Speaker-independent Recognition Research Articles

Speech recognition using quantized LSP parameters and their transformations in digital communication

In digital communication networks, speech recognition systems conventionally first reconstruct speech and then extract feature parameters. In this paper, we consider a useful approach of incorporating speech coding parameters into the speech recognizer. Most speech coders employed in digital communication networks use line spectrum pairs (LSPs) as spectral parameters. We introduce two ways to improve the recognition performance of the LSP-based speech recognizer. One is to devise weighted distance measures of LSPs and the other is to transform LSPs into a new feature set, named pseudo-cepstrum (PCEP). The speaker-independent connected-digit recognition experiments based on the discrete hidden Markov model showed that the weighted distance measures provide better recognition accuracy than unweighted ones do. Additionally, a mel-scale PCEP gives an even better performance than the weighted distance measures do. To clarify the performance improvement of the proposed methods, a significance test is introduced. As a result, the proposed methods achieved higher performances in recognition accuracy, compared with the conventional methods employing mel-frequency cepstral coefficients.

Phonetic voice activated dialing

A telephone communications system Advanced Intelligent Network (AIN) platform provides a voice activated call dialing functionality through speaker independent phoneme speech recognition having a minimum volume of storage without requiring user template training. Speaker independent phoneme recognition identifies phoneme strings of caller spoken utterances which are then compared to phoneme string representations that previously have been stored in respective caller processing records (CPRs) for those subscribers listed in the ISCP database, or stored in an equivalent peripheral database with which the ISCP can communicate. Each stored phoneme string representation is associated in the CPR with a destination telephone number that may then be extracted to route a call.

Improving Viterbi Bayesian predictive classification via sequential bayesian learning in robust speech recognition

In this paper, we extend our proposed Viterbi Bayesian predictive classification (VBPC) algorithm to a new class of prior probability density function (pdf), namely a family of natural conjugate prior pdf's of the complete-data density in continuous density hidden Markov model (CDHMM) and their mixtures. In this way, we can on-line adapt the prior pdf via a sequential Bayesian learning algorithm when some new data are available, so that the performance of VBPC can be continuously improved. Moreover, we also study a sequential Bayesian learning strategy for CDHMM based on a finite mixture approximation of its prior/posterior density which attempts to derive a more accurate prior pdf to describe the unknown mismatches. The experimental results on a speaker-independent recognition task of isolated Japanese digits confirm the viability and the usefulness of the proposed method.

Robust speech recognition based on a Bayesian prediction approach

We study a category of robust speech recognition problem in which mismatches exist between training and testing conditions, and no accurate knowledge of the mismatch mechanism is available. The only available information is the test data along with a set of pretrained Gaussian mixture continuous density hidden Markov models (CDHMMs). We investigate the problem from the viewpoint of Bayesian prediction. A simple prior distribution, namely constrained uniform distribution, is adopted to characterize the uncertainty of the mean vectors of the CDHMMs. Two methods, namely a model compensation technique based on Bayesian predictive density and a robust decision strategy called Viterbi Bayesian predictive classification are studied. The proposed methods are compared with the conventional Viterbi decoding algorithm in speaker-independent recognition experiments on isolated digits and TI connected digit strings (TIDTGITS), where the mismatches between training and testing conditions are caused by: (1) additive Gaussian white noise, (2) each of 25 types of actual additive ambient noises, and (3) gender difference. The experimental results show that the adopted prior distribution and the proposed techniques help to improve the performance robustness under the examined mismatch conditions.

Cepstrum third-order normalisation method for noisy speech recognition

A new cepstrum normalisation method is proposed which can be used to compensate for distortion caused by additive noise. Conventional methods only compensate for the deviation of the cepstral mean and/or variance. However, deviations of higher order moments also exist in noisy speech signals. The proposed method normalises the cepstrum up to its third-order moment, providing closer probability density functions between clean and noisy cepstra than is possible using conventional methods. From the speaker-independent isolated-word recognition experiments, it is shown that the proposed method gives improved performance compared with that of conventional methods, especially in heavy noise environments.

