Automatic building of synthetic voices from large multi-paragraph speech databases
نویسندگان
چکیده
Large multi paragraph speech databases encapsulate prosodic and contextual information beyond the sentence level which could be exploited to build natural sounding voices. This paper discusses our efforts on automatic building of synthetic voices from large multi-paragraph speech databases. We show that the primary issue of segmentation of large speech file could be addressed with modifications to forced-alignment technique and that the proposed technique is independent of the duration of the audio file. We also discuss how this framework could be extended to build a large number of voices from public domain large multi-paragraph recordings.
منابع مشابه
Automatic Building of Synthetic Voices from Audio Books
Current state-of-the-art text-to-speech systems produce intelligible speech but lack the prosody of natural utterances. Building better models of prosody involves development of prosodically rich speech databases. However, development of such speech databases requires a large amount of effort and time. An alternative is to exploit story style monologues (long speech files) in audio books. These...
متن کاملCLUSTERGEN: a statistical parametric synthesizer using trajectory modeling
Unit selection synthesis has shown itself to be capable of producing high quality natural sounding synthetic speech when constructed from large databases of well-recorded, well-labeled speech. However, the cost in time and expertise of building such voices is still too expensive and specialized to be able to build individual voices for everyone. The quality in unit selection synthesis is direct...
متن کاملSpeech recognition based confidence measures for building voices from untranscribed speech
Today, large amount of audio data is available on the web in the form of audiobooks, podcasts, video lectures, video blogs, news bulletins. In addition, we can effortlessly record and store audio data such as read/lecture/impromptu speech on hand-held devices. These data are rich in prosody, provide a plethora of voices to choose from, and their availability can significantly reduce the overhea...
متن کاملProsodic and Spectral iVectors for Expressive Speech Synthesis
This work presents a study on the suitability of prosodic and acoustic features, with a special focus on i-vectors, in expressive speech analysis and synthesis. For each utterance of two different databases, a laboratory recorded emotional acted speech, and an audiobook, several prosodic and acoustic features are extracted. Among them, i-vectors are built not only on the MFCC base, but also on ...
متن کاملHandling large audio files in audio books for building synthetic voices
One of the issues in using audio books for building a synthetic voice is the segmentation of large audio files. The use of standard forced-alignment to obtain phone boundaries on large audio files fails primarily because of huge memory requirements. Earlier works have attempted to resolve this problem by using large vocabulary speech recognition system employing restricted dictionary and langua...
متن کامل