A Multitask Learning Perspective on Acoustic-Articulatory Inversion (2008)
This paper proposes the idea that by viewing an inversion mapping MLP from a Multitask Learning perspective, we may be able to relax two constraints which are inherent in using electromagnetic...
Festival Multisyn Voices for the 2007 Blizzard Challenge (2008)
Korin Richmond, Volker Strom, Robert Clark, Junichi Yamagishi, Sue Fitt
This paper describes selected aspects of the Festival Multisyn entry to the Blizzard Challenge 2007. We provide an overview of the process of building the three required voices from the speech data...
Towards an Improved Modeling of the Glottal Source in Statistical Parametric Speech Synthesis (2008)
João P. Cabral, Steve Renals, Korin Richmond, Junichi Yamagishi
This paper proposes the use of the Liljencrants-Fant model (LFmodel) to represent the glottal source signal in HMM-based speech synthesis systems. These systems generally use a pulse train to model...
Abstract Multisyn: Open-domain unit selection for the Festival speech synthesis system (2008)
We present the implementation and evaluation of an open-domain unit selection speech synthesis engine designed to be flexible enough to encourage further unit selection research and allow rapid voice...
We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algorithm for...
A multitask learning perspective on acoustic-articulatory inversion (2007)
This paper proposes the idea that by viewing an inversion mapping MLP from a Multitask Learning perspective, we may be able to relax two constraints which are inherent in using electromagnetic...
Festival multisyn voices for the 2007 blizzard challenge. (2007)
Richmond, Korin, Strom, Volker, Clark, Robert A J, Yamagishi, Junichi, Fitt, Sue
This paper describes selected aspects of the Festival Multisyn entry to the Blizzard Challenge 2007. We provide an overview of the process of building the three required voices from the speech data...
Speech production knowledge in automatic speech recognition (2007)
King, Simon, Frankel, Joe, Livescu, Karen, McDermott, Erik, Richmond, Korin, Wester, Mirjam
Although much is known about how speech is produced, and research into speech production has resulted in measured articulatory data, feature systems of different kinds and numerous models, speech...
Towards an improved modeling of the glottal source in statistical parametric speech synthesis (2007)
Cabral, Joao P, Renals, Steve, Richmond, Korin, Yamagishi, Junichi
This paper proposes the use of the Liljencrants-Fant model (LF-model) to represent the glottal source signal in HMM-based speech synthesis systems. These systems generally use a pulse train to model...
A trajectory mixture density network for the acoustic-articulatory inversion mapping (2006)
Abstract. We have previously proposed a trajectory model which is based on a mixture density network (MDN) trained with target variables augmented with dynamic features together with an algorithm for...
Multisyn voice for the Blizzard Challenge 2006 (2006)
Robert Clark, Korin Richmond, Volker Strom, Simon King
This paper describes the process of building unit selection voices for the Festival Multisyn engine using the ATR dataset provided for the Blizzard Challenge 2006. We begin by discussing recent...
A trajectory mixture density network for the acoustic-articulatory inversion mapping (2006)
This paper proposes a trajectory model which is based on a mixture density network trained with target features augmented with dynamic features together with an algorithm for estimating maximum...
Multisyn voices from ARCTIC data for the Blizzard challenge. (2005)
Clark, Robert A J, Richmond, Korin, King, Simon
This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is...
Informed Blending of Databases for Emotional Speech Synthesis (2005)
Hofer, Gregor O, Richmond, Korin, Clark, Robert A J
The goal of this project was to build a unit selection voice that could portray emotions with varying intensities. A suitable definition of an emotion was developed along with a descriptive framework...
Phonology impacts segmentation in online speech processing (2005)
Onnis, Luca, Monaghan, Padraic, Richmond, Korin, Chater, Nick
Peña, Bonatti, Nespor and Mehler(2002) investigated an artificial language where the structure of words was determined by nonadjacent dependencies between syllables. They found that segmentation of...
Multisyn voices from ARCTIC data for the Blizzard challenge. (2005)
Clark, Robert A J, Richmond, Korin, King, Simon
This paper describes the process of building unit selection voices for the Festival Multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build process is...
Informed Blending of Databases for Emotional Speech Synthesis (2005)
Hofer, Gregor O, Richmond, Korin, Clark, Robert A J
The goal of this project was to build a unit selection voice that could portray emotions with varying intensities. A suitable definition of an emotion was developed along with a descriptive framework...
Phonology impacts segmentation in online speech processing (2005)
Onnis, Luca, Monaghan, Padraic, Richmond, Korin, Chater, Nick
Peña, Bonatti, Nespor and Mehler(2002) investigated an artificial language where the structure of words was determined by nonadjacent dependencies between syllables. They found that segmentation of...
Luca Onnis, Padraic Monaghan, Korin Richmond, Nick Chater, Luca Onnis
Peña, Bonatti, Nespor, and Mehler (2002) investigated an artificial language where the structure of words was determined by nonadjacent dependencies between syllables. They found that segmentation...
Multisyn voices from ARCTIC data for the Blizzard challenge (2005)
Robert Clark, Korin Richmond, Simon King
This paper describes the process of building unit selection voices for the Festival multisyn engine using four ARCTIC datasets, as part of the Blizzard evaluation challenge. The build procedure is...
Festival 2 – Build Your Own General Purpose Unit Selection Speech Synthesiser (2004)
Clark, Robert A J, Richmond, Korin, King, Simon
This paper describes version 2 of the Festival speech synthesis system. Festival 2 provides a development environment for concatenative speech synthesis, and now includes a general purpose unit...
