Language model domain adaption usually uses a large quantity of auxiliary data in different genres and domains. It has mostly been relying on scoring functions for selection and it is typically independent of intended applications such as machine translation. In this paper, we present a novel domain adaptation approach that is directly motivated by the need of translation engine. We first identify interesting phrases by examining phrase translation tables, and then use those phrases as anchors to select useful and relevant sentences from general domain data, with the goal of improving domain coverage or providing additional contextual information. The experimental results on Farsi to English translation in military force protection domain and Chinese to English translation in travel domain show statistical significant gain using the reinforced language models over the baseline.

Speech-to-speech translation has evolved into an attractive area in recent years with significant progress made by various research groups. However, the translation engines usually suffer from the lack of bilingual training data, especially for low-resource languages. In this paper we present an unsupervised training technique to alleviate this problem by taking advantage of available source language data. Different approaches are proposed and compared through extensive experiments conducted on a speech-to-speech translation task between Farsi and English. The translation performance is significantly improved in both directions with the enhanced translation model. A state-of-the-art Farsi automatic speech recognition system is also established in this work.

Estimation and alignment procedures for word and phrase alignment hidden Markov models (HMMs) are developed for the alignment of parallel text. The development of these models is motivated by an analysis of the desirable features of IBM Model 4, one of the original and most effective models for word alignment. These models are formulated to capture the desirable aspects of Model 4 in an HMM alignment formalism. Alignment behavior is analyzed and compared to human-generated reference alignments, and the ability of these models to capture different types of alignment phenomena is evaluated. In analyzing alignment performance, Chinese-English word alignments are shown to be comparable to those of IBM Model 4 even when models are trained over large parallel texts. In translation performance, phrase-based statistical machine translation systems based on these HMM alignments can equal and exceed systems based on Model 4 alignments, and this is shown in Arabic-English and Chinese-English translation. These alignment models can also be used to generate posterior statistics over collections of parallel text, and this is used to refine and extend phrase translation tables with a resulting improvement in translation quality.

Language modeling for an inflected language such as Arabic poses new challenges for speech recognition and machine translation due to its rich morphology. Rich morphology results in large increases in out-of-vocabulary (OOV) rate and poor language model parameter estimation in the absence of large quantities of data. In this study, we present a joint morphological-lexical language model (JMLLM) that takes advantage of Arabic morphology. JMLLM combines morphological segments with the underlying lexical items and additional available information sources with regards to morphological segments and lexical items in a single joint model. Joint representation and modeling of morphological and lexical items reduces the OOV rate and provides smooth probability estimates while keeping the predictive power of whole words. Speech recognition and machine translation experiments in dialectal-Arabic show improvements over word and morpheme based trigram language models. We also show that as the tightness of integration between different information sources increases, both speech recognition and machine translation performances improve.

We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a stochastic generative process over text translation pairs, and derive two different alignment procedures based on the underlying alignment model. The first procedure is a now-standard dynamic programming alignment model which we use to generate an initial coarse alignment of the parallel text. The second procedure is a divisive clustering parallel text alignment procedure which we use to refine the first-pass alignments. This latter procedure is novel in that it permits the segmentation of the parallel text into sub-sentence units which are allowed to be reordered to improve the chunk alignment. The quality of chunk pairs are measured by the performance of machine translation systems trained from them. We show practical benefits of divisive clustering as well as how system performance can be improved by exploiting portions of the parallel text that otherwise would have to be discarded. We also show that chunk alignment as a first step in word alignment can significantly reduce word alignment error rate.

This paper focuses on the use of both text and phonetic information in a speech translation system in order to make translation results more robust to speech recognition errors. Conventional statistical speech translation formulas are extended to exploit both text-form and phonetic speech recognition results. A novel data-driven word/text tying algorithm is then proposed to group words based on both pronunciation similarity and meaning equivalency. In our speech-to-text translation experiments, significant improvement was achieved by using phonetic information and the proposed word tying algorithm.