Speaker-dependent speech recognition using speaker independent models

The memory and data management requirements for text independent speaker dependent recognition are drastically reduced by using a novel approach that eliminates the need for separate acoustic recognition models for each speaker. This is achieved by using speaker independent recognition models at the acoustic level. The speaker dependent data stored for each item to be recognized consists only of information needed to determine the speaker independent recognition model sequence for that item.

Further reduced form of Karhunen-Loeve transform for text independent speaker recognition

A text independent speaker recognition system based on the Karhunen-Loeve transform, derived from the split-and-merge algorithm, is proposed. The split-and-merge algorithm is applied to speaker data compression in the time domain. A set of experiments is conducted which gives a 91% recognition rate for 100 Mandarin speakers.

Speaker-independent recognition of isolated words using rough sets

The aim of the presented research is to elaborate and to test the speaker-independent system for the man-machine voice interfacing. The trajectory tracking method was implemented to feature vector extraction from speech signal. Statistical method was employed to the quantization of attribute values. The rough set method was used to derive decision rules for the recognition of speech patterns. Results and conclusions on the effectiveness of implemented algorithmic solutions were presented.

Speech recognition method using quantised LSP parameters in CELP-type coders

A low-complexity speech recognition method applicable to digital communication networks is proposed. A feature set suitable for speech recognition is obtained from quantised LSP parameters in CELP-type coders without reconstructing the speech signals. The authors present the effects of the speech coder on speaker-independent recognition performance, and show that the recognition accuracy of the proposed method is better than that of the recogniser using reconstructed speech signals.

Pluralizing simple similarity based on a natural observation method of normal type, with an application to speaker-independent vowel recognition

Pluralizing simple similarity based on a natural observation method of normal type, with an application to speaker-independent vowel recognition

ASR and TTS telecommunications applications in Japan

This paper first describes recent trends of ASR and TTS telecommunications applications in Japan. ASR applications focus on public services such as operator automation, operator assistance, voice-activated information retrieval, and voice dialing. Major TTS applications include information service by voice and e-mail reading. The usage of ASR and TTS functions is expected to dramatically increase in the near future with the penetration of handy and mobile telephone terminals; hot topics are text broadcasting and digital communication. Secondly this paper describes NTT's experimental interactive system featuring (1) highly accurate speaker independent and large vocabulary speech recognition based on context-dependent accurate acoustic phoneme HMM models trained with speech data from more than 10,000 speakers collected over telephone network, (2) high quality text-to-speech synthesis that generates speech by concatenating triphone-context-dependent waveform segments, (3) software-based configuration that requires no special hardware except a PC equipped with a sound board and a voice modem, and (4) easy and rapid prototyping which enables the developer to build a system by writing some types of service scenarios.

Speechreading using Probabilistic Models

We describe a robust method for locating and tracking lips in gray-level image sequences. Our approach learns patterns of shape variability from a training set which constrains the model during image search to only deform in ways similar to the training examples. Image search is guided by a learned gray-level model which is used to describe the large appearance variability of lips. Such variability might be due to different individuals, illumination, mouth opening, specularity, or visibility of teeth and tongue. Visual speech features are recovered from the tracking results and represent both shape and intensity information. We describe a speechreading (lip-reading) system, where the extracted features are modeled by Gaussian distributions and their temporal dependencies by hidden Markov models. Experimental results are presented for locating lips, tracking lips, and speechreading. The database used consists of a broad variety of speakers and was recorded in a natural environment with no special lighting or lip markers used. For a speaker independent digit recognition task using visual information only, the system achieved an accuracy about equivalent to that of untrained humans.

Speech recognition employing keyword modeling and non-key word modeling

Speaker independent recognition of small vocabularies, spoken over the long distance telephone network, is achieved using two types of models, one type for defined vocabulary words (e.g., collect, calling-card, person, third-number and operator), and one type for extraneous input which ranges from non-speech sounds to groups of non-vocabulary words (e.g. `I want to make a collect call please`). For this type of key word spotting, modifications are made to a connected word speech recognition algorithm based on state-transitional (hidden Markov) models which allow it to recognize words from a pre-defined vocabulary list spoken in an unconstrained fashion. Statistical models of both the actual vocabulary words and the extraneous speech and background noises are created. A syntax-driven connected word recognition system is then used to find the best sequence of extraneous input and vocabulary word models for matching the actual input speech.

