharing technique is proposed and shown to be more effective in reducing the computational complexity. A smaller environmental model set is determined by the environment transition model for mixture sharing. The proposed scheme is evaluated on the connected single digits portion of the CU-Move database using the Aurora2 evaluation toolkit. Experimental results indicate that our feature compensation method is effective for improving speech recognition in real-life in-vehicle conditions. A reduction of 73.10% of the computational requirements was obtained by employing the environment dependent mixture sharing scheme with only a slight change in recognition performance. This demonstrates that the proposed method is effective in maintaining the distinctive characteristics among the different environmental models, even when selecting a large number of Gaussian components for mixture sharing.

A sweep spectrum analyzer has been improved over the years, but the fundamental method has not been changed before the 'Super Sweep' method appeared. The 'Super Sweep' method has been expected to break the limitation of the conventional sweep spectrum analyzer, a limit of the maximum sweep rate which is in inverse proportion to the square of the frequency resolution. The superior performance of the 'Super Sweep' method, however, has not been experimentally proved yet. This paper gives the experimental evaluation on the 'Super Sweep' spectrum analyzer, of which theoretical concepts have already been presented by the authors of this paper. Before giving the experimental results, we give complete analysis for a sweep spectrum analyzer and express the principle of the super-sweep operation with a complete set of equations. We developed an experimental system whose components operated in an optimum condition as the spectrum analyzer. Then we investigated its properties, a peak level reduction and broadening of the frequency resolution of the measured spectrum, by changing the sweep rate. We also confirmed that the experimental system satisfactorily detected the spectrum at least 30 times faster than the conventional method and the sweep rate was in proportion to the bandwidth of the base band signal to be analyzed. We proved that the 'Super Sweep' method broke the restriction of the sweep rate put on a conventional sweep spectrum analyzer.

Robust automatic language identification (LID) is the task of identifying the language from a short utterance spoken by an unknown speaker. The mainstream approaches include parallel phone recognition language modeling (PPRLM), support vector machine (SVM) and the general Gaussian mixture models (GMMs). These systems map the cepstral features of spoken utterances into high level scores by classifiers. In this paper, in order to increase the dimension of the score vector and alleviate the inter-speaker variability within the same language, multiple data groups based on supervised speaker clustering are employed to generate the discriminative language characterization score vectors (DLCSV). The back-end SVM classifiers are used to model the probability distribution of each target language in the DLCSV space. Finally, the output scores of back-end classifiers are calibrated by a pair-wise posterior probability estimation (PPPE) algorithm. The proposed language identification frameworks are evaluated on 2003 NIST Language Recognition Evaluation (LRE) databases and the experiments show that the system described in this paper produces comparable results to the existing systems. Especially, the SVM framework achieves an equal error rate (EER) of 4.0% in the 30-second task and outperforms the state-of-art systems by more than 30% relative error reduction. Besides, the performances of proposed PPRLM and GMMs algorithms achieve an EER of 5.1% and 5.0% respectively.

In this paper, we propose a design for testability method for test programs of software-based self-test using test program templates. Software-based self-test using templates has a problem of error masking where some faults detected in a test generation for a module are not detected by the test program synthesized from the test. The proposed method achieves 100% template level fault efficiency, that is, it completely avoids the error masking. Moreover, the proposed method has no performance degradation (adds only observation points) and enables at-speed testing.

This paper proposes a novel technique in designing the optimum pulse shape for ultra wideband (UWB) systems under the presence of timing jitter. In the UWB systems, pulse transmission power and timing jitter tolerance are crucial keys to communications success. While there is a strong desire to maximize both of them, one must be traded off against the other. In the literature, much effort has been devoted to separately optimize each of them without considering the drawback to the other. In this paper, both factors are jointly considered. The proposed pulse attains the adequate power to survive the noise floor and at the same time provides good resistance to the timing jitter. The proposed pulse also meets the power spectral mask restriction as prescribed by the Federal Communications Commission (FCC) for indoor UWB systems. Simulation results confirm the advantages of the proposed pulse over other previously known UWB pulses. Parameters of the proposed optimization algorithm are also investigated in this paper.

