The mathematical theory of closed form functions for calculating LSFs on the basis of generating functions is presented. Exploiting recurrence relationships in the series expansion of Chebyshev polynomials of the first kind makes it possible to bootstrap iterative LSF-search from a set of characteristic polynomial zeros. The theoretical analysis is based on decomposition of sequences into symmetric and anti-symmetric polynomials defined as a series expansion of reduced Chebyshev polynomials of the first kind. Two variants of closed form functions are presented — each characterised by using a recurrence relationship in Chebyshev polynomials. The first exploits the well known three terms recurrence relationships of Chebyshev polynomials. The second hitherto unused recurrence properties of Chebyshev coefficients defining a set of coefficients and zeros used for bootstrapping calculation of LSFs. The theory is tested using bootstrapped calculation of zeros and by evaluating the complexity of the closed form function. The results of the lower complexity calculations show that real axis zeros are within a given iteration tolerance when compared to results of a standard root-finder. Full Paper

In the present paper, a method is proposed for adaptive estimation and tracking of roots of time-varying, complex, and univariate polynomials, e.g.z-transform polynomials that arise from finite signal sequences.The objective with the method is to alleviate the computational burden induced by factorization.The estimation is done by solving a set of linear equations; the number of equations equals the order of the polynomial.To avoid potential drifting of the estimations, it is proposed to verify with Aberth-Ehrlich's factorization method at given intervals.A numerical experiment supplements theory by estimating roots of time-varying polynomials of different order.As a function of order, the proposed method has a lower run time than Lindsey-Fox and computing eigenvalues of companion matrices.The estimations are quite accurate, but tend to drift slightly in response to increasing coefficient pertubation lengths.

In recent studies, a non-parametric speech waveform representation (rep.) based on zeros of the z-transform (ZZT) has been proposed. The ZZT rep. has successfully been applied in separating mixed phase signals, e.g. pitch-synchronously windowed speech, into min/max phase by using the unit circle as discriminant. As the ZZT rep. is obtained by factorization of the z-transform, relations to the complex cepstrum (CC) exist. The present paper interrelates the ZZT rep. with the CC via factorization of the z-transform, and demonstrates that unit circle discrimination of a ZZT rep. can be formulated as a CC based separation by causality. A numerical experiment supplements theory by separating a range of LF glottal flow waveforms into their opening and closing phase constituents. Further, randomized mixed phase sequences are separated. As the CC based separation also can be obtained via FFT it has a lower time and space complexity than the ZZT based counterpart.

Current research has proposed a non-parametric speech waveform representation (rep) based on zeros of the z-transform (ZZT) [1] [2]. Empirically, the ZZT rep has successfully been applied in discriminating the glottal and vocal tract components in pitch-synchronously windowed speech by using the unit cir-cle (UC) as discriminant [1] [2]. Further, similarity between ZZT reps of windowed speech, glottal flow waveforms, and waveforms of glottal flow opening and closing phases has been demonstrated [1] [3]. Therefore, the underlying cause of the separation on either side of the UC can be analyzed via the individual ZZT reps of the opening and closing phase wave-forms; the waveforms are generated by the LF glottal flow model (GFM) [1]. The present paper demonstrates this cause and effect analytically and thereby supplement the previous em-pirical works. Moreover, this paper demonstrates that immisci-bility is variant under changes in frame lengths; lengths that maximize or minimize immiscibility are presented. Index Terms: Zeros of the z-transform, LF glottal flow model, opening/closing phase separation

The nonlocal means (NL-means) algorithm recently proposed for image denoising has proved highly effective for removing additive noise while to a large extent maintaining image details. The algorithm performs denoising by averaging each pixel with other pixels that have similar characteristics in the image. This letter considers the real and imaginary parts of complex speech spectrogram each as a separate image and presents a modified NL-means algorithm to them for denoising to improve the noise robustness of speech recognition. Recognition results on a noisy speech database show that the proposed method is superior to classical methods such as spectral subtraction.

