http://www.informatik.uni-ulm.de/ni/staff/FSchwenker/lit/papers/2001-Trentin-NC.pdf

A survey of hybrid ANN/HMM models for automatic speech recognition

Frame-based speech processing inherently assumes a stationary behavior of speech signals in a short period of time. Over a long time, the characteristics of the signals can change significantly and frames are not equally important, underscoring the need for frame selection. In this paper, we present a low-complexity and effective frame selection approach based on a posteriori signal-to-noise ratio (SNR) weighted energy distance: The use of an energy distance, instead of, e.g., a standard cepstral distance, makes the approach computationally efficient and enables fine granularity search, and the use of a posteriori SNR weighting emphasizes the reliable regions in noisy speech signals. It is experimentally found that the approach is able to assign a higher frame rate to fast changing events such as consonants, a lower frame rate to steady regions like vowels and no frames to silence, even for very low SNR signals. The resulting variable frame rate analysis method is applied to three speech processing tasks that are essential to natural interaction with intelligent environments. First, it is used for improving speech recognition performance in noisy environments. Second, the method is used for scalable source coding schemes in distributed speech recognition where the target bit rate is met by adjusting the frame rate. Third, it is applied to voice activity detection. Very encouraging results are obtained for all three speech processing tasks.

Low-Complexity Variable Frame Rate Analysis for Speech Recognition and Voice Activity Detection

Research highlights? In the responsive logistics information system, radio frequency identification can provide visibility of product flow and capture the real time inventory data. ? The captured data are analysed by online analytical process to identify the market segment. ? With advert of artificial neural network, the demand pattern is recognized and the corresponding replenishment strategy can be formulated. This paper discusses demand and supply chain management and examines how artificial intelligence techniques and RFID technology can enhance the responsiveness of the logistics workflow. This proposed system is expected to have a significant impact on the performance of logistics networks by virtue of its capabilities to adapt unexpected supply and demand changes in the volatile marketplace with the unique feature of responsiveness with the advanced technology, Radio Frequency Identification (RFID). Recent studies have found that RFID and artificial intelligence techniques drive the development of total solution in logistics industry. Apart from tracking the movement of the goods, RFID is able to play an important role to reflect the inventory level of various distribution areas. In today's globalized industrial environment, the physical logistics operations and the associated flow of information are the essential elements for companies to realize an efficient logistics workflow scenario. Basically, a flexible logistics workflow, which is characterized by its fast responsiveness in dealing with customer requirements through the integration of various value chain activities, is fundamental to leverage business performance of enterprises. The significance of this research is the demonstration of the synergy of using a combination of advanced technologies to form an integrated system that helps achieve lean and agile logistics workflow.

https://minerva-access.unimelb.edu.au/bitstream/handle/11343/118663/20.pdf

Design and development of logistics workflow systems for demand management with RFID

Posterior probabilities of sub-word units have been shown to be an effective front-end for ASR. However, attempts to model this type of features either do not benefit from modeling context-dependent phonemes, or use an inefficient distribution to estimate the state likelihood. This paper presents a novel acoustic model for posterior features that overcomes these limitations. The proposed model can be seen as a HMM where the score associated with each state is the KL divergence between a distribution characterizing the state and the posterior features from the test utterance. This KL-based acoustic model establishes a framework where other models for posterior features such as hybrid HMM/MLP and discrete HMM can be seen as particular cases. Experiments on the WSJ database show that the KL-based acoustic model can significantly outperform these latter approaches. Moreover, the proposed model can obtain comparable results to complex systems, such as HMM/GMM, using significantly fewer parameters.

/pdf/using-kl-based-acoustic-models-in-a-large-vocabulary-2i3zapilkr.pdf

Using KL-based Acoustic Models in a Large Vocabulary Recognition Task

Most speech processing algorithms analyze speech signals frame by frame with a fixed frame rate. Fixed-rate analysis is inconsistent with human speech perception and effectively assigns the same importance or 'weight' to all equi-duration frames. In Zhu et al. (2000), we proposed a variable frame rate (VFR) analysis technique that is based on a Euclidian distance measure. In this paper, we propose another approach for VFR based on the entropy of the signal. We compare entropy and Euclidian distance measures for VFR in ASR experiments using the Aurora2 and T146 databases. Better performance is observed for the entropy-based VFR over our earlier VFR approach and over the fixed-rate system.

/pdf/entropy-based-variable-frame-rate-analysis-of-speech-signals-5ci832p63q.pdf

Entropy-based variable frame rate analysis of speech signals and its application to ASR

Variable frame rate (VFR) analysis is a technique used in speech processing and recognition for discarding frames that are too much alike. The article introduces a new method for VFR. Instead of calculating the distance between frames, the norm of the derivative parameters is used in deciding to retain or to discard a frame, informal inspection of speech spectrograms shows that this new method puts more emphasis on the transient regions of the speech signal. Experimental results with a hidden Markov model (HMM) based system show that the new method outperforms the classical method. >

A new variable frame analysis method for speech recognition

A novel combination of multilayer perceptrons (MLPs) and hidden Markov models (HMMs) is presented. Instead of using MLPs as probability generators for HMMs, the authors propose to use MLPs as labelers for discrete parameter HMM's. Compared with the probabilistic interpretation of MLPs, this gives them the advantage of flexibility in system design (e.g., the use of word models instead of phonetic models while using the same MLPs). Moreover, since they do not need to reach a global minimum, they can do with MLPs with fewer hidden nodes, which can be trained faster. In addition, they do not need to retrain the MLPs with segmentations generated by a Viterbi alignment. Compared with Euclidean labeling, their method has the advantages of needing fewer HMM parameters per state and obtaining a higher recognition accuracy. Several improvements of the baseline MLP labeling are investigated. When using one MLP, the best results are obtained when giving the labels a fuzzy interpretation. It is also possible to use parallel MLPs where each is based on a different parameter set (e.g., basic parameters, their time derivatives, and their second-order time derivatives). This strategy increases the recognition results considerably. A final improvement is the training of MLPs for subphoneme classification. >

Multilayer perceptrons as labelers for hidden Markov models

The authors investigate the use of multilayer perceptrons (MLPs) as labelers for a discrete parameter hidden Markov model (HMM) system. They introduce a number of strategies, of which the multi-MLP approach, which uses parallel MLPs for separate parameter sets, is the most promising. The performance of the new system is just as good as that of a classical discrete parameter HMM system (using multiple Euclidean vector quantization), but needs fewer HMM parameters (80 compared with 330 per state). Therefore, multi-MLP labeling is much more efficient than Euclidean labeling. >

Using parallel MLPs as labelers for multiple codebook HMMs

Reduction techniques for frames and frame dimensions in automatic speech recognition

Describes a recurrent neural network based, isolated word speech recognizer. The recognizer uses 2 MLPs. A first, static MLP is used for classification of frames in phonemes. Next, a time compression step is applied. The resulting pseudo-segments are then used as inputs for a second, dynamic MLP that integrates the information over time to decide the current word. The authors apply this approach on an isolated digit recognition task and compare the results with hybrid MLP/HMM approach using the same static MLP. >

P Le Cerf

Papers

A new variable frame analysis method for speech recognition

Multilayer perceptrons as labelers for hidden Markov models

Using parallel MLPs as labelers for multiple codebook HMMs

Reduction techniques for frames and frame dimensions in automatic speech recognition

Pseudo-segment based speech recognition using neural recurrent whole-word recognizers