Stephan Kanthak

Bio: Stephan Kanthak is an academic researcher from RWTH Aachen University. The author has contributed to research in topics: Word error rate & Machine translation. The author has an hindex of 18, co-authored 24 publications receiving 1018 citations. Previous affiliations of Stephan Kanthak include AT&T.

Context-dependent acoustic modeling using graphemes for large vocabulary speech recognition

Abstract: In this paper we propose to use a decision tree based on graphemic acoustic sub-word units together with phonetic questions. We also show that automatic question generation can be used to completely eliminate any manual effort.

Novel Reordering Approaches in Phrase-Based Statistical Machine Translation

Abstract: This paper presents novel approaches to reordering in phrase-based statistical machine translation. We perform consistent reordering of source sentences in training and estimate a statistical translation model. Using this model, we follow a phrase-based monotonic machine translation approach, for which we develop an efficient and flexible reordering framework that allows to easily introduce different reordering constraints. In translation, we apply source sentence reordering on word level and use a reordering automaton as input. We show how to compute reordering automata on-demand using IBM or ITG constraints, and also introduce two new types of reordering constraints. We further add weights to the reordering automata. We present detailed experimental results and show that reordering significantly improves translation quality.

On the integration of speech recognition and statistical machine translation.

Abstract: This paper focuses on the interface between speech recognition and machine translation in a speech translation system. Based on a thorough theoretical framework, we exploit word lattices of automatic speech recognition hypotheses as input to our translation system which is based on weighted finite-state transducers. We show that acoustic recognition scores of the recognized words in the lattices positively and significantly affect the translation quality. In experiments, we have found consistent improvements on three different corpora compared with translations of single best recognized results. In addition we build and evaluate a fully integrated speech translation model.

Speaker adaptive modeling by vocal tract normalization

Abstract: This paper presents methods for speaker adaptive modeling using vocal tract normalization (VTN) along with experimental tests on three databases. We propose a new training method for VTN: By using single-density acoustic models per HMM state for selecting the scale factor of the frequency axis, we avoid the problem that a mixture-density tends to learn the scale factors of the training speakers and thus cannot be used for selecting the scale factor. We show that using single Gaussian densities for selecting the scale factor in training results in lower error rates than using mixture densities. For the recognition phase, we propose an improvement of the well-known two-pass strategy: by using a non-normalized acoustic model for the first recognition pass instead of a normalized model, lower error rates are obtained. In recognition tests, this method is compared with a fast variant of VTN. The two-pass strategy is an efficient method, but it is suboptimal because the scale factor and the word sequence are determined sequentially. We found that for telephone digit string recognition this suboptimality reduces the VTN gain in recognition performance by 30% relative. In summary, on the German spontaneous speech task Verbmobil, the WSJ task and the German telephone digit string corpus SieTill, the proposed methods for VTN reduce the error rates significantly.

Improved methods for vocal tract normalization

Abstract: This paper presents improved methods for vocal tract normalization (VTN) along with experimental tests on three databases. We propose a new method for VTN in training: by using acoustic models with single Gaussian densities per state for selecting the normalization scales the need for the models to learn the normalization scales of the training speakers is avoided. We show that using single Gaussian densities for selecting the normalization scales in training results in lower error rates than using mixture densities. For VTN in recognition, we propose an improvement of the well-known multiple-pass strategy: by using an unnormalized acoustic model for the first recognition pass instead of a normalized model lower error rates are obtained. In recognition tests, this method is compared with a fast variant of VTN. The multiple-pass strategy is an efficient method but it is suboptimal because the normalization scale and the word sequence are determined sequentially. We found that for telephone digit string recognition this suboptimality reduces the VTN gain in recognition performance by 30% relative. On the German spontaneous scheduling task Verbmobil, the WSJ task and the German telephone digit string corpus SieTill the proposed methods for VTN reduce the error rates significantly.

Moses: Open Source Toolkit for Statistical Machine Translation

Abstract: We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

Joint-sequence models for grapheme-to-phoneme conversion

Abstract: Grapheme-to-phoneme conversion is the task of finding the pronunciation of a word given its written form. It has important applications in text-to-speech and speech recognition. Joint-sequence models are a simple and theoretically stringent probabilistic framework that is applicable to this problem. This article provides a self-contained and detailed description of this method. We present a novel estimation algorithm and demonstrate high accuracy on a variety of databases. Moreover, we study the impact of the maximum approximation in training and transcription, the interaction of model size parameters, n-best list generation, confidence measures, and phoneme-to-grapheme conversion. Our software implementation of the method proposed in this work is available under an Open Source license.

Large Language Models in Machine Translation

Abstract: Systems, methods, and computer program products for machine translation are provided. In some implementations a system is provided. The system includes a language model including a collection of n-grams from a corpus, each n-gram having a corresponding relative frequency in the corpus and an order n corresponding to a number of tokens in the n-gram, each n-gram corresponding to a backoff n-gram having an order of n-1 and a collection of backoff scores, each backoff score associated with an n-gram, the backoff score determined as a function of a backoff factor and a relative frequency of a corresponding backoff n-gram in the corpus.

OpenFst: a general and efficient weighted finite-state transducer library

Abstract: We describe OpenFst, an open-source library for weighted finite-state transducers (WFSTs). OpenFst consists of a C++ template library with efficient WFST representations and over twenty-five operations for constructing, combining, optimizing, and searching them. At the shell-command level, there are corresponding transducer file representations and programs that operate on them. OpenFst is designed to be both very efficient in time and space and to scale to very large problems. This library has key applications speech, image, and natural language processing, pattern and string matching, and machine learning. We give an overview of the library, examples of its use, details of its design that allow customizing the labels, states, and weights and the lazy evaluation of many of its operations. Further information and a download of the OpenFst library can be obtained from http://www.openfst.org.

Discriminative Training for Large-Vocabulary Speech Recognition Using Minimum Classification Error

Abstract: The minimum classification error (MCE) framework for discriminative training is a simple and general formalism for directly optimizing recognition accuracy in pattern recognition problems. The framework applies directly to the optimization of hidden Markov models (HMMs) used for speech recognition problems. However, few if any studies have reported results for the application of MCE training to large-vocabulary, continuous-speech recognition tasks. This article reports significant gains in recognition performance and model compactness as a result of discriminative training based on MCE training applied to HMMs, in the context of three challenging large-vocabulary (up to 100 k word) speech recognition tasks: the Corpus of Spontaneous Japanese lecture speech transcription task, a telephone-based name recognition task, and the MIT Jupiter telephone-based conversational weather information task. On these tasks, starting from maximum likelihood (ML) baselines, MCE training yielded relative reductions in word error ranging from 7% to 20%. Furthermore, this paper evaluates the use of different methods for optimizing the MCE criterion function, as well as the use of precomputed recognition lattices to speed up training. An overview of the MCE framework is given, with an emphasis on practical implementation issues