Speech Recognition Experiments with Silicon Auditory Models

We have developed a real-time system to transform an audio signal into several specialized representations of sound. The system uses analog circuit models of biological audition to compute these representations. We report on a speech recognizer that uses this system for feature extraction, and we evaluate the performance of this speech recognition system on a speaker-independent 13-word recognition task.

Hard-limited Karhunen-Loeve transform for text independent speaker recognition

A text independent speaker recognition system based on hard-limited eigenfunctions derived from the Karhunen-Loeve transform is proposed. Two databases, each with 100 Mandarin speakers, are collected for system evaluation. It is demonstrated that > 94% correct classification rates can be achieved by the use of the first 32 hard-limited features.

Speaker-Independent Recognition of Digits—Experiments with Neural Networks, Fuzzy Logic and Rough Sets

ABSTRACTThe aim of the presented research was to elaborate and to test the speaker-independent system for the man-machine voice interfacing using a small vocabulary containing digits. The trajectory tracking method was implemented to feature vector extraction from speech signal. Some intelligent decision systems were tried as the neural network algorithm supported by the fuzzy logic classification procedure and the rough set method permitting to derive decision rules for the recognition of speech patterns. Implemented methods will be described. Results of comparative studies in the domain of speaker-independent recognition of digits will be presented. Conclusions on the effectiveness of implemented decision systems will be added.

Commercial applications of speech interface technology: an industry at the threshold.

Speech interface technology, which includes automatic speech recognition, synthetic speech, and natural language processing, is beginning to have a significant impact on business and personal computer use. Today, powerful and inexpensive microprocessors and improved algorithms are driving commercial applications in computer command, consumer, data entry, speech-to-text, telephone, and voice verification. Robust speaker-independent recognition systems for command and navigation in personal computers are now available; telephone-based transaction and database inquiry systems using both speech synthesis and recognition are coming into use. Large-vocabulary speech interface systems for document creation and read-aloud proofing are expanding beyond niche markets. Today's applications represent a small preview of a rich future for speech interface technology that will eventually replace keyboards with microphones and loud-speakers to give easy accessibility to increasingly intelligent machines.

Voice-operated service

First Page

Speech recognition system for electronic switches in a cellular telephone or personal communication network

An advanced telecommunications system is provided for the recognizing of spoken commands over a cellular telephone (15), satellite telephone (14), or personal communications network (16). In the cellular application, for example, a Speech Recognition System (20) interconnects either internally with or as an external peripheral to a cellular telecommunications switch (12). The Speech Recognition System (20) includes an administrative subsystem (21), a call processing subsystem (23), a speaker-dependent recognition subsystem (25), a speaker-independent recognition subsystem (27), and a data storage subsystem (29). Pre-recorded instructional messages are stored in the memory of the call processing subsystem (23) for instructing a user on his or her progress in using the system. The speaker-independent recognition subsystem (27) allows the user to interact with the system employing non-user specific functions. User specific functions are controlled with the speaker-dependent recognition subsystem (25). User specific attributes collected by the recognition subsystems are stored in the data storage subsystem (29).

Speech recognition algorithms for voice control interfaces

Recognition accuracy has been the primary objective of most speech recognition research, and impressive results have been obtained, e.g. less than 0.3% word error rate on a speaker-independent digit recognition task. When it comes to real-world applications, robustness and real-time response might be more important issues. For the first requirement we review some of the work on robustness and discuss one specific technique, spectral normalization, in more detail. The requirement of real-time response has to be considered in the light of the limited hardware resources in voice control applications, which are due to the tight cost constraints. In this paper we discuss in detail one specific means to reduce the processing and memory demands: a clustering technique applied at various levels within the acoustic modelling.