Language model combination and adaptation using weighted finite state transducers

In speech recognition systems language model (LMs) are often constructed by training and combining multiple n-gram models. They can be either used to represent different genres or tasks found in diverse text sources, or capture stochastic properties of different linguistic symbol sequences, for example, syllables and words. Unsupervised LM adaptation may also be used to further improve robustness to varying styles or tasks. When using these techniques, extensive software changes are often required. In this paper an alternative and more general approach based on weighted finite state transducers (WFSTs) is investigated for LM combination and adaptation. As it is entirely based on well-defined WFST operations, minimum change to decoding tools is needed. A wide range of LM combination configurations can be flexibly supported. An efficient on-the-fly WFST decoding algorithm is also proposed. Significant error rate gains of 7.3% relative were obtained on a state-of-the-art broadcast audio recognition task using a history dependently adapted multi-level LM modelling both syllable and word sequences. ©2010 IEEE.

Fixed-lag blind equalization and sequence estimation in digital communications systems using sequential importance sampling

We present methods for fixed-lag smoothing using Sequential Importance sampling (SIS) on a discrete non-linear, non-Gaussian state space system with unknown parameters. Our particular application is in the field of digital communication systems. Each input data point is taken from a finite set of symbols. We represent transmission media as a fixed filter with a finite impulse response (FIR), hence a discrete state-space system is formed. Conventional Markov chain Monte Carlo (MCMC) techniques such as the Gibbs sampler are unsuitable for this task because they can only perform processing on a batch of data. Data arrives sequentially, so it would seem sensible to process it in this way. In addition, many communication systems are interactive, so there is a maximum level of latency that can be tolerated before a symbol is decoded. We will demonstrate this method by simulation and compare its performance to existing techniques.

Robust noise reduction for speech and audio signals

Statistical model-based methods are presented for the reconstruction of autocorrelated signals in impulsive plus continuous noise environments. Signals are modelled as autoregressive and noise sources as discrete and continuous mixtures of Gaussians, allowing for robustness in highly impulsive and non-Gaussian environments. Markov Chain Monte Carlo methods are used for reconstruction of the corrupted waveforms within a Bayesian probabilistic framework and results are presented for contaminated voice and audio signals.

Semi-analytic slope delay model for CMOS switch-level timing verification

A novel slope delay model for CMOS switch-level timing verification is presented. It differs from conventional methods in being semianalytic in character. The model assumes that all input waveforms are trapezoidal in overall shape, but that they vary in their slope. This simplification is quite reasonable and does not seriously affect precision, but it facilitates rapid solution. The model divides the stages in a switch-level circuit into two types. One corresponds to the logic gates, and the other corresponds to logic gates with pass transistors connected to their outputs. Semianalytic modeling for both cases is discussed.

Switch-level timing verification for CMOS circuits. A semianalytic approach

The paper describes a semianalytic slope delay model for CMOS switch-level timing verification. It is characterised by classification of the effects of the input slope, internal size and load capacitance of a logic gate on delay time, and then the use of a series of carefully chosen analytic functions to estimate delay times under different circumstances. In the field of VLSI analysis, this model achieves improvements in speed and accuracy compared with conventional approaches to transistor-level and switch-level simulation.

Improving speech transcription for Mandarin-english translation

This paper describes the development of the CU-HTK Mandarin Speech-To-Text (STT) system and assesses its performance as part of a transcription-translation pipeline which converts broadcast Mandarin audio into English text. Recent improvements to the STT system are described and these give Character Error Rate (CER) gains of 14.3% absolute for a Broadcast Conversation (BC) task and 5.1% absolute for a Broadcast News (BN) task. The output of these STT systems is then post-processed, so that it consists of sentence-like segments, and translated into English text using a Statistical Machine Translation (SMT) system. The performance of the transcription-translation pipeline is evaluated using the Translation Edit Rate (TER) and BLEU metrics. It is shown that improving both the STT system and the post-STT segmentations can lower the TER scores by up to 5.3% absolute and increase the BLEU scores by up to 2.7% absolute. © 2007 IEEE.

Automatic transcription of conversational telephone speech

This paper discusses the Cambridge University HTK (CU-HTK) system for the automatic transcription of conversational telephone speech. A detailed discussion of the most important techniques in front-end processing, acoustic modeling and model training, language and pronunciation modeling are presented. These include the use of conversation side based cepstral normalization, vocal tract length normalization, heteroscedastic linear discriminant analysis for feature projection, minimum phone error training and speaker adaptive training, lattice-based model adaptation, confusion network based decoding and confidence score estimation, pronunciation selection, language model interpolation, and class based language models. The transcription system developed for participation in the 2002 NIST Rich Transcription evaluations of English conversational telephone speech data is presented in detail. In this evaluation the CU-HTK system gave an overall word error rate of 23.9%, which was the best performance by a statistically significant margin. Further details on the derivation of faster systems with moderate performance degradation are discussed in the context of the 2002 CU-HTK 10 × RT conversational speech transcription system. © 2005 IEEE.

Patterning and detailed study of human hNT astrocytes on parylene-C/silicon dioxide substrates to the single cell level.

It is estimated that the adult human brain contains 100 billion neurons with 5-10 times as many astrocytes. Although it has been generally considered that the astrocyte is a simple supportive cell to the neuron, recent research has revealed new functionality of the astrocyte in the form of information transfer to neurons of the brain. In our previous work we developed a protocol to pattern the hNT neuron (derived from the human teratocarcinoma cell line (hNT)) on parylene-C/SiO(2) substrates. In this work, we report how we have managed to pattern hNT astrocytes, on parylene-C/SiO(2) substrates to single cell resolution. This article disseminates the nanofabrication and cell culturing steps necessary for the patterning of such cells. In addition, it reports the necessary strip lengths and strip width dimensions of parylene-C that encourage high degrees of cellular coverage and single cell isolation for this cell type. The significance in patterning the hNT astrocyte on silicon chip is that it will help enable single cell and network studies into the undiscovered functionality of this interesting cell, thus, contributing to closer pathological studies of the human brain.

Language model cross adaptation for LVCSR system combination

State-of-the-art large vocabulary continuous speech recognition (LVCSR) systems often combine outputs from multiple subsystems developed at different sites. Cross system adaptation can be used as an alternative to direct hypothesis level combination schemes such as ROVER. In normal cross adaptation it is assumed that useful diversity among systems exists only at acoustic level. However, complimentary features among complex LVCSR systems also manifest themselves in other layers of modelling hierarchy, e.g., subword and word level. It is thus interesting to also cross adapt language models (LM) to capture them. In this paper cross adaptation of multi-level LMs modelling both syllable and word sequences was investigated to improve LVCSR system combination. Significant error rate gains up to 6.7% rel. were obtained over ROVER and acoustic model only cross adaptation when combining 13 Chinese LVCSR subsystems used in the 2010 DARPA GALE evaluation. © 2010 ISCA.