SRILM is a collection of C++ libraries, executable programs, and helper scripts designed to allow both production of and experimentation with statistical language models for speech recognition and other applications. SRILM is freely available for noncommercial purposes. The toolkit supports creation and evaluation of a variety of language model types based on N-gram statistics, as well as several related tasks, such as statistical tagging and manipulation of N-best lists and word lattices. This paper summarizes the functionality of the toolkit and discusses its design and implementation, highlighting ease of rapid prototyping, reusability, and combinability of tools. 1.

decide which contexts are similar and can share parameters. A key feature of this approach is that it allows the construction of models which are dependent upon contextual effects occurring across word boundaries. The use of cross word context dependent models presents problems for conventional decoders. The second part of the thesis therefore presents a new decoder design which is capable of using these models efficiently. The decoder is suitable for use with very large vocabularies and long span language models. It is also capable of generating a lattice of word hypotheses with little computational overhead. These lattices can be used to constrain further decoding, allowing efficient use of complex acoustic and language models. The effectiveness of these techniques has been assessed on a variety of large vocabulary continuous speech recognition tasks and results are presented which analyse performance in terms of computational complexity and recognition accuracy. The experiments dem

Hidden Markov Models (HMMs) are statistical models of sequential data that have been used successfully in many machine learning applications, especially for speech recognition. Furthermore, in the last few years, many new and promising probabilistic models related to HMMs have been proposed. We first summarize the basics of HMMs, and then review several recent related learning algorithms and extensions of HMMs, including in particular hybrids of HMMs with artificial neural networks, Input-Output HMMs (which are conditional HMMs using neural networks to compute probabilities), weighted transducers, variable-length Markov models and Markov switching state-space models. Finally, we discuss some of the challenges of future research in this very active area. 1 Introduction Hidden Markov Models (HMMs) are statistical models of sequential data that have been used successfully in many applications in artificial intelligence, pattern recognition, speech recognition, and modeling of biological ...

Contents 1 Spoken Language Input 1 Ron Cole & Victor Zue, chapter editors 1.1 Overview : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : 1 Victor Zue & Ron Cole 1.2 Speech Recognition : : : : : : : : : : : : : : : : : : : : : : : : : : : 4 Victor Zue, Ron Cole, & Wayne Ward 1.3 Signal Representation : : : : : : : : : : : : : : : : : : : : : : : : : : 11 Melvyn J. Hunt 1.4 Robust Speech Recognition : : : : : : : : : : : : : : : : : : : : : : 17 Richard M. Stern 1.5 HMM Methods in Speech Recognition : : : : : : : : : : : : : : : 24 Renato De Mori & Fabio Brugnara 1.6 Language Representation : : : : : : : : : : : : : : : : : : : : : : : : 35 Salim Roukos 1.7 Speaker Recognition : : : : : : : : : : : : : : : : : : : : : : : : : : :<F35.37

This thesis is about modeling, analyzing, and predicting errorful behavior in large vocabulary continuous speech recognition systems. Because today's state-of-the-art recognizers are not designed to be situated naturally in an error feedback loop, they are ill-positioned for inclusion in multi-modal interfaces, multi-media databases, and other interesting applications. I make improvements to the current approach to predicting and analyzing error behaviors, which is currently based only on the measurement ofword error rate. The speech recognizer's functionality is extended to include con dence annotations, which are \meta-level " markings that indicate how certain the recognizer is that it has decoded its input correctly. This is accomplished by feeding externally de ned error conditions back to the recognizer. Error feedback enables the construction of statistical models that map measurements of the recognizer's internal states and behaviors to externally de ned error conditions.

