Language independent automated segmentation of speech using Bach scale filter-banks

This correspondence describes a method for automated segmentation of speech. The method proposed in this paper uses a specially designed filter-bank called Bach filter-bank which makes use of 'music' related perception criteria. The speech signal is treated as continuously time varying signal as against a short time stationary model. A comparative study has been made of the performances using Mel, Bark and Bach scale filter banks. The preliminary results show up to 80 % matches within 20 ms of the manually segmented data, without any information of the content of the text and without any language dependence. The Bach filters are seen to marginally outperform the other filters.

Multi-Pattern Viterbi Algorithm for joint decoding of multiple speech patterns

Joint decoding of multiple speech patterns so as to improve speech recognition performance is important, especially in the presence of noise. In this paper, we propose a Multi-Pattern Viterbi algorithm (MPVA) to jointly decode and recognize multiple speech patterns for automatic speech recognition (ASR). The MPVA is a generalization of the Viterbi Algorithm to jointly decode multiple patterns given a Hidden Markov Model (HMM). Unlike the previously proposed two stage Constrained Multi-Pattern Viterbi Algorithm (CMPVA),the MPVA is a single stage algorithm. MPVA has the advantage that it cart be extended to connected word recognition (CWR) and continuous speech recognition (CSR) problems. MPVA is shown to provide better speech recognition performance than the earlier techniques: using only two repetitions of noisy speech patterns (-5 dB SNR, 10% burst noise), the word error rate using MPVA decreased by 28.5%, when compared to using individual decoding. (C) 2010 Elsevier B.V. All rights reserved.

Continuity Metric for Unit Selection based Text-to-Speech Synthesis

A new method based on unit continuity metric (UCM) is proposed for optimal unit selection in text-to-speech (TTS) synthesis. UCM employs two features, namely, pitch continuity metric and spectral continuity metric. The methods have been implemented and tested on our test bed called MILE-TTS and it is available as web demo. After verification by a self selection test, the algorithms are evaluated on 8 paragraphs each for Kannada and Tamil by native users of the languages. Mean-opinion-score (MOS) shows that naturalness and comprehension are better with UCM based algorithm than the non-UCM based ones. The naturalness of the TTS output is further enhanced by a new rule based algorithm for pause prediction for Tamil language. The pauses between the words are predicted based on parts-of-speech information obtained from the input text.

Tool for Identification of Duplicate Records Downloaded from Multiple Cd-Roms. A Case Study with Spirs Based Databases

As research becomes more and more interdisciplinary, literature search from CD-ROM databases is often carried out on more than one CD-ROM database. This results in retrieving duplicate records due to same literature being covered (indexed) in more than one database. The retrieval software does not identify such duplicate records. Three different programs have been written to accomplish the task of identifying the duplicate records. These programs are executed from a shell script to minimize manual intervention. The various fields that have been used (extracted) to identify the duplicate records include the article title, year, volume number, issue number and pagination. The shell script when executed prompts for input file that may contain duplicate records. The programs identify the duplicate records and write them to a new file.

Integrating CDS/ISIS Databases with Greenstone Digital Library Software (GSDL)

CDS/ISIS is an advanced non-numerical information storage and retrieval software developed by UNESCO since 1985 to satisfy the need expressed by many institutions, especially in developing countries, to be able to streamline their information processing activities by using modern (and relatively inexpensive) technologies [1]. CDS/ISIS is available for MS-DOS, Windows and Unix operating system platforms. The formatting language of CDS/ISIS is one of its several strengths. It is not only used for formatting records for display but is also used for creating customized indexes. CDS/ISIS by itself does not facilitate in publishing its databases on the Internet nor does it facilitate in publishing on CD-ROMs. However, numbers of open source tools are now available, which enables in publishing CDS/ISIS databases on the Internet and also on CD-ROMs. In this paper, we have discussed the ways and means of integrating CDS/ISIS databases with GSDL, an open source digital library (DL) software.

