Speech concatenation and synthesis using an overlap-add sinusoidal model
نویسندگان
چکیده
In this paper, an algorithm for the concatenation of speech signal segments taken from disjoint utterances is presented. The algorithm is based on the Analysis-bySynthesis/Overlap-Add (ABS/OLA) sinusoidal model [1, 2, 3], which is capable of performing high quality pitchand time-scale modi cation of both speech and music signals. With the incorporation of concatenation and smoothing techniques, the model is capable of smoothing the transitions between separately-analyzed speech segments by matching the timeand frequencydomain characteristics of the signals at their boundaries. The application of these techniques in a textto-speech system based on concatenation of diphone sinusoidal models is also presented.
منابع مشابه
An enhanced ABS/OLA sinusoidal model for waveform synthesis in TTS
This paper describes a method for text-to-speech waveform synthesis based on the Analysis-by-Synthesis/Overlap-Add (ABS/OLA) sinusoidal model. This model has been shown in previous work to be a useful framework for pitch and time-scale modi cation of both speech and music signals. This paper explores some extensions of the original ABS/OLA formulation that attempt to overcome speci c artifacts,...
متن کاملSynthesis of sinusoids via non-overlapping inverse Fourier transform
| Additive synthesis is a powerful tool for the analysis/modiication/synthesis of complex audio or speech signals. However, the cost of wavetable sinusoidal synthesis can become prohibitive for large numbers of sinusoids (more than a few hundred). In that case, techniques based on the inverse Fourier transform ooer an attractive alternative, being 200% to 300% more eecient than wavetable synthe...
متن کاملA Pitch-Asynchronous Simple Method for Speech Synthesis by Diphone Concatenation using the Deterministic plus Stochastic Model
One of the most common approaches to speech synthesis is the concatenation of diphones, extracted from a previously recorded database. The prosodic parameters of the recorded speech fragments have to be adapted to the specifications of the new utterances to be synthesized. In this paper, the deterministic plus stochastic model of speech is used to modify and smoothly concatenate the analyzed di...
متن کاملEpoch synchronous non-overlap-add (ESNOLA) method-based concatenative speech synthesis system for Bangla
In the last decade there has been a shift towards development of speech synthesizer using concatenative synthesis technique instead of parametric synthesis. There are a number of different methodologies for concatenative synthesis like TDPSOLA, PSOLA, and MBROLA. This paper, describes a concatenative speech synthesis system based on Epoch Synchronous Non Over Lapp Add (ESNOLA) technique, for st...
متن کاملNepali Text to Speech Synthesis System using ESNOLA Method of Concatenation
This paper confer the tools and methodology used in developing a Nepali Text to Speech Synthesis System, which is based on concatenative approach employing Epoch Synchronous Non Overlap Add Method (ESNOLA), which uses signal dictionary having raw sound signal representing parts of phonemes as a speech database. The developed system is an unintonated (flat) TTS system where the pitch of the pre-...
متن کامل