Distributed Speech Recognition Research Articles

Improved model adaptation approach for recognition of reduced-frame-rate continuous speech.

In distributed speech recognition applications, the front-end device that stands for any handheld electronic device like smartphones and personal digital assistants (PDAs) captures the speech signal, extracts the speech features, and then sends the speech-feature vector sequence to the back-end server for decoding. Since the front-end mobile device has limited computation capacity, battery power and bandwidth, there exists a feasible strategy of reducing the frame rate of the speech-feature vector sequence to alleviate the drawback. Previously, we proposed a method for adjusting the transition probabilities of the hidden Markov model to enable it to address the degradation of recognition accuracy caused by the frame-rate mismatch between the input and the original model. The previous model adaptation method is referred to as the adapting-then-connecting approach that adapts each model individually and then connects the adapted models to form a word network for speech recognition. We have found that this model adaption approach introduces transitions that skip too many states and increase the number of insertion errors. In this study, we propose an improved model adaptation approach denoted as the connecting-then-adapting approach that first connects the individual models to form a word network and then adapts the connected network for speech recognition. This new approach calculates the transition matrix of a connected model, adapts the transition matrix of the connected model according to the frame rate, and then creates a transition arc for each transition probability. The new approach can better align the speech feature sequence with the states in the word network and therefore reduce the number of insertion errors. We conducted experiments to investigate the effectiveness of our new approach and analyzed the results with respect to insertion, deletion, and substitution errors. The experimental results indicate that the proposed new method obtains a better recognition rate than the old method.

Suppression by Selecting Wavelets for Feature Compression in Distributed Speech Recognition

Distributed speech recognition DSR splits the processing of data between a mobile device and a network server. In the front-end, features are extracted and compressed to transmit over a wireless channel to a back-end server, where the incoming stream is received and reconstructed for recognition tasks. In this paper, we propose a feature compression algorithm termed suppression by selecting wavelets SSW to achieve the two main goals of DSR: Minimizing memory and device requirements while also maintaining or even improving the recognition performance. The SSW approach first applies the discrete wavelet transform DWT to filter the incoming speech feature sequence into two temporal subsequences at the client terminal. Feature compression is achieved by keeping the low modulation frequency subsequence while discarding the high frequency counterpart. The low-frequency subsequence is then transmitted across the remote network for specific feature statistics normalization. Wavelets are favorable for resolving the temporal properties of the feature sequence, and the down-sampling process in DWT achieves data compression by reducing the amount of data at the terminal prior to transmission across the network. Once the compressed features have arrived at the server, the feature sequence can be enhanced by statistics normalization, reconstructed with inverse DWT, and compensated with a simple post filter to alleviate any over-smoothing effects from the compression stage. Results on a standard robustness task Aurora-4 and on a Mandarin Chinese news corpus showed SSW outperforms conventional noise-robustness techniques while also providing nearly a 50% compression rate during the transmission stage of DSR systems.

Particle Swarm Optimization to Improve Robustness of Distributed Speech Recognition

Particle Swarm Optimization to Improve Robustness of Distributed Speech Recognition

Using geometric spectral subtraction approach for feature extraction for DSR front-end Arabic system

Noise robustness and Arabic language are still considered as the main challenges for speech recognition over mobile environments. This paper contributed to these trends by proposing a new robust Distributed Speech Recognition (DSR) system for Arabic language. A speech enhancement algorithm was applied to the noisy speech as a robust front-end pre-processing stage to improve the recognition performance. While an isolated Arabic word engine was designed, and developed using HMM Model to perform the recognition process at the back-end. To test the engine, several conditions including clean, noisy and enhanced noisy speech were investigated together with speaker dependent and speaker independent tasks. With the experiments carried out on noisy database, multi-condition training outperforms the clean training mode in all noise types in terms of recognition rate. The results also indicate that using the enhancement method increases the DSR accuracy of our system under severe noisy conditions especially at low SNR down to 10 dB.

The Lineal Prediction Applied to Distributed Speech Recognition in IP Nets

This work presents results in the application of speech compression to speech recognition technics in IP nets. That’s why the three fundamental areas of the knowledge that are involved are: the voice compression, the transmission channels simulation and the speech recognition. This areas are integrated to achieve an application developed in MATLAB, able to carry out a remote speech recognition by means of the transmission of compressed voice, with the peculiarity that it is considered the probability of occurrence of losses of information in the transmission channels, in such way that the robustness of the proposed system is demonstrated.

