An overlap-add technique based on waveform similarity (WSOLA) for high quality time-scale modification of speech

By Werner Verhelst, Marc Roelands. 1993

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Neural Speech Synthesis with Transformer Network (2018, methodology): “and stitch them by some algorithms such as Viterbi (Viterbi 1967) followed by signal process methods (Charpentier and Stella 1986; Verhelst and Roelands 1993) to generate new waves.”
Wavenet Based Low Rate Speech Coding (2017, background): “Resyn-chronization can be achieved with conventional techniques [23].”
RobuTrans: A Robust Transformer-Based Text-to-Speech Model (2020, methodology): “Concatenative TTS systems (Hunt and Black 1996) split original waves into small units, and stitch them by some algorithms such as Viterbi (Viterbi 1967) followed by signal process methods (Charpentier and Stella 1986; Verhelst and Roelands 1993) to generate new waves.”
ASVspoof 2019: A large-scale public database of synthesized, converted and replayed speech (2019, methodology): “In this method, an F0 transformed residual signal is ﬁrst generated from the input speech waveform by applying WSOLA [42], inverse ﬁltering, and resampling processes.”
Audio augmentation for speech recognition (2015, methodology): “The WSOLA [16] based implementation in the tempo command of the SoX tool was used to achieve this perturbation.”
Real-Time Signal Estimation From Modified Short-Time Fourier Transform Magnitude Spectra (2007, methodology): “Such approaches include the G&L method [1], the synchronized overlap and add algorithm (SOLA) [15], and its various modifications such as WSOLA [16], PAOLA [17], PSOLA [18], the phase vocoder algorithm [19], and some methods for building specific Fig.”