NST (Natural Speech Technology)
Browse by
Natural Speech Technology (NST) is an EPSRC Programme Grant with the aim of significantly advancing the state-of-the-art in speech technology by making it more natural, approaching human levels of reliability, adaptability and conversational richness. NST is a collaboration between the Centre for Speech Technology Research (CSTR) at the University of Edinburgh, the Speech Group at the University of Cambridge and the Speech and Hearing Research Group (SpandH), University of Sheffield.
More information can be found at www.natural-speech-technology.org/about.
Items in this Collection
-
Listening test materials for "A template-based approach for speech synthesis intonation generation using LSTMs"
This data release contains listening test materials associated with the paper "A template-based approach for speech synthesis intonation generation using LSTMs", presented at Interspeech 2016 in San Francisco, USA. -
Listening test materials for "Waveform generation based on signal reshaping for statistical parametric speech synthesis"
The dataset contains the testing stimuli and listeners' MUSHRA test responses for the Interspeech 2016 paper "Waveform generation based on signal reshaping for statistical parametric speech synthesis". On this paper, we ... -
## SUPERSEDED: THIS DATASET HAS BEEN REPLACED. ## Noisy speech database for training speech enhancement algorithms and TTS models
## SUPERSEDED: THIS DATASET HAS BEEN REPLACED by the one which can be found at https://doi.org/10.7488/ds/2117. ## Clean and noisy parallel speech database. The database was designed to train and test speech enhancement ... -
Listening test materials for "Evaluating comprehension of natural and synthetic conversational speech"
Current speech synthesis methods typically operate on isolated sentences and lack convincing prosody when generating longer segments of speech. Similarly, prevailing TTS evaluation paradigms, such as intelligibility ... -
Listening test materials for "Robust TTS duration modelling using DNNs"
This data release contains listening test materials associated with the paper "Robust TTS duration modelling using DNNs", presented at ICASSP 2016 in Shanghai, China. -
Listening test materials for "From HMMs to DNNs: Where do the improvements come from?"
This data release contains listening test materials associated with the paper "From HMMs to DNNs: Where do the improvements come from?", presented at ICASSP 2016 in Shanghai, China. -
Experiment materials for "Testing the consistency assumption: pronunciation variant forced alignment in read and spontaneous speech synthesis"
The matlab scripts are used to analyse the results files in the results folder. The Test_Wavs are the wavfiles used for the listening test divided by group and the pre-test test files. -
Listening test materials for "Smooth Talking: Articulatory Join Costs for Unit Selection"
This is the listening test data for the experiment presented in the ICASSP 2016 paper "Smooth Talking: Articulatory Join Costs for Unit Selection", which proposes and evaluates computation of unit selection join costs in ... -
Listening test materials for "Deep neural network-guided unit selection synthesis"
These are the listening test materials for "Deep neural network-guided unit selection synthesis". They include the waveforms played to listeners as well as the listeners' responses. -
Listening test materials for "Multiple Feed-forward Deep Neural Networks for Statistical Parametric Speech Synthesis"
In the paper which this data accompanies, we investigate a combination of several feed-forward deep neural networks (DNNs) for a high-quality statistical parametric speech synthesis system. Recently, DNNs have significantly ... -
Experiment materials for "Disfluencies in change detection in natural, vocoded and synthetic speech."
The current dataset is associated with the DiSS paper "Disfluencies in change detection in natural, vocoded and synthetic speech." In this paper we investigate the effect of filled pauses, a discourse marker and silent ... -
Experiment materials for "The temporal delay hypothesis: Natural, vocoded and synthetic speech."
Including disfluencies in synthetic speech is being explored as a way of making synthetic speech sound more natural and conversational. How to measure whether the resulting speech is actually more natural, however, is not ... -
Listening test materials for "A study of speaker adaptation for DNN-based speech synthesis"
The dataset contains the testing stimuli and listeners' MUSHRA test responses for the Interspeech 2015 paper, "A study of speaker adaptation for DNN-based speech synthesis". In this paper, we conduct an experimental analysis ... -
Superseded - Human vs Machine Spoofing
This Item has been replaced. Please see Wester, M; Wu, Z; Yamagishi, J. (2015). Human vs Machine Spoofing, [dataset]. University of Edinburgh. https://doi.org/10.7488/ds/258. -
Human vs Machine Spoofing
Listening test materials for "Human vs Machine Spoofing Detection on Wideband and Narrowband data." They include lists of the speech material selected from the SAS spoofing database and the listeners' responses. The main ... -
Listening test materials for "Deep neural network context embeddings for model selection in rich-context HMM synthesis"
These are the listening test materials for "Deep neural network context embeddings for model selection in rich-context HMM synthesis". They include the waveforms played to listeners as well as the listeners' responses. -
Artificial Personality
This dataset is associated with the paper “Artificial Personality and Disfluency” by Mirjam Wester, Matthew Aylett, Marcus Tomalin and Rasmus Dall published at Interspeech 2015, Dresden. The focus of this paper is ...