Implementing WWWISIS for Providing Web Access to Bibliographic Databases

CDS/ISIS, an advanced non-numerical information storage and retrieval software was developed by UNESCO. With the emergence of WWW technology, most of the information activities are becoming Web-centric. Libraries and information providers are taking advantage of these Internet developments to provide access to their resources/information on the Web. A number of tools are now available for publishing CDS/ISIS databases on the Internet. One such tool is the WWWISIS Web gateway software, developed by BIREME, Brazil. This paper illustrates porting of sample records from a bibliographic database into CDS/ISIS, and then publishing this database on the Internet using WWWISIS.

A Tutorial on Integrating CDS/ISIS Databases with the World Wide Web

With the emergence of Internet, the global connectivity of computers has become a reality. Internet has progressed to provide many user-friendly tools like Gopher, WAIS, WWW etc. for information publishing and access. The WWW, which integrates all other access tools, also provides a very convenient means for publishing and accessing multimedia and hypertext linked documents stored in computers spread across the world. With the emergence of WWW technology, most of the information activities are becoming Web-centric. Once the information is published on the Web, a user can access this information from any part of the world. A Web browser like Netscape or Internet Explorer is used as a common user interface for accessing information/databases. This will greatly relieve a user from learning the search syntax of individual information systems. Libraries are taking advantage of these developments to provide access to their resources on the Web. CDS/ISIS is a very popular bibliographic information management software used in India. In this tutorial we present details of integrating CDS/ISIS with the WWW. A number of tools are now available for making CDS/ISIS database accessible on the Internet/Web. Some of these are 1) the WAIS_ISIS Server. 2) the WWWISIS Server 3) the IQUERY Server. In this tutorial, we have explained in detail the steps involved in providing Web access to an existing CDS/ISIS database using the freely available software, WWWISIS. This software is developed, maintained and distributed by BIREME, the Latin American & Caribbean Centre on Health Sciences Information. WWWISIS acts as a server for CDS/ISIS databases in a WWW client/server environment. It supports functions for searching, formatting and data entry operations over CDS/ISIS databases. WWWISIS is available for various operating systems. We have tested this software on Windows '95, Windows NT and Red Hat Linux release 5.2 (Appolo) Kernel 2. 0. 36 on an i686. The testing was carried out using IISc's main library's OPAC containing more than 80,000 records and Current Contents issues (bibliographic data) containing more than 25,000 records. WWWISIS is fully compatible with CDS/ISIS 3.07 file structure. However, on a system running Unix or its variant, there is no guarantee of this compatibility. It is therefore safe to recreate the master and the inverted files, using utilities provided by BIREME, under Unix environment.

Dynamic subspace clustering for very large high-dimensional databases

Emerging high-dimensional data mining applications needs to find interesting clusters embeded in arbitrarily aligned subspaces of lower dimensionality. It is difficult to cluster high-dimensional data objects, when they are sparse and skewed. Updations are quite common in dynamic databases and they are usually processed in batch mode. In very large dynamic databases, it is necessary to perform incremental cluster analysis only to the updations. We present a incremental clustering algorithm for subspace clustering in very high dimensions, which handles both insertion and deletions of datapoints to the backend databases.

Research bed for unit selection based text to speech synthesis

The paper describes a modular, unit selection based TTS framework, which can be used as a research bed for developing TTS in any new language, as well as studying the effect of changing any parameter during synthesis. Using this framework, TTS has been developed for Tamil. Synthesis database consists of 1027 phonetically rich prerecorded sentences. This framework has already been tested for Kannada. Our TTS synthesizes intelligible and acceptably natural speech, as supported by high mean opinion scores. The framework is further optimized to suit embedded applications like mobiles and PDAs. We compressed the synthesis speech database with standard speech compression algorithms used in commercial GSM phones and evaluated the quality of the resultant synthesized sentences. Even with a highly compressed database, the synthesized output is perceptually close to that with uncompressed database. Through experiments, we explored the ambiguities in human perception when listening to Tamil phones and syllables uttered in isolation,thus proposing to exploit the misperception to substitute for missing phone contexts in the database. Listening experiments have been conducted on sentences synthesized by deliberately replacing phones with their confused ones.