An experimental framework for Arabic digits speech recognition in noisy environments

In this paper we present an experimental framework for Arabic isolated digits speech recognition named ARADIGITS-2. This framework provides a performance evaluation of Modern Standard Arabic devoted to a Distributed Speech Recognition system, under noisy environments at various Signal-to-Noise Ratio (SNR) levels. The data preparation and the evaluation scripts are designed by deploying a similar methodology to that followed in AURORA-2 database. The original speech data contains a total of 2704 clean utterances, spoken by 112 (56 male and 56 female) Algerian native speakers, down-sampled at 8 kHz. The feature vectors, which consist of a set of Mel Frequency Cepstral Coefficients and log energy, are extracted from speech samples using ETSI Advanced Front-End (ETSI-AFE) standard; whereas, the Hidden Markov Models (HMMs) Toolkit is used for building the speech recognition engine. The recognition task is conducted in speaker-independent mode by considering both word and syllable as acoustic units. Therefore, an optimal fitting of HMM parameters, as well as the temporal derivatives window, is carried out through a series of experiments performed on the two training modes: clean and multi-condition. Better results are obtained by exploiting the polysyllabic nature of Arabic digits. These results show the effectiveness of syllable-like unit in building Arabic digits recognition system, which exceeds word-like unit by an overall Word Accuracy Rate of 0.44 and 0.58% for clean and multi-condition training modes, respectively.

An efficient low bit-rate compression scheme of acoustic features for distributed speech recognition

Due to the limited network bandwidth, a noise robust low bit-rate compression scheme of Mel frequency cepstral coefficients (MFCCs) is desired for distributed speech recognition (DSR) services. In this paper, we present an efficient MFCCs compression method based on weighted least squares (W-LS) polynomial approximation through the exploitation of the high correlation across consecutive MFCC frames. Polynomial coefficients are quantized by designing a tree structured vector quantization (TSVQ) based scheme. Recognition experiments are conducted on the noisy Aurora-2 database, under both clean and multi-condition training modes. The results show that the proposed W-LS encoder slightly exceeds the ETSI advanced front-end (ETSI-AFE) baseline system for bit-rates ranging from 1400 bps to 1925 bps under clean training mode. However, a negligible degradation is observed in case of multi-condition training mode (around 0.6% and 0.2% at 1400 bps and 1925 bps, respectively). Furthermore, the obtained performance generally outperforms the ETSI-AFE source encoder at 4400 bps under clean training and provides similar performance, at 1925 bps, under multi-condition training.

Optimisation of multiple feature stream weights for distributed speech processing in mobile environments

Mobile environments are highly influenced by ambient noise that can cause a significant deterioration in speech recognition performance. In this study, a new framework integrating a noise-robust frontend (FE) in distributed speech recognition (DSR) is presented. Using the Aurora-2 speech database, the authors evaluate the impact of the proposed multidimensional acoustical analysis on the performance of the Mel-frequency-based European Telecommunications Standards Institute-advanced FE (AFE) combined with the Mel-line spectral frequencies (MLSFs) robust features for highly noisy speech. The stream weights of the resulting multi-stream hidden Markov models are optimised automatically by deploying a novel approach based on a discriminative model combination. Finally, these features are effectively transformed and reduced using the Karhunen–Loeve transform. The proposed MLSF-based FE (MLSF-FE) is shown to exhibit a reduction in the relative error rate. Moreover, the proposed FE provides comparable recognition performance to the current DSR-AFE available in global system of mobile communications.

Speech Emotion Classification using Machine Learning

recent years, the interaction between humans and machines has become an issue of concern. This paper results from study of various researches related to the investigation of the six basic human emotions which include anger, dislike, fear, happiness, sadness and surprise. (1, 3) Feature extraction is done from various voice utterances recorded from different persons. The various features like pitch, energy, fundamental frequency are extracted from the utterances using respective feature extraction algorithms. After feature extraction procedure, the extracted features are classified under the basic six emotions using various machine learning algorithms. (1, 3, 4)And using the different algorithms the classification accuracy is measured for each algorithm respectively. Various acoustic and prosodic features are extracted from the speech recorded and then classified under different emotional category using machine learning tools. (7) This paper discusses how feature extraction through speech samples and then classification of the extracted features under different emotions is performed. KeywordsEmotion Recognition Models: Distributed speech recognition model; Feature Extraction; Classification Algorithms.

Improving Domain-independent Cloud-Based Speech Recognition with Domain-Dependent Phonetic Post-Processing

Automatic speech recognition (ASR) technology has been developed to such a level that off-the-shelf distributed speech recognition services are available (free of cost), which allow researchers to integrate speech into their applications with little development effort or expert knowledge leading to better results compared with previously used open-source tools. Often, however, such services do not accept language models or grammars but process free speech from any domain. While results are very good given the enormous size of the search space, results frequently contain out-of-domain words or constructs that cannot be understood by subsequent domain-dependent natural language understanding (NLU) components. We present a versatile post-processing technique based on phonetic distance that integrates domain knowledge with open-domain ASR results, leading to improved ASR performance. Notably, our technique is able to make use of domain restrictions using various degrees of domain knowledge, ranging from pure vocabulary restrictions via grammars or N-Grams to restrictions of the acceptable utterances. We present results for a variety of corpora (mainly from human-robot interaction) where our combined approach significantly outperforms Google ASR as well as a plain open-source ASR solution.