. Initially introduced in the late 1960s and early 1970s, dynamic programming algorithms have become increasingly popular in automatic speech recognition. There are two reasons why this has occurred: First, the dynamic programming strategy can be combined with avery e#cient and practical pruning strategy so that very large search spaces can be handled. Second, the dynamic programming strategy has turned out to be extremely #exible in adapting to new requirements. Examples of such requirements are the lexical tree organization of the pronunciation lexicon and the generation of a word graph instead of the single best sentence. In this paper, we attempt to systematically review the use of dynamic programming search strategies for small#vocabulary and large#vocabulary continuous speech recognition. The following methods are described in detail: search using a linear lexicon, search using a lexical tree, language-model look-ahead and word graph generation. 1 Introduction Search strategie...

We describe SRI’s large vocabulary conversational speech recognition system as used in the March 2000 NIST Hub-5E evaluation. The system performs four recognition passes: (1) bigram recognition with phone-loop-adapted, within-word triphone acoustic models, (2) lattice generation with transcription-mode-adapted models, (3) trigram lattice recognition with adapted cross-word triphone models, and (4) N-best rescoring and reranking with various additional knowledge sources. The system incorporates two new kinds of acoustic model: triphone models conditioned on speaking rate, and an explicit joint model of within-word phone durations. We also obtained an unusually large improvement from modeling crossword pronunciation variants in “multiword ” vocabulary items. The language model (LM) was enhanced with an “anti-LM ” representing acoustically confusable word sequences. Finally, we applied a generalized ROVER algorithm to combine the N-best hypotheses from several systems based on different acoustic models. 1.

In large-vocabulary, multi-pass speech recognition systems, it is desirable to generate word lattices incorporating a large number of hypotheses while keeping the lattice sizes small. We describe two new techniques for reducing word lattice sizes without eliminating hypotheses. The first technique is an algorithm to reduce the size of non-deterministic bigram word lattices. The algorithm iteratively combines lattice nodes and transitions if local properties show that this does not change the set of allowed hypotheses. On bigram word lattices generated from Hub4 Broadcast News speech, it reduces lattice sizes by half on average. It was also found to produce smaller lattices than the standard finite state automaton determinization and minimization algorithms. The second technique is an improved algorithm for expanding lattices with trigram language models. Instead of giving all nodes a unique trigram context, this algorithm only creates unique contexts for trigrams that are explicitly represented in the model. Backed-off trigram probabilities are encoded without node duplication by factoring the probabilities into bigram probabilities and backoff weights. Experiments on Broadcast News show that this method reduces trigram lattice sizes by a factor of 6, and reduces expansion time by more than a factor of 10. Compared to conventionally expanded lattices, recognition with the compactly expanded lattices was also found to be 40 % faster, without affecting recognition accuracy. 1 1.

This paper describes a new architecture for large vocabulary continuous speech recognition (LVCSR), which will be developed within the project FLaVoR (Flexible Large Vocabulary Recognition). The proposed architecture abandons the standard all-in-one search strategy with integrated acoustic, lexical and language model information. Instead, a modular framework is proposed which allows for the integration of more complex linguistic components. The search process consists of two layers. First, a pure acoustic-phonemic search generates a dense phoneme network enriched with meta-data. Then, the output of the first layer is used by sophisticated language technology components for word decoding in the second layer. Preliminary experiments prove the feasibility of the approach.

Language modeling, especially for spontaneous speech, often suffers from a mismatch of utterance segmentations between training and test conditions. In particular, training often uses linguistically-based segments, whereas testing occurs on acoustically determined segments, resulting in degraded performance. We present an N-best rescoring algorithm that removes the effect of segmentation mismatch. Furthermore, we show that explicit language modeling of hidden linguistic segment boundaries is improved by including turn-boundary events in the model. 1. THE SEGMENTATION PROBLEM IN LANGUAGE MODELING One of the problems encountered in speech recognition on continuous, spontaneous speech is the segmentation of long waveforms. Because current recognizers prefer short waveform segments for best performance and to limit computational resources, conversation-length waveforms are typically pre-segmented using simple acoustic criteria, such as locations of long pauses and turn switches. This crea...