Rahul Chitturi

Learn More
Speech is the most prominent and natural form of communication between humans. Human beings have long been motivated to create computer that can understand and talk like human. When the research tries to develop certain recognition system they require certain previously stored data i. e. database for respective recognition system. There are various speech(More)
In this paper, we discuss our efforts in the development of Indian language speech databases in Tamil, Telugu and Marathi for building large vocabulary speech recognition systems. We have collected speech data from about 560 speakers in these three languages. We discuss the design and methodology of collection of speech databases. We also present(More)
The variation in speech due to dialect is a factor which significantly impacts speech system performance. In this study, we investigate effective methods of combining acoustic and language information to take advantage of (i) speaker based acoustic traits as well as (ii) content based word selection across the text sequence. For acoustics, a GMM based(More)
The vowel sounds are perhaps the most interesting class of sound in English. Their importance to the classification and representation of written text is very low; however, most practical speech recognition systems rely heavily on vowel recognition to achieve high performance. In this paper we propose a technique for the vowel classification using Linear(More)
Building an Automatic Speech Recognition System for a language requires a good amount of clean speech data and significant effort in training it. More so for foreign language speech recognition, where the native accent of the speaker brings about, a considerable difference in the pronunciation. In this paper, we propose a neural network based approach to(More)
The training of precise speech recognition models depends on accurate segmentation of the phonemes in a training corpus. Segmentation is typically performed using HMMs, but recent speech recognition work suggests that the transient acoustic features characteristic of manner-class phoneme boundaries (landmarks) may be more precisely localized using acoustic(More)
There are different kinds of TTS (Text to Speech) systems are already available for Personal computers and web applications. In the Platform of Smart Phone, few of TTS systems are available for Bangla Language. Nowadays android is a popular platform considering Smartphone. There are few Bangla TTS Systems are Available with different kind of Mechanisms and(More)
The training of precise speech recognition models depends on accurate segmentation of the phonemes in a training corpus. Segmentation is typically performed using HMMs, but recent speech recognition work suggests that the transient acoustic features characteristic of manner-class phoneme boundaries (landmarks) may be more precisely localized using acoustic(More)
In this paper, we investigate two important issues that influence dialect classification: (i) exploring dialect dependent features, and (ii) an effective way of combining spectral, excitation, and vocal tract information to improve dialect classification. The motivation is that dialect dependent features such as formants, LSP (Line Spectral Pairs) and MEPZ(More)
This paper studies the impact of written language variations and the way it affects the capitalization task over time. A discriminative approach, based on maximum entropy models, is proposed to perform capitalization, taking the language changes into consideration. The proposed method makes it possible to use large corpora for training. The evaluation is(More)