Model adaptation method for recognition of speech with missing frames

In distributed speech recognition (DSR), data packets may be lost over error prone channels. A commonly used approach to rectify this is to reconstruct a full frame rate data sequence for recognition using linear interpolation. In this study, an error-concealment decoding method that dynamically adapts the transition probabilities of hidden Markov models to match the frame loss observation sequence is proposed. Experimental results show that a DSR system using the proposed method can achieve the same level of accuracy as a data reconstruction method, is more robust against heavy frame loss, and significantly reduces the computation time.

Adaptation of Hidden Markov Models for Recognizing Speech of Reduced Frame Rate

The frame rate of the observation sequence in distributed speech recognition applications may be reduced to suit a resource-limited front-end device. In order to use models trained using full-frame-rate data in the recognition of reduced frame-rate (RFR) data, we propose a method for adapting the transition probabilities of hidden Markov models (HMMs) to match the frame rate of the observation. Experiments on the recognition of clean and noisy connected digits are conducted to evaluate the proposed method. Experimental results show that the proposed method can effectively compensate for the frame-rate mismatch between the training and the test data. Using our adapted model to recognize the RFR speech data, one can significantly reduce the computation time and achieve the same level of accuracy as that of a method, which restores the frame rate using data interpolation.

Low bit rate compression methods of feature vectors for distributed speech recognition

In this paper, we present a family of compression methods based on differential vector quantization (DVQ) for encoding Mel frequency cepstral coefficients (MFCC) in distributed speech recognition (DSR) applications. The proposed techniques benefit from the existence of temporal correlation across consecutive MFCC frames as well as the presence of intra-frame redundancy. We present DVQ schemes based on linear prediction and non-linear methods with multi-layer perceptrons (MLP). In addition to this, we propose the use of a multipath search coding strategy based on the M-algorithm that obtains the sequence of centroids that minimize the quantization error globally instead of selecting the centroids that minimize the quantization error locally in a frame by frame basis. We have evaluated the performance of the proposed methods for two different tasks. On the one hand, two small-size vocabulary databases, Spechdat-Car and Aurora 2, have been considered obtaining negligible degradation in terms of Word Accuracy (around 1%) compared to the unquantized scheme for bit-rates as low as 0.5kbps. On the other hand, for a large vocabulary task (Aurora 4), the proposed method achieves a WER comparable to the unquantized scheme only with 1.6kbps. Moreover, we propose a combined scheme (differential/non-differential) that allows the system to present the same sensitivity to transmission errors than previous multi-frame coding proposals for DSR.

Low Bit-Rate Encoding Algorithm for Distributed Speech Recognition Based on SVD Decomposition

The paper presents an algorithm for compression of front-end feature extracted parameters used in Distributed Speech Recognition (DSR). In the proposed method the source encoder is mainly based on truncated Singular Value Decomposition transform (SVD) with conventional vector and scalar quantizers. The system provides a compression bit-rate around 3500 bps. The experiments were carried out on the TIDigitsAurora-2 database using Hidden Makcov Model Toolkit (HTK). The simulation results show good recognition performance without dramatic change, comparing toconventional ETSI Aurorastandard front-end feature compression algorithm with quantized features at 4400 bps.

Reducing bandwidth for robust distributed speech recognition in conditions of packet loss

This paper proposes a method to reduce the bandwidth requirements for a distributed speech recognition (DSR) system, with minimal impact on recognition performance. Bandwidth reduction is achieved by applying a wavelet decomposition to feature vectors extracted from speech using an auditory-based front-end. The resulting vectors undergo vector quantisation and are then combined in pairs for transmission over a statistically modeled channel that is subject to packet burst loss. Recognition performance is evaluated in the presence of both background noise and packet loss. When there is no packet loss, results show that the proposed method can reduce the bandwidth required to 50% of the bandwidth required for the system in which the proposed method is not used, without compromising recognition performance. The bandwidth can be further reduced to 25% of the baseline for a slight decrease in recognition performance. Furthermore, in the presence of packet loss, the proposed method for bandwidth reduction, when combined with a suitable redundancy scheme, gives a 29% reduction in bandwidth, when compared to the recognition performance of an established packet loss mitigation technique.