In this paper, the temporal correlation of speech is exploited in front-end feature extraction, client-based error recovery, and server-based error concealment (EC) for distributed speech recognition. First, the paper investigates a half frame rate (HFR) front-end that uses double frame shifting at the client side. At the server side, each HFR feature vector is duplicated to construct a full frame rate (FFR) feature sequence. This HFR front-end gives comparable performance to the FFR front-end but contains only half the FFR features. Second, different arrangements of the other half of the FFR features creates a set of error recovery techniques encompassing multiple description coding and interleaving schemes where interleaving has the advantage of not introducing a delay when there are no transmission errors. Third, a subvector-based EC technique is presented where error detection and concealment is conducted at the subvector level as opposed to conventional techniques where an entire vector is replaced even though only a single bit error occurs. The subvector EC is further combined with weighted Viterbi decoding. Encouraging recognition results are observed for the proposed techniques. Lastly, to understand the effects of applying various EC techniques, this paper introduces three approaches consisting of speech feature, dynamic programming distance, and hidden Markov model state duration comparison.

Condition-dependent training strategy divides a training database into a number of clusters, each corresponding to a noise condition and subsequently trains a hidden Markov model (HMM) set for each cluster. This paper investigates and compares a number of condition-dependent training strategies in order to achieve a better understanding of the effects on automatic speech recogntion (ASR) performance as caused by a splitting of the training databases. Also, the relationship between mismatches in signal-to-noise ratio (SNR) is analyzed. The results show that a splitting of the training material in terms of both noise type and SNR value is advantageous compared to previously used methods, and that training of only a limited number of HMM sets is sufficient for each noise type for robustly handling of SNR mismatches. This leads to the introduction of an SNR and noise classification-based training strategy (SNT-SNC). Better ASR performance is obtained on test material containing data from known noise types as compared to either multicondition training or noise-type dependent training strategies. The computational complexity of the SNT-SNC framework is kept low by choosing only one HMM set for recognition. The HMM set is chosen on the basis of results from noise classification and SNR value estimations. However, compared to other strategies, the SNT-SNC framework shows lower performance for unknown noise types. This problem is partly overcome by introducing a number of model and feature domain techniques. Experiments using both artificially corrupted and real-world noisy speech databases are conducted and demonstrate the effectiveness of these methods.

Compared to multi-condition training (MTR), condition-dependent training generates multiple acoustic hidden Markov model sets each identified by a noisy environment and is known to perform substantially better for known noise types (included in training) while worse for unknown (untrained) noise types. This paper attempts to bridge the performance gap between known and unknown noise types by introducing a Minimum Mean-Square Error (MMSE) noise-type based compensation algorithm. On the basis of a modified Vector Taylor Series and the measurement of feature reliability as well as noise similarity, the MMSE estimation adapts the test features corrupted by the unknown noise type to the corresponding features corrupted by the known noise type. This method significantly improves the recognition performance for unknown noise types while maintaining the good performance for known noise types. Furthermore, in order to benefit directly from MTR, a model interpolation strategy is investigated which combines the MTR and the condition-dependent model sets. Both good performance and low computational cost are achieved by only interpolating the mixtures of each condition-dependent model state with the least weighted mixture in the corresponding MTR model state. The overall system gives promising results.

Robustness against transmission errors is one of the primary barriers to the widespread application of automatic speech recognition (ASR) in mobile communications. We have previously proposed a subvector based error concealment (EC) method that conducts error detection and mitigation in the feature-domain at the subvector level. This paper presents a weighted Viterbi decoding (WVD) algorithm that works in the model domain for counteracting unreliable features generated by the subvector based EC. The reliability of each feature is estimated during the process of subvector based EC and is used by the WVD for modifying the observation probability of the feature. Recognition experiments are conducted on the Aurora 2 database corrupted by GSM error pattern EP3. Combining the WVD and the subvector EC achieves 70 % and 24% performance improvement as compared to the ETSI-DSR standard and the subvector based EC, respectively. Index Terms: distributed speech recognition, error concealment, split vector quantization, weighted Viterbi

The introduction of ubiquitous computing and networking has fostered automatic speech recognition (ASR) systems of a distributed nature. The major challenge in deploying ubiquitous ASR is that the operating environments may change rapidly leaving the ASR system very vulnerable. This paper deals with the concept of making ASR systems context-aware with the aim of improving robustness against varying conditions such as dynamic network constraints and environmental noise. To fully benefit from a variety of networks with different characteristics, a number of distributed speech recognition (DSR) schemes are presented each of which is applicable to a specific network context. To increase ASR system robustness in varying environmental noise context, a multiple-model framework for noise-robust ASR is presented where multiple HMM model sets are trained, one for each noise type and each specific signal-to-noise ratio (SNR) that characterise the noise context. Experimental results show that the performance of ASR is largely improved by exploiting the context information. 1.

