Automatic discovery of a phonetic inventory for unwritten languages for statistical speech synthesis
PK Muthukumar, AW Black - 2014 IEEE International …, 2014 - ieeexplore.ieee.org
Speech synthesis systems are typically built with speech data and transcriptions. In this
paper, we try to build synthesis systems when no transcriptions or knowledge about the …
paper, we try to build synthesis systems when no transcriptions or knowledge about the …
Use of articulatory bottle-neck features for query-by-example spoken term detection in low resource scenarios
G Mantena, K Prahallad - 2014 IEEE international conference …, 2014 - ieeexplore.ieee.org
For query-by-example spoken term detection (QbE-STD), generation of phone
posteriorgrams requires labelled data which would be difficult for languages with low …
posteriorgrams requires labelled data which would be difficult for languages with low …
Speech synthesis from found data
P Baljekar - 2018 - kilthub.cmu.edu
Text-to-speech synthesis (TTS) has progressed to such a stage that given a large, clean,
phonetically balanced dataset from a single speaker, it can produce intelligible, almost …
phonetically balanced dataset from a single speaker, it can produce intelligible, almost …
[PDF][PDF] Using articulatory features and inferred phonological segments in zero resource speech processing.
Unsupervised discovery of subword units is an important problem in recognition and
synthesis of zero-resource languages, in which phonesets may not be known and the only …
synthesis of zero-resource languages, in which phonesets may not be known and the only …
Articulatory controllable speech modification based on statistical inversion and production map**s
In this paper, we present an innovative way of utilizing the natural relationship between
speech sounds and articulatory movements by develo** an articulatory controllable …
speech sounds and articulatory movements by develo** an articulatory controllable …
[PDF][PDF] Articulatory controllable speech modification based on statistical feature map** with Gaussian mixture models.
This paper presents a novel speech modification method capable of controlling
unobservable articulatory parameters based on a statistical feature map** technique with …
unobservable articulatory parameters based on a statistical feature map** technique with …
[PDF][PDF] IIIT-H SWS 2013: Gaussian Posteriorgrams of Bottle-Neck Features for Query-by-Example Spoken Term Detection.
GV Mantena, K Prahallad - MediaEval, 2013 - academia.edu
This paper describes the experiments conducted for spoken web search (SWS) at
MediaEval 2013 evaluations. A conventional approach is to train a multi-layer perceptron …
MediaEval 2013 evaluations. A conventional approach is to train a multi-layer perceptron …
[PDF][PDF] Articulatory controllable speech modification based on Gaussian mixture models with direct waveform modification using spectrum differential
In our previous work, we have developed a speech modification system capable of
manipulating unobserved articulatory movements by sequentially performing speech-to …
manipulating unobserved articulatory movements by sequentially performing speech-to …
Non-linear Pitch Modification in Voice Conversion Using Artificial Neural Networks
Majority of the current voice conversion methods do not focus on the modelling local
variations of pitch contour, but only on linear modification of the pitch values, based on …
variations of pitch contour, but only on linear modification of the pitch values, based on …
[PDF][PDF] Query-by-example spoken term detection on low resource languages
G Mantena - 2015 - cdn.iiit.ac.in
The task of a query-by-example spoken term detection (QbE-STD) is to find a spoken query
within a spoken audio database. A key aspect of QbE-STD is to enable searching in multi …
within a spoken audio database. A key aspect of QbE-STD is to enable searching in multi …