Results 281 to 290 of about 1,679,078 (335)
Some of the next articles are maybe not open access.
Speech zero-crossing rate compression for bandwidth compression
IEEE Transactions on Acoustics, Speech, and Signal Processing, 1975As analysis performed on a proposed special purpose hearing aid yields data on single-sidebanded voice zero-crossing rates extracted by a phase-locked loop (PLL), and also data on the logarithmically compressed voltage analog of the zero-crossing rate.
W. Done, R. Kirlin
openaire +1 more source
Speech compression CODIMEX system
IEEE Transactions on Audio, 1963A relatively simple installation is sufficient to obtain a four-to-one reduction of the frequency bandwidth occupied by a telephonic signal. The speech is decomposed into its three principal formants which constitute the basic information carrying elements.
openaire +1 more source
Speech Compression and Synthesis
1980Abstract : This report concludes our work for the past two years on speech compression and synthesis. A real-time variable-frame-rate LPC vocoder was implemented operating at an average rate of 2000 bits/s. We also tested our mixed-source model as part of the vocoder.
John Sorensen +3 more
openaire +1 more source
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
arXiv.orgWe introduce a text-to-speech (TTS) model called BASE TTS, which stands for $\textbf{B}$ig $\textbf{A}$daptive $\textbf{S}$treamable TTS with $\textbf{E}$mergent abilities. BASE TTS is the largest TTS model to-date, trained on 100K hours of public domain
Mateusz Lajszczak +18 more
semanticscholar +1 more source
Design Examples—Speech Compression
1986This last chapter is devoted entirely to the illustration, in the field of speech compression, of the theory developed in the previous chapters. We would like to emphasize that the results to be presented shortly are only of illustrative value and are not intended, in their present form, to be recommendations for practical consumption.
G. Gabor, Z. Györfi
openaire +1 more source
Stutterers' Perception of Time-Compressed Speech
Perceptual and Motor Skills, 1971This study represents an attempt to test the hypothesis (derived from the motor theory of speech perception) that persons who have stuttered for many years will be less facile than nonstutterers at decoding time-compressed speech. 4 stutterers and 4 nonstutterers answered questions and rewrote paragraphs and sentences presented at various rates of ...
openaire +2 more sources
Autoregressive Speech Synthesis without Vector Quantization
Annual Meeting of the Association for Computational LinguisticsWe present MELLE, a novel continuous-valued token based language modeling approach for text-to-speech synthesis (TTS). MELLE autoregressively generates continuous mel-spectrogram frames directly from text condition, bypassing the need for vector ...
Lingwei Meng +11 more
semanticscholar +1 more source
Speech pattern compression arrangement utilizing speech event identification
The Journal of the Acoustical Society of America, 1990There are disclosed speech encoding methods and arrangements, including among others a speech synthesizer that reproduces speech from the encoded speech signals. These methods and arrangements employ a reduced bandwidth encoding of speech for which the bandwidth more nearly than in prior arrangements approaches that of the rate of occurrences of the ...
openaire +1 more source
Wavelet transform for speech compression and denoising
International Conference on Multimedia Computing and Systems, 2018F. Chelali +3 more
semanticscholar +1 more source