This paper presents a multiple-model framework for noise-robust speech recognition. In this framework, multiple HMM model sets are trained- each identified by a noise type and a specific Signal-to-Noise Ratio (SNR) value. This, however, does not increase the computational complexity of the recognition process since only one model set is selected according to the noise classification and SNR estimation. The optimal number of model sets is first identified on the basis of the Aurora 2 database. With only three model sets for each noise type, the framework shows superior performance to Multi-style TRaining (MTR) when testing on known noise types but lower performance on unknown noise types. To overcome this drawback, a modified Jacobian method is proposed to adapt the selected HMM models to the test environment. Furthermore, given the fact that MTR often gives relatively stable performance for unknown noise types, a combined technique is applied in which interpolation between the MTR and the adapted models is performed. This combined technique gives more than 24 % performance improvement as compared to MTR. 1.

In this paper a half frame-rate (HFR) front-end is investigated for distributed speech recognition (DSR). The work is inspired from the need for low bit-rate and is justified by the redundancies known to exist in full frame-rate (FFR) features. At the client-side in the DSR architecture, implementation of the HFR is carried out by using double frame shifting as compared to the FFR resulting in the achievement of half the bit rate. At the server-side, each HFR feature vector is repeated once to construct the FFR features and no changes are therefore required in the recognition back-end. It is experimentally justified that the performance achieved by HFR is comparable to FFR and that repetition of each HFR feature vector is critical for the HFR front-end to maintain the performance. Motivated by the effectiveness of HFR, a number of additional FFR-based DSR schemes are further presented. Finally, this paper introduces an adaptive multi-frame-rate scheme in which the DSR system adapts to the characteristics of the transmission channel by switching between HFR and the FFR-based schemes. This multi-frame-rate scheme is found to be superior to the basic FFR

Conventional error concealment (EC) algorithms for distributed speech recognition (DSR) share a common characteristic namely the fact of conducting EC at the vector (or frame) level. This strategy, however, fails to effectively exploit the error-free fraction left within erroneous vectors where a substantial number of subvectors often are error-free. This paper proposes a novel EC approach for DSR encoded by split vector quantization (SVQ) where the detected erroneous vectors are submitted to a further analysis at the subvector level. Specifically, a data consistency test is applied to each erroneous vector to identify inconsistent subvectors. Only inconsistent subvectors are replaced by their nearest neighbouring consistent subvectors whereas consistent subvectors are kept untouched. Experimental results demonstrate that the proposed algorithm in terms of recognition accuracy is superior to conventional EC methods having almost the same complexity and resource requirement.

This paper presents the basic rationale behind the development and testing of a multimodal communication aid especially designed for people suffering from global aphasia, and thus having severe expressive difficulties. The principle of the aid is to trigger patient associations by presenting various multimodal representations of communicative expressions. The aid can in this way be seen as a conceptual continuation of previous research within the field of communication aids based on uni-modal (pictorial) representations of communicative expressions. As patients suffering from global aphasia seldom have identical symptoms, the focus of this paper is placed on the development of a highly dedicated communication aid adaptive to the individual patients’ needs. The paper investigates whether or not such a highly dedicated communication aid based on multimodal representations of communicative expressions can be used to support patients with global aphasia in communicating by means of short sentences with their surroundings. Only a limited evaluation is carried out, and as such no statistically significant results are obtained. The tests however indicate that the aid is capable of supporting a global aphasia patient in participating in conversations based on short sentences which otherwise would be impossible without the use of a communication aid.

Mobile communication presents a number of challenges to speech technology such as the limited resources available in the terminals in addition to the bandwidth constraints and the errors occurring in transmissions over mobile networks. These challenges need to be solved before automatic speech recognition (ASR) is ready for widespread use in the context of personal communication environments. This paper gives an overview of the problems inherent in the recently developed network based ASR with an emphasis on the robustness issues that are highly influenced by network degradations. The paper further presents a number of transmission error protection and concealment schemes that are evaluated in a number of ASR experiments encompassing a range of typical real-environment transmission errors. 1.

