M. Ali Basha Shaik

Sub-lexical language models for German LVCSR

One of the major difficulties related to German LVCSR is the rich morphology nature of German, leading to high out-of-vocabulary (OOV) rates, and high language model (LM) perplexities. Normally, compound words make up an essential fraction of the German vocabulary. Most compound OOVs are composed of frequent in-vocabulary words. Here, we investigate the use of sub-lexical LMs based on different approaches for word decomposition, namely supervised and unsupervised decomposition, as well as decomposition derived from grapheme-to-phoneme (G2P) conversion. In the later approach, we augment a normal word model with a set of grapheme-phoneme pairs called graphones used to model the OOV words. A novel approach is proposed to select the representative graphone sequences for OOVs based on unsupervised decomposition and word-pronunciation alignment. We obtain relative reductions in word error rate (WER) from 4.2% to 6.5% with respect to a comparable full-words system.

Using morpheme and syllable based sub-words for polish LVCSR

Polish is a synthetic language with a high morpheme-per-word ratio. It makes use of a high degree of inflection leading to high out-of-vocabulary (OOV) rates, and high Language Model (LM) perplexities. This poses a challenge for Large Vocabulary and Continuous Speech Recognition (LVCSR) systems. Here, the use of morpheme and syllable based units is investigated for building sub-lexical LMs. A different type of sub-lexical units is proposed based on combining morphemic or syllabic units with corresponding pronunciations. Thereby, a set of grapheme-phoneme pairs called graphones are used for building LMs. A relative reduction of 3.5% in Word Error Rate (WER) is obtained with respect to a traditional system based on full-words.

Improved strategies for a zero oov rate LVCSR system

In this work, multiple hierarchical language modeling strategies for a zero OOV rate large vocabulary continuous speech recognition system are investigated. In our previously proposed hierarchical approach, a full-word language model and a context independent character-level LM (CLM) are directly used during search. The novelty of this work is to jointly model the character-level prior and the pronunciation probabilities, to introduce across-word context into the characterlevel LM, and to properly normalize the character-level LM using prefix-tree based normalization for the hierarchical approach. Significant reductions in-terms of word error rates (WER) on the best full-word Quaero Polish LVCSR system are reported.

Investigation of Segmental Conditional Random Fields for large vocabulary handwriting recognition

Multiple types of models are used in handwriting recognition and can be broadly categorized into generative and discriminative models. Gaussian Hidden Markov Models are used successfully in most of the systems. Discriminative training can be applied to these models to improve them further. Alternatively, Segmental Conditional Random Fields have the advantage of being discriminative as well as segmental. The novelty of this work is the investigation of Segmental Conditional Random Fields for handwriting recognition. In addition, Multi-Layer Perceptrons and Long Short Term Memory Recurrent Neural Networks are compared for the observations generation in this framework. Various types of features are investigated in the segmental models for handwriting recognition. Furthermore, class-based language model features are proposed to extend this model. Visual features based on moments are extracted at a word level to make the model more robust. Experimental results on English handwriting show a relative reduction of 13.7% in terms of word error rate w.r.t. the baseline system. The proposed system also outperforms the Gaussian Hidden Markov Models trained discriminatively using the minimum phone error criterion by a relative reduction of 6.9% in terms of word error rate.