We present a Weighted Finite State Transducer Translation Template Model for statistical machine translation. This is a source-channel model of translation inspired by the Alignment Template translation model. The model attempts to overcome the deficiencies of word-to-word translation models by considering phrases rather than words as units of translation. The approach we describe allows us to implement each constituent distribution of the model as a weighted finite state transducer or acceptor. We show that bitext word alignment and translation under the model can be performed with standard finite state machine operations involving these transducers. One of the benefits of using this framework is that it avoids the need to develop specialized search procedures, even for the generation of lattices or N-Best lists of bitext word alignments and translation hypotheses. We report and analyze bitext word alignment and translation performance on the Hansards French-English task and the FBIS Chinese-English task under the Alignment Error Rate, BLEU, NIST and Word Error-Rate metrics. These experiments identify the contribution of each of the model components to different aspects of alignment and translation performance. We finally discuss translation performance with large bitext training sets on the NIST 2004 Chinese-English and Arabic-English MT tasks.

Speaker adaptive training (SAT), which reduces inter-speaker variability, and eigenspace-based maximum likelihood linear regression (eigenMLLR) adaptation, which takes advantage of prior knowledge about the test speaker's linear transforms, are combined and developed. During training, SAT generates a set of speaker independent (SI) Gaussian parameters, along with matched speaker dependent transforms for all the speakers in the training set. Then, a set of regression class dependent eigen transforms are derived by doing singular value decomposition (SVD). Normally, during recognition, the test speaker's linear transforms are obtained with MLLR. In this work, the test speaker's linear transforms are assumed to be a linear combination of the decomposed eigen transforms. Experimental results conducted on large vocabulary conversational speech recognition (LVCSR) material from the switchboard corpus show that this strategy has better performance than ML-SAT and significantly reduces the number of parameters needed (an 87% reduction is achieved), while still effectively capturing the essential variation between speakers.

We address the problem of estimating the word error rate (WER) of an automatic speech recognition (ASR) system without using acoustic test data. This is an important problem which is faced by the designers of new applications which use ASR. Quick estimate of WER early in the design cycle can be used to guide the decisions involving dialog strategy and grammar design. Our approach involves estimating the probability distribution of the word hypotheses produced by the underlying ASR system given the text test corpus. A critical component of this system is a phonemic confusion model which seeks to capture the errors made by ASR on the acoustic data at a phonemic level. We use a confusion model composed of probabilistic phoneme sequence conversion rules which are learned from phonemic transcription pairs obtained by leave-one-out decoding of the training set. We show reasonably close estimation of WER when applying the system to test sets from different domains. 1.

Tone is an essential language phenomenon for Mandarin Chinese language. Until now, we still do not know exactly how context affects tone pattern variation in continuous Mandarin speech. In this paper, we proposed a decision tree based approach to obtain the quantitative result of tone pattern variation in continuous Mandarin speech. Many possible factors other than tone of neighboring syllables were taken into consideration when the decision tree was constructed, After the tree was established, 29 tone patterns were automatically obtained, and we found that syllable position in the word together with consonant/vowel type of the syllable made an important contribution to tone pattern variation in continuous utterance. We also presented a novel approach to integrate tone information into the search process at word level. Experimental results showed that the character error rate was reduced by 15.2%.

An accent adaptation approach using pronunciation variation modeling technology for the Mandarin accent was proposed in this paper. As the Chinese language is monosyllabic, the syllable pronunciation variation dictionary (SPVD) was built to depict the characteristics of accent. Firstly, the pronunciation modeling technology was utilized to get the context-independent and context-dependent accent-specific syllable confusion matrix according to the acoustic recognition results (pin-yin stream). Then the accent-specific Chinese SPVD was constructed from this confusion matrix. Finally, N-Best acoustic recognition candidates were re-scored with the help of SPVD. The proposed method was experimented on INTEL Shanghai-Accent Mandarin Corpus and the 863 standard Mandarin acoustic recognizer. The syllable recognition error rate was reduced 15% by context-independent SPVD, and 20% by context-dependent SPVD.