In standard Spectral Subtraction (SS), Half-Wave Rectification SS (HWR-SS) is normally applied to avoid negative values in the Power Spectral Density (PSD) that occur mainly due to inaccurate noise estimation caused by a Voice Activity Detector (VAD). In this paper analyses show that, given accurate noise estimation, the phase relationship between speech and noise becomes the dominant cause of the negative values. FullWave Rectification based SS (FWR-SS) combined with Instantaneous Noise Estimation (INE) is therefore proposed to be applied instead of VAD based HWR-SS as it is better capable of maintaining the speech information in those negative values. It is also shown in the paper that FWR-SS provides optimum orthogonality between the estimated noise and speech signals. The INE method proposed in this paper is Likelihood Controlled Instantaneous Noise Estimation (LCINE), which combines long-term statistical characteristics of noise resulting from a VAD with a method of short-term INE. The combination of FWR-SS and LCINE is computationally efficient and shows a 51% error rate reduction on the Aurora 2 database in comparison to the basic Aurora front-end provided by ETSI [1].

This paper presents research on two aspects of distributed speech recognition (DSR) in the presence of channel transmission errors in wireless network environments. The first is on experiments with a frame-based channel error protection scheme, where in previous research we reported results from experiments using randomly distributed bit-errors. This paper presents results from experiments using three additional, more realistic error distributions: burst-like packet loss, GSM error patterns and UMTS statistics. The second is on exploiting the knowledge about channel transmission errors for the purpose of optimising the Out-of-Vocabulary (OOV) detection. Transmission errors influence the acoustic likelihood, and therefore affect the optimal threshold setting for discrimination between In-Vocabulary (IV) words and OOV words. An OOV-detection method is proposed in which the estimated Frame-Error-Rate (FER) is used to adjust the discrimination threshold. Results from experiments are reported over a range of transmission errors.

This paper describes ongoing research preparing for the widespread deployment of spoken language processing in networks encompassing wired and wireless transmission channels. The paper gives a brief overview of the standardized bit-error protection scheme aimed at minimising channel transmission errors and used within the distributed speech recognition (DSR) paradigm. Within the ETSI-DSR standard, two quantised mel-spectral frames – each of 10 ms duration- are grouped together and protected with a 4-bit Cyclic Redundancy Checking (CRC) forming a frame-pair. However, this causes the entire frame-pair erroneous if a one-bit error only occurs in the frame-pair packet. Over an error-prone transmission channel this format will cause severe problems. To overcome this, the paper presents a one-frame architecture in which a 4-bit CRC is calculated to protect each frame independently. This scheme results in that the overall probability of one frame in error is lower, or that an error occurring in one frame does not affect another frame. A number of simple recognition experiments have been conducted to verify the introduction of the one-frame CRC protection scheme for a number of simulated transmission channel bit-error rates (BER) ranging from 0 (no transmission channel involved) to 2٠10-2. Experimental results show that the one-frame protection scheme is more robust to channel errors although a slight increase in the error-protection overhead is needed. 1.

Two systems (statistical trajectory models (STM) and continuous density HMMs) utilizing three preprocessing methodologies (MFCC, RASTA and FBDYN) were evaluated on two databases, namely CTIMIT and the corresponding down-sampled TIMIT. Within the bounds of the experimental setup the comparative performance analysis showed that the STM significantly outperforms the HMM system on the CTIMIT database. Specifically, the performance of the STM system was found to be at least 10% better as compared to the one obtained by HMM when the RASTA preprocessing was used. The performance of both systems with FBDYN parametrization was found to be inferior to those using MFCC and RASTA. On the other hand, in low-noise conditions on the TIMIT database FBDYN yielded an improved performance for the HMM system, whereas STM achieved the best results with the MFCC parametrization.

decoding, the second transforms the parameters from This work is concerned with the subject of language- the decoding module and classifies the language. identification (LID). Two central issues are addressed. The common acoustic signal preprocessor calculates The first is to analyse the trade-off between detailed 12 RASTA filtered MFCC's, their first derivatives and acoustic modelling and robust estimation of acoustic the delta-log-energy. The phone and language decoding and language models. The second to find the optimal module consists of three parallel branches. In each of combination of acoustic and language scores for language- these the phone recogniser matches the acoustic identification. parameters to the acoustic models used by that recogniser. Experiments are carried out using the three languages The output from each recogniser is further matched American-English, German and Spanish from the OGI-TS against three language models. database. It is shown that on the average th...