Festival 2 – Build Your Own General Purpose Unit Selection Speech Synthesiser (2004)
Clark, Robert A J, Richmond, Korin, King, Simon
This paper describes version 2 of the Festival speech synthesis system. Festival 2 provides a development environment for concatenative speech synthesis, and now includes a general purpose unit...
Festival 2 - Build Your Own General Purpose Unit Selection Speech Synthesiser (2004)
This paper describes version 2 of the Festival speech synthesis system. Festival 2 provides a development environment for concatenative speech synthesis, and now includes a general purpose unit...
Modelling the uncertainty in recovering articulation from acoustics (2003)
Richmond, Korin, King, Simon, Taylor, Paul
This paper presents an experimental comparison of the performance of the multilayer perceptron (MLP) with that of the mixture density network (MDN) for an acoustic-to-articulatory mapping task. A...
Modelling the uncertainty in recovering articulation from acoustics (2003)
Richmond, Korin, King, Simon, Taylor, Paul
This paper presents an experimental comparison of the performance of the multilayer perceptron (MLP) with that of the mixture density network (MDN) for an acoustic-to-articulatory mapping task. A...
COMPUTER SPEECH AND LANGUAGE (2003)
Korin Richmond, Simon King, Paul Taylor
Modelling the uncertainty in recovering articulation from acoustics
Researchers have been investigating methods for retrieving the articulation underlying an acoustic speech signal for more than three decades. A successful method would find many applications, for...
Researchers have been investigating methods for retrieving the articulation underlying an acoustic speech signal for more than three decades. A successful method would find many applications, for...
Frankel, Joe, Richmond, Korin, King, Simon, Taylor, Paul
We describe a speech recognition system which uses articulatory parameters as basic features and phone-dependent linear dynamic models. The system first estimates articulatory trajectories from the...
Continuous Speech Recognition Using Articulatory Data (2000)
Wrench, Alan A, Richmond, Korin
In this paper we show that there is measurable information in the articulatory system which can help to disambiguate the acoustic signal. We measure directly the movement of the lips, tongue, jaw,...
Frankel, Joe, Richmond, Korin, King, Simon, Taylor, Paul
We describe a speech recognition system which uses articulatory parameters as basic features and phone-dependent linear dynamic models. The system first estimates articulatory trajectories from the...
Continuous Speech Recognition Using Articulatory Data (2000)
Wrench, Alan A., Richmond, Korin
In this paper we show that there is measurable information in the articulatory system which can help to disambiguate the acoustic signal. We measure directly the movement of the lips, tongue, jaw,...
Speech recognition via phonetically-featured syllables (2000)
King, Simon, Taylor, Paul, Frankel, Joe, Richmond, Korin
We describe recent work on two new automatic speech recognition systems. The first part of this paper describes the components of a system based on phonological features (which we call Espresso-P) in...
Speech recognition via phonetically-featured syllables (2000)
King, Simon, Taylor, Paul, Frankel, Joe, Richmond, Korin
We describe recent work on two new automatic speech recognition systems. The first part of this paper describes the components of a system based on phonological features (which we call Espresso-P) in...
Speech recognition via phonetically-featured syllables (2000)
Simon King, Paul Taylor, Joe Frankel, Korin Richmond
We describe recent work on two new automatic speech recognition systems. The first part of this paper describes the components of a system based on phonological features (which we call Espresso-P) in...
Joe Frankel, Korin Richmond, Simon King, Paul Taylor
We describe a speech recognition system which uses articulatory parameters as basic features and phone-dependent linear dynamic models. The system first estimates articulatory trajectories from the...
Continuous speech recognition using articulatory data (2000)
Alan A. Wrench, Korin Richmond
In this paper we show that there is measurable information in the articulatory system which can help to disambiguate the acoustic signal. We measure directly the movement of the lips, tongue, jaw,...
Estimating velum height from acoustics during continuous speech. (1999)
This paper reports on present work, in which a recurrent neural network is trained to estimate `velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400...
Estimating velum height from acoustics during continuous speech. (1999)
This paper reports on present work, in which a recurrent neural network is trained to estimate `velum height' during continuous speech. Parallel acoustic-articulatory data comprising more than 400...
Detecting subject boundaries within text: A language-independent statistical approach. (1997)
Richmond, Korin, Smith, Andrew James, Amitay, Einat
We describe here an algorithm for detecting subject boundaries within text based on a statistical lexical similarity measure. Hearst has already tackled this problem with good results (Hearst, 1994)....
Detecting subject boundaries within text: A language-independent statistical approach. (1997)
Richmond, Korin, Smith, Andrew James, Amitay, Einat
We describe here an algorithm for detecting subject boundaries within text based on a statistical lexical similarity measure. Hearst has already tackled this problem with good results (Hearst, 1994)....
Detecting subject boundaries within text: A language independent statistical approach (1997)
We describe here an algorithm for detect-ing subject boundaries within text based on a statistical lexical similarity measure. Hearst has already tackled this problem with good results (Hearst,...
Detecting Subject Boundaries Within Text: A Language Independent Statistical Approach (1997)
Korin Richmond, Andrew Smith, Buccleuch Place, Einat Amitay
We describe here an algorithm for detecting subject boundaries within text based on a statistical lexical similarity measure. Hearst has already tackled this problem with good results (Hearst, 1994)....