Search Results for author:
Found 54 papers, 4 papers with code
BASE TTS: Lessons from building a billion-parameter Text-to-Speech model on 100K hours of data
Echoing the widely-reported "emergent abilities" of large language models when trained on increasing volume of data, we show that BASE TTS variants built with 10K+ hours and 500M+ parameters begin to demonstrate natural prosody on textually complex sentences.
A Comparative Analysis of Pretrained Language Models for Text-to-Speech
In this study, we aim to address this gap by conducting a comparative analysis of different PLMs for two TTS tasks: prosody prediction and pause prediction.
Controllable Emphasis with zero data for text-to-speech
We show that this technique significantly closes the gap to methods that require explicit recordings.
eCat: An End-to-End Model for Multi-Speaker TTS & Many-to-Many Fine-Grained Prosody Transfer
We show that eCat statistically significantly reduces the gap in naturalness between CopyCat2 and human recordings by an average of 46. 7% across 2 languages, 3 locales, and 7 speakers, along with better target-speaker similarity in FPT.
Computer-assisted Pronunciation Training -- Speech synthesis is almost all you need
We show that these techniques not only improve the accuracy of three machine learning models for detecting pronunciation errors but also help establish a new state-of-the-art in the field.
Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody
In this paper, we examine simple extensions to a Transformer-based FastSpeech-like system, with the goal of improving prosody for multi-sentence TTS.
Expressive, Variable, and Controllable Duration Modelling in TTS
First, we propose a duration model conditioned on phrasing that improves the predicted durations and provides better modelling of pauses.
CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer
In this paper, we present CopyCat2 (CC2), a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually appropriate prosody, and c) transferring prosody at fine-grained level between any pair of seen speakers.
Distribution augmentation for low-resource expressive text-to-speech
This paper presents a novel data augmentation technique for text-to-speech (TTS), that allows to generate new (text, audio) training examples without requiring any additional data.
Multi-Scale Spectrogram Modelling for Neural Text-to-Speech
We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody.
Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments
Voice Conversion (VC) is a technique that aims to transform the non-linguistic information of a source utterance to change the perceived identity of the speaker.
A learned conditional prior for the VAE acoustic space of a TTS system
Many factors influence speech yielding different renditions of a given sentence.
Weakly-supervised word-level pronunciation error detection in non-native English speech
To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words.
Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling
A common approach to the automatic detection of mispronunciation in language learning is to recognize the phonemes produced by a student and compare it to the expected pronunciation of a native speaker.
EmoCat: Language-agnostic Emotional Voice Conversion
In this work we propose EmoCat, a language-agnostic emotional voice conversion model.
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
This paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS).
Prosodic Representation Learning and Contextual Sampling for Neural Text-to-Speech
In Stage II, we propose a novel method to sample from this learnt prosodic distribution using the contextual information available in text.
Analysis and Synthesis of Hypo and Hyperarticulated Speech
This paper focuses on the analysis and synthesis of hypo and hyperarticulated speech in the framework of HMM-based speech synthesis.
Maximum Phase Modeling for Sparse Linear Prediction of Speech
The proposed method is shown to significantly increase the sparsity of the LP residual signal and to be effective in two illustrative applications: speech polarity detection and excitation modeling.
Parametric Representation for Singing Voice Synthesis: a Comparative Evaluation
Various parametric representations have been proposed to model the speech signal.
Residual Excitation Skewness for Automatic Speech Polarity Detection
Detecting the correct speech polarity is a necessary step prior to several speech processing techniques.
Data-driven Detection and Analysis of the Patterns of Creaky Voice
This paper investigates the temporal excitation patterns of creaky voice.
Maximum Voiced Frequency Estimation: Exploiting Amplitude and Phase Spectra
Recent studies have shown that its proper estimation and modeling enhance the quality of statistical parametric speech synthesizers.
Glottal source estimation robustness: A comparison of sensitivity of voice source estimation techniques
This paper addresses the problem of estimating the voice source directly from speech waveforms.
Oscillating Statistical Moments for Speech Polarity Detection
An inversion of the speech polarity may have a dramatic detrimental effect on the performance of various techniques of speech processing.
Glottal Source Estimation using an Automatic Chirp Decomposition
In a previous work, we showed that the glottal source can be estimated from speech signals by computing the Zeros of the Z-Transform (ZZT).
Chirp Complex Cepstrum-based Decomposition for Asynchronous Glottal Analysis
It was recently shown that complex cepstrum can be effectively used for glottal flow estimation by separating the causal and anticausal components of speech.
On the Mutual Information between Source and Filter Contributions for Voice Pathology Detection
This paper addresses the problem of automatic detection of voice pathologies directly from the speech signal.
Phase-based Information for Voice Pathology Detection
In most current approaches of speech processing, information is extracted from the magnitude spectrum.