In this paper, we propose a PLSA-based language model for sports-related live speech. This model is implemented using a unigram rescaling technique that combines a topic model and an n-gram. In the conventional method, unigram rescaling is performed with a topic distribution estimated from a recognized transcription history. This method can improve the performance, but it cannot express topic transition. By incorporating the concept of topic transition, it is expected that the recognition performance will be improved. Thus, the proposed method employs a "Topic HMM" instead of a history to estimate the topic distribution. The Topic HMM is an Ergodic HMM that expresses typical topic distributions as well as topic transition probabilities. Word accuracy results from our experiments confirmed the superiority of the proposed method over a trigram and a PLSA-based conventional method that uses a recognized history.

This paper proposes a technique for building an effective speech corpus with lower cost by utilizing a statistical multidimensional scaling method. The statistical multidimensional scaling method visualizes multiple HMM acoustic models into two-dimensional space. At first, a small number of voice samples per speaker is collected; speaker adapted acoustic models trained with collected utterances, are mapped into two-dimensional space by utilizing the statistical multidimensional scaling method. Next, speakers located in the periphery of the distribution, in a plotted map are selected; a speech corpus is built by collecting enough voice samples for the selected speakers. In an experiment for building an isolated-word speech corpus, the performance of an acoustic model trained with 200 selected speakers was equivalent to that of an acoustic model trained with 533 non-selected speakers. It means that a cost reduction of more than 62% was achieved. In an experiment for building a continuous word speech corpus, the performance of an acoustic model trained with 500 selected speakers was equivalent to that of an acoustic model trained with 1179 non-selected speakers. It means that a cost reduction of more than 57% was achieved.

This letter mainly focuses on improving current noise reduction methods to solve the critical speech distortion problems with robust noise reduction in noisy speech signals for speech enhancement over IP networks. For robust noise reduction with packet loss recovery, we propose a novel optimized Wiener filtering technique that uses the estimated SNR (Signal-to-Noise Ratio) with packet loss recovery method which is applied as post-filtering over IP-networks. Simulation results demonstrate that the proposed scheme provides better reduction and recovery rates with considering packet loss and SNR environment than other methods.

Speech recognition in a noisy environment is one of the hottest topics in the speech recognition research. Noise-tolerant acoustic models or noise reduction techniques are often used to improve recognition accuracy. In this paper, we propose a method to improve accuracy of spoken dialog system from a language model point of view. In the proposed method, the dialog system automatically changes its language model and dialog strategy according to the estimated recognition accuracy in a noisy environment in order to keep the performance of the system high. In a noise-free environment, the system accepts any utterance from a user. On the other hand, the system restricts its grammar and vocabulary in a noisy environment. To realize this strategy, we investigated a method to avoid the user's out-of-grammar utterances through an instruction given by the system to a user. Furthermore, we developed a method to estimate recognition accuracy from features extracted from noise signals. Finally, we realized a proposed dialog system according to these investigations.

We have previously proposed a noise-robust speaker verification method using fundamental frequency (F0) extracted using the Hough transform. The method also incorporates an automatic stream-weight and decision threshold estimation technique. It has been confirmed that the proposed method is effective for white noise at various SNR conditions. This paper evaluates the proposed method in more practical in-car and elevator-hall noise conditions. The paper first describes the noise-robust F0 extraction method and details of our robust speaker verification method using multi-stream HMMs for integrating the extracted F0 and cepstral features. Details of the automatic stream-weight and threshold estimation method for multi-stream speaker verification framework are also explained. This method simultaneously optimizes stream-weights and a decision threshold by combining the linear discriminant analysis (LDA) and the Adaboost technique. Experiments were conducted using Japanese connected digit speech contaminated by white, in-car, or elevator-hall noise at various SNRs. Experimental results show that the F0 features improve the verification performance in various noisy environments, and that our stream-weight and threshold optimization method effectively estimates control parameters so that FARs and FRRs are adjusted to achieve equal error rates (EERs) under various noisy conditions.