Recently, we described a two-step self-learning approach for grapheme-to-phoneme (G2P) conversion [1].In the first step, grapheme and phoneme strings in the training data are aligned via an iterative Viterbi procedure that may insert graphemic and phonemic nulls where required.In the second step, a Trie structure encoding pronunciation rules is generated.In this paper we describe the alignment module, and give alignment accuracies on the NETtalk database.We also compare transcription accuracies for two approaches to the second step on three databases: the NETtalk database, the CMU dictionary and the French part of the ONOMASTICA lexicon.The two transcription approaches applied in this research are a Trie approach [1] and an approach based on binary decision trees grown by means of the Gelfand-Ravishankar-Delp algorithm [2,3,4].We discuss the choice of questions for these decision trees -it may be possible to formulate questions about groups of characters (e.g., "is the next letter a vowel?") that yield better trees than those that only use questions about individual characters (e.g., "is the next letter an 'A' ?").Finally, we discuss the implications of our work for G2P conversion.

A Self-Learning system for Grapheme to Phoneme conversion is described and tested. The system acquires the knowledge needed for grapheme-to-phoneme conversion from a training session in which a large number of pairs of grapheme strings and their corresponding (manually verified) phonemic transcription strings are presented to the system. The result from the training is a stochastic decision tree in which statistics - as given in the training material - about corresponding graphemes and phonemes are stored for later retrieval. The system is tested on a number of European languages and results from three tests are reported. In the first test, which concerns proper names, only the most probable phoneme candidate at each leaf of the tree is utilised. The second and the third test, both using a database of ordinary words, aims at analysing phoneme and word accuracies resulting from using N-Best phonemes at each leaf and from introducing phonotactic information, respectively. Using N-Best ...

The research reported in this paper presents a method to identify poly- and mono-phonemes for four European languages. The functionality of the poly-phonemes is tested in two experiments, and a limited set of mono-phonemes is identified for a language-identification experiment. Ten acoustically-similar speech sounds were identified across the four languages British-English, Danish, German, and Italian. These sounds, which constitute a substantial proportion of the phonemes of each language, are designated as (language independent) poly-phonemes, and may serve as a multi-lingual training base for labelling and recognition systems. The remaining sounds of each language, which do not fulfil the similarity conditions, are dubbed mono-phonemes. Two application experiments were conducted. In the first the poly-phonemes are applied in a label alignment task. In the second a small selected of mono-phonemes for each of the four languages is used in a preliminary test of the ability of these sets to serve as language discriminators.>

Results are reported from research on the use of continuously valued acoustic-phonetic features in the multi-language label alignment of combined speech corpora from three European languages: Danish, English, and Italian. A self-organizing neural network is used to transform cepstrum coefficients into a set of features, which are subsequently transformed into a set of principal components. These are used to model individual phonemes, which are used in a Viterbi search/level-building process to align an independently given string of phonemes with the corresponding speech signal. The results obtained show an overall accuracy of 55.7% in the positioning of the label boundary transitions in the combined test corpus. Detailed analysis shows that certain sound class boundaries are very accurately positioned. To provide a general solution to the problem of positioning badly positioned boundaries, an interactive component of the alignment system has been developed. First results demonstrate this component to be very valuable in the task of user-assisted boundary positioning.>

Successful and flexible establishment of a spoken dialogue system requires the integration of dialogue design, dialogue management and spoken language processing into a common system environment. The research and development reported in this paper give details from the establishment of such an environment and its necessary development tools and devices as well as preliminary results from testing the integral continuous speech recogniser component on an artificial CADapplication. The application is characterised by a vocabulary containing names of geometrical objects, words by which these objects may be moved, changed in size, coloured etc, such that speech activated manipulation of the objects may be observed on a display. The interactive functionality is guided by reproductive speech output telling the user if, for instance, he/she is asking the system to perform illegal actions as seen from the pragmatic/semantic component of the dialogue system. The continuous speech recogniser pa...

In previous work on label alignment, encouraging results were obtained using selected acoustic-phonetic features to model the individuals speech phonemes. Selection was based on minimal covariance between features on the one hand, and the inclusion of features underlying critical phonological opposition on the other. In the present work, principal component analysis was applied to give a number of uncorrelated output parameters which maximally exploit the discriminatory power of the features and are derived independently of the phonological functionality. Results of label alignment on three different European languages, Danish, English, and Italian, using different numbers of principal parameters show that the accuracy with ten parameters is at least as good as with 15 manually selected features. The best result is found for British English, which has 78% of its phoneme transition boundaries positioned within +or-20 ms of manually placed reference boundaries.>