Feature selection for reduced-bandwidth distributed speech recognition

The impact on speech recognition performance in a distributed speech recognition (DSR) environment of two methods used to reduce the dimension of the feature vectors is examined in this paper. The motivation behind reducing the dimension of the feature set is to reduce the bandwidth required to send the feature vectors over a channel from the client front-end to the server back-end in a DSR system. In the first approach, the features are empirically chosen to maximise recognition performance. A data-centric transform-based dimensionality-reduction technique is applied in the second case. Test results for the empirical approach show that individual coefficients have different impacts on the speech recognition performance, and that certain coefficients should always be present in an empirically selected reduced feature set for given training and test conditions. Initial results show that for the empirical method, the number of elements in a feature vector produced by an established DSR front-end can be reduced by 23% with low impact on the recognition performance (less than 8% relative performance drop compared to the full bandwidth case). Using the transform-based approach, for a similar impact on recognition performance, the number of feature vector elements can be reduced by 30%. Furthermore, for best recognition performance, the results indicate that the SNR of the speech signal should be considered using either approach when selecting the feature vector elements that are to be included in a reduced feature set.

Bayesian on-line spectral change point detection: a soft computing approach for on-line ASR

Current automatic speech recognition (ASR) works in off-line mode and needs prior knowledge of the stationary or quasi-stationary test conditions for expected word recognition accuracy. These requirements limit the application of ASR for real-world applications where test conditions are highly non-stationary and are not known a priori. This paper presents an innovative frame dynamic rapid adaptation and noise compensation technique for tracking highly non-stationary noises and its application for on-line ASR. The proposed algorithm is based on a soft computing model using Bayesian on-line inference for spectral change point detection (BOSCPD) in unknown non-stationary noises. BOSCPD is tested with the MCRA noise tracking technique for on-line rapid environmental change learning in different non-stationary noise scenarios. The test results show that the proposed BOSCPD technique reduces the delay in spectral change point detection significantly compared to the baseline MCRA and its derivatives. The proposed BOSCPD soft computing model is tested for joint additive and channel distortions compensation (JAC)-based on-line ASR in unknown test conditions using non-stationary noisy speech samples from the Aurora 2 speech database. The simulation results for the on-line AR show significant improvement in recognition accuracy compared to the baseline Aurora 2 distributed speech recognition (DSR) in batch-mode.

Robust Acoustic Speech Feature Prediction From Noisy Mel-Frequency Cepstral Coefficients

This paper examines the effect of applying noise compensation to acoustic speech feature prediction from noisy mel-frequency cepstral coefficient (MFCC) vectors within a distributed speech recognition architecture. An acoustic speech feature (comprising fundamental frequency, formant frequencies, speech/nonspeech classification, and voicing classification) is predicted from an MFCC vector in a maximum a posteriori (MAP) framework using phoneme-specific or global models of speech. The effect of noise is considered and three different noise compensation methods, that have been successful in robust speech recognition, are integrated within the MAP framework. Experiments show that noise compensation can be applied successfully to prediction with best performance given by a model adaptation method that performs only slightly worse than matched training and testing. Further experiments consider application of the predicted acoustic features to speech reconstruction. A series of human listening tests show that the predicted features are sufficient for speech reconstruction and that noise compensation improves speech quality in noisy conditions.

Low Bit-Rate Speech Coding through Quantization of Mel-Frequency Cepstral Coefficients

In this paper, we propose a low bit-rate speech codec based on vector quantization (VQ) of the mel-frequency cepstral coefficients (MFCCs). We begin by showing that if a high-resolution mel-frequency cepstrum (MFC) is computed, good-quality speech reconstruction is possible from the MFCCs despite the lack of phase information. By evaluating the contribution toward speech quality that individual MFCCs make and applying appropriate quantization, our results show that the MFCC-based codec exceeds the state-of-the-art MELPe codec across the entire range of 600-2400 bps, when evaluated with the perceptual evaluation of speech quality (PESQ) (ITU-T recommendation P.862). The main advantage of the proposed codec is in distributed speech recognition (DSR) since the MFCCs can be directly applied thus eliminating additional decode and feature extract stages; furthermore, the proposed codec better preserves the fidelity of MFCCs and better word accuracy rates as compared to CELP and MELPe codecs.

Statistical Model-Based Noise Reduction Approach for Car Interior Applications to Speech Recognition

This paper presents a statistical model-based noise suppression approach for voice recognition in a car environment. In order to alleviate the spectral whitening and signal distortion problem in the traditional decisiondirected Wiener filter, we combine a decision-directed method with an original spectrum reconstruction method and develop a new two-stage noise reduction filter estimation scheme. When a tradeoff between the performance and computational efficiency under resource-constrained automotive devices is considered, ETSI standard advance distributed speech recognition font-end (ETSI-AFE) can be an effective solution, and ETSI-AFE is also based on the decision-directed Wiener filter. Thus, a series of voice recognition and computational complexity tests are conducted by comparing the proposed approach with ETSI-AFE. The experimental results show that the proposed approach is superior to the conventional method in terms of speech recognition accuracy, while the computational cost and frame latency are significantly reduced.