This paper describes a robust automatic speech recognition (ASR) system with less computation. Acoustic models of a hidden Markov model (HMM)-based classifier include various types of hidden factors such as speaker-specific characteristics, coarticulation, and an acoustic environment, etc. If there exists a canonicalization process that can recover the degraded margin of acoustic likelihoods between correct phonemes and other ones caused by hidden factors, the robustness of ASR systems can be improved. In this paper, we introduce a canonicalization method that is composed of multiple distinctive phonetic feature (DPF) extractors corresponding to each hidden factor canonicalization, and a DPF selector which selects an optimum DPF vector as an input of the HMM-based classifier. The proposed method resolves gender factors and speaker variability, and eliminates noise factors by applying the canonicalzation based on the DPF extractors and two-stage Wiener filtering. In the experiment on AURORA-2J, the proposed method provides higher word accuracy under clean training and significant improvement of word accuracy in low signal-to-noise ratio (SNR) under multi-condition training compared to a standard ASR system with mel frequency ceptral coeffient (MFCC) parameters. Moreover, the proposed method requires a reduced, two-fifth, Gaussian mixture components and less memory to achieve accurate ASR.

To achieve high recognition performance for a wide variety of noise and for a wide range of signal-to-noise ratio, this paper presents methods for integration of four noise reduction algorithms: spectral subtraction with smoothing of time direction, temporal domain SVD-based speech enhancement, GMM-based speech estimation and KLT-based comb-filtering. In this paper, we proposed two types of combination methods of noise suppression algorithms: selection of front-end processor and combination of results from multiple recognition processes. Recognition results on the CENSREC-1 task showed the effectiveness of our proposed methods.

We propose a domain specific model for statistical machine translation. It is well-known that domain specific language models perform well in automatic speech recognition. We show that domain specific language and translation models also benefit statistical machine translation. However, there are two problems with using domain specific models. The first is the data sparseness problem. We employ an adaptation technique to overcome this problem. The second issue is domain prediction. In order to perform adaptation, the domain must be provided, however in many cases, the domain is not known or changes dynamically. For these cases, not only the translation target sentence but also the domain must be predicted. This paper focuses on the domain prediction problem for statistical machine translation. In the proposed method, a bilingual training corpus, is automatically clustered into sub-corpora. Each sub-corpus is deemed to be a domain. The domain of a source sentence is predicted by using its similarity to the sub-corpora. The predicted domain (sub-corpus) specific language and translation models are then used for the translation decoding. This approach gave an improvement of 2.7 in BLEU score on the IWSLT05 Japanese to English evaluation corpus (improving the score from 52.4 to 55.1). This is a substantial gain and indicates the validity of the proposed bilingual cluster based models.

The accuracy of automatic speech recognition in a car is significantly degraded in a very low SNR (Signal to Noise Ratio) situation such as "Fan high" or "Window open". In such cases, speech signals are often buried in broadband noise. Although several existing noise reduction algorithms are known to improve the accuracy, other approaches that can work with them are still required for further improvement. One of the candidates is enhancement of the harmonic structures in human voices. However, most conventional approaches are based on comb filtering, and it is difficult to use them in practical situations, because their assumptions for F0 detection and for voiced/unvoiced detection are not accurate enough in realistic noisy environments. In this paper, we propose a new approach that does not rely on such detection. An observed power spectrum is directly converted into a filter for speech enhancement, by retaining only the local peaks considered to be harmonic structures in the human voice. In our experiments, this approach reduced the word error rate by 17% in realistic automobile environments. Also, it showed further improvement when used with existing noise reduction methods.

This paper is aimed to present the design and feasibility investigations of adopting the available on-site optical inspection system, which is commonly used for steel plate dimension measurement, to supply on-line dynamic gap measurements of a non-contacting conveyance structure in a steel mill. Adequate software and hardware implementations based on digital image processing techniques have been adapted to the entire system formulations and estimations. Results show that the system can supply accurate and rapid gap measurements and thus can fulfill the design and operational objectives.

A high-speed triangular-modulated spread-spectrum clock generator using a fractional phase-locked loop is presented. The fractional division is implemented by a nested fractional topology, which is constructed from a dual-modulus divide-by-(N-1/16)/N divider to divide the VCO outputs as a first division period and a fractional control circuit to establish a second division period to cause the overall fractional division. The dual-modulus divider introduces a delay-locked-loop network to achieve phase compensation. Operating at the frequency of 3.2 GHz, the measured peak power reduction is around 16 dB for a deviation of 0.37% and a frequency modulation of 33 kHz. The circuit occupies 1.41.4 mm2 in a 0.18-µm CMOS process and consumes 52 mW.