Subspace Based Speech Enhancement Using Gaussian Mixture Model

Traditional subspace based speech enhancement (SSE)methods use linear minimum mean square error (LMMSE) estimation that is optimal if the Karhunen Loeve transform (KLT) coefficients of speech and noise are Gaussian distributed. In this paper, we investigate the use of Gaussian mixture (GM) density for modeling the non-Gaussian statistics of the clean speech KLT coefficients. Using Gaussian mixture model (GMM), the optimum minimum mean square error (MMSE) estimator is found to be nonlinear and the traditional LMMSE estimator is shown to be a special case. Experimental results show that the proposed method provides better enhancement performance than the traditional subspace based methods.Index Terms: Subspace based speech enhancement, Gaussian mixture density, MMSE estimation.

Two stage iterative wiener filtering for speech enhancement

We formulate a two-stage Iterative Wiener filtering (IWF) approach to speech enhancement, bettering the performance of constrained IWF, reported in literature. The codebook constrained IWF (CCIWF) has been shown to be effective in achieving convergence of IWF in the presence of both stationary and non-stationary noise. To this, we include a second stage of unconstrained IWF and show that the speech enhancement performance can be improved in terms of average segmental SNR (SSNR), Itakura-Saito (IS) distance and Linear Prediction Coefficients (LPC) parameter coincidence. We also explore the tradeoff between the number of CCIWF iterations and the second stage IWF iterations.

Comparison of AM-FM Based Features For Robust Speech Recognition

Effective feature extraction for robust speech recognition is a widely addressed topic and currently there is much effort to invoke non-stationary signal models instead of quasi-stationary signal models leading to standard features such as LPC or MFCC. Joint amplitude modulation and frequency modulation (AM-FM) is a classical non-parametric approach to non-stationary signal modeling and recently new feature sets for automatic speech recognition (ASR) have been derived based on a multi-band AM-FM representation of the signal. We consider several of these representations and compare their performances for robust speech recognition in noise, using the AURORA-2 database. We show that FEPSTRUM representation proposed is more effective than others. We also propose an improvement to FEPSTRUM based on the Teager energy operator (TEO) and show that it can selectively outperform even FEPSTRUM

Online Unsupervised Pattern Discovery in Speech Using Parallelization

Segmental dynamic time warping (DTW) has been demonstrated to be a useful technique for finding acoustic similarity scores between segments of two speech utterances. Due to its high computational requirements, it had to be computed in an offline manner, limiting the applications of the technique. In this paper, we present results of parallelization of this task by distributing the workload in either a static or dynamic way on an 8-processor cluster and discuss the trade-offs among different distribution schemes. We show that online unsupervised pattern discovery using segmental DTW is plausible with as low as 8 processors. This brings the task within reach of today's general purpose multi-core servers. We also show results on a 32-processor system, and discuss factors affecting scalability of our methods.

Speech Enhancement using Intra-frame Dependency in DCT Domain

In this paper, we present a new speech enhancement approach, that is based on exploiting the intra-frame dependency of discrete cosine transform (DCT) domain coefficients. It can be noted that the existing enhancement techniques treat the transformdomain coefficients independently. Instead of this traditional approach of independently processing the scalars, we split the DCT domain noisy speech vector into sub-vectors and each sub-vector is enhanced independently. Through this sub-vector based approach, the higher dimensional enhancement advantage, viz. non-linear dependency, is exploited. In the developed method, each clean speech sub-vector is modeled using a Gaussian mixture (GM) density. We show that the proposed Gaussian mixture model (GMM) based DCT domain method, using sub-vector processing approach, provides better performance than the conventional approach of enhancing the transform domain scalar components independently. Performance improvement over the recently proposed GMM based time domain approach is also shown.