Speech-driven gesture synthesis is a field of growing interest in virtual human creation. However, critical challenge the inherent intricate one-to-many mapping between speech and gestures. Previous studies have explored achieved significant progress with generative models. Notwithstanding, most synthetic gestures are still vastly less natural. This paper presents DiffMotion, novel speech-drive...

Current understanding of the cortical mechanisms of speech perception and production stems mostly from studies that focus on single words or sentences. However, it has been suggested that processing of real-life connected speech may rely on additional cortical mechanisms. In the present study, we examined the neural substrates of natural speech production and perception with magnetoencephalogra...

The objective of this project is to develop a robust and high-performance speech recognitiotl system using a segment-based approach to phonetic recognition. The recognition system will eventually be integrated with natural language processing to achieve spoken lallguagc understanding. Developed a phonetic recognition front-end and achieved 77% and 71% classiilcatiou accuracy under speaker-depen...

This paper presents two tonal issues in spoken Mandarin Chinese from the perspective of speech synthesis. One is a unique Chinese phonetic category Qingsheng ( ). Based on speech synthesis and natural speech analysis, two acoustic criteria were suggested for distinguishing Qingsheng from the unstressed syllables which occur frequently in natural speech. The other is a tone sandhi phenomenon whi...

Candidate brain regions constituting a neural network for preattentive phonetic perception were identified with fMRI and multivariate multiple regression of imaging data. Stimuli contrasted along speech/nonspeech, acoustic, or phonetic complexity (three levels each) and natural/synthetic dimensions. Seven distributed brain regions' activity correlated with speech and speech complexity dimension...

In this paper we present a trainable speech synthesis system that uses the trended Hidden Markov Model to generate the trajectories of spectral features of synthesis units. The synthesis units are trained from a transcribed continuous speech corpus, making the speech more natural than that produced by conventional diphone synthesisers which are generally trained from a highly articulated speech...

We study substitute vectors to solve the part-of-speech ambiguity problem in an unsupervised setting. Part-of-speech tagging is a crucial preliminary process in many natural language processing applications. Because many words in natural languages have more than one part-of-speech tag, resolving part-of-speech ambiguity is an important task. We claim that partof-speech ambiguity can be solved u...

In a text-to-speech system, spoken utterances are automatically produced from text. In this paper, we present a corpus-driven Tamil text-to-speech (TTS) system based on the concatenative synthesis approach. The most important qualities of a synthesized speech are naturalness and intelligibility. In this system, words and syllables are used as the basic units for synthesis. Our corpus consists o...

The comprehension of natural and synthetic speech in Swedish and American English was investigated using a sentence-by-sentence listening paradigm. The synthesized speech was generated by the KTH text-to-speech systems. Results indicated that sentence listening times were signzficantly longer only for American English synthetic speech as compared to natural speech. Text dijjjculty was found to ...