Eigenresiduals for improved Parametric Speech Synthesis
Statistical parametric speech synthesizers have recently shown their ability to produce natural-sounding and flexible voices.
A Comparative Evaluation of Pitch Modification Techniques
This paper addresses the problem of pitch modification, as an important module for an efficient voice transformation system.
Excitation-based Voice Quality Analysis and Modification
This paper investigates the differences occuring in the excitation for different voice qualities.
Using a Pitch-Synchronous Residual Codebook for Hybrid HMM/Frame Selection Speech Synthesis
The source signal is obtained by concatenating excitation frames picked up from the codebook, based on a selection criterion and taking target residual coefficients as input.
Causal-Anticausal Decomposition of Speech using Complex Cepstrum for Glottal Source Estimation
Via a systematic study of the windowing effects on the deconvolution quality, we show that the complex cepstrum causal-anticausal decomposition can be effectively used for glottal flow estimation when specific windowing criteria are met.
The Deterministic plus Stochastic Model of the Residual Signal and its Applications
The applicability of the DSM in two fields of speech processing is then studied.
Glottal Source Processing: from Analysis to Applications
The great majority of current voice technology applications relies on acoustic features characterizing the vocal tract response, such as the widely used MFCC of LPC parameters.
Complex Cepstrum-based Decomposition of Speech for Glottal Source Estimation
Homomorphic analysis is a well-known method for the separation of non-linearly combined signals.
A Deterministic plus Stochastic Model of the Residual Signal for Improved Parametric Speech Synthesis
For this, we hereby propose an adaptation of the Deterministic plus Stochastic Model (DSM) for the residual.
Detection of Glottal Closure Instants from Speech Signals: a Quantitative Review
The five techniques compared are the Hilbert Envelope-based detection (HE), the Zero Frequency Resonator-based method (ZFR), the Dynamic Programming Phase Slope Algorithm (DYPSA), the Speech Event Detection using the Residual Excitation And a Mean-based Signal (SEDREAMS) and the Yet Another GCI Algorithm (YAGA).
Joint Robust Voicing Detection and Pitch Estimation Based on Residual Harmonics
This paper focuses on the problem of pitch tracking in noisy conditions.
A Comparative Study of Glottal Source Estimation Techniques
Techniques based on the mixed-phase decomposition and on a closed-phase inverse filtering process turn out to give the best results on both clean synthetic and real speech signals.
Glottal Closure and Opening Instant Detection from Speech Signals
This paper proposes a new procedure to detect Glottal Closure and Opening Instants (GCIs and GOIs) directly from speech waveforms.
Singing Synthesis: with a little help from my attention
We present UTACO, a singing synthesis model based on an attention-based sequence-to-sequence mechanism and a vocoder based on dilated causal convolutions.
Voice Conversion for Whispered Speech Synthesis
We present an approach to synthesize whisper by applying a handcrafted signal processing recipe and Voice Conversion (VC) techniques to convert normally phonated speech to whispered speech.
Dynamic Prosody Generation for Speech Synthesis using Linguistics-Driven Acoustic Embedding Selection
Recent advances in Text-to-Speech (TTS) have improved quality and naturalness to near-human capabilities when considering isolated sentences.
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
This paper proposed a novel approach for the detection and reconstruction of dysarthric speech.
Fine-grained robust prosody transfer for single-speaker neural text-to-speech
However, when trained on a single-speaker dataset, the conventional prosody transfer systems are not robust enough to speaker variability, especially in the case of a reference signal coming from an unseen speaker.
Towards achieving robust universal neural vocoding
This vocoder is shown to be capable of generating speech of consistently good quality (98% relative mean MUSHRA when compared to natural speech) regardless of whether the input spectrogram comes from a speaker or style seen during training or from an out-of-domain scenario when the recording conditions are studio-quality.
In Other News: A Bi-style Text-to-speech Model for Synthesizing Newscaster Voice with Limited Data
Neural text-to-speech synthesis (NTTS) models have shown significant progress in generating high-quality speech, however they require a large quantity of training data.
Active and Semi-Supervised Learning in ASR: Benefits on the Acoustic and Language Models
The goal of this paper is to simulate the benefits of jointly applying active learning (AL) and semi-supervised training (SST) in a new speech recognition application.
Traditional Machine Learning for Pitch Detection
In this paper, we consider voicing detection as a classification problem and F0 contour estimation as a regression problem.
Robust universal neural vocoding
This paper introduces a robust universal neural vocoder trained with 74 speakers (comprised of both genders) coming from 17 languages.
Effect of data reduction on sequence-to-sequence neural TTS
Recent speech synthesis systems based on sampling from autoregressive neural networks models can generate speech almost undistinguishable from human recordings.
LSTM-based Whisper Detection
We prove that, with enough data, the LSTM model is indeed as capable of learning whisper characteristics from LFBE features alone compared to a simpler MLP model that uses both LFBE and features engineered for separating whisper and normal speech.
