Alexis Moinet

Arnaud Joly, Marco Nicolis, Ekaterina Peterova et al. · amazon-science

We present a scalable method to produce high quality emphasis for text-to-speech (TTS) that does not require recordings or annotations. Many TTS models include a phoneme duration model. A simple but effective method to achieve emphasized speech consists in increasing the predicted duration of the emphasised word. We show that this is significantly better than spectrogram modification techniques improving naturalness by $7.3\%$ and correct testers' identification of the emphasized word in a sentence by $40\%$ on a reference female en-US voice. We show that this technique significantly closes the gap to methods that require explicit recordings. The method proved to be scalable and preferred in all four languages tested (English, Spanish, Italian, German), for different voices and multiple speaking styles.

Peter Makarov, Ammar Abbas, Mateusz Łajszczak et al.

Generating expressive and contextually appropriate prosody remains a challenge for modern text-to-speech (TTS) systems. This is particularly evident for long, multi-sentence inputs. In this paper, we examine simple extensions to a Transformer-based FastSpeech-like system, with the goal of improving prosody for multi-sentence TTS. We find that long context, powerful text features, and training on multi-speaker data all improve prosody. More interestingly, they result in synergies. Long context disambiguates prosody, improves coherence, and plays to the strengths of Transformers. Fine-tuning word-level features from a powerful language model, such as BERT, appears to profit from more training data, readily available in a multi-speaker setting. We look into objective metrics on pausing and pacing and perform thorough subjective evaluations for speech naturalness. Our main system, which incorporates all the extensions, achieves consistently strong results, including statistically significant improvements in speech naturalness over all its competitors.

Mateusz Łajszczak, Guillermo Cámbara, Yang Li et al.

We 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 speech data, achieving a new state-of-the-art in speech naturalness. It deploys a 1-billion-parameter autoregressive Transformer that converts raw texts into discrete codes ("speechcodes") followed by a convolution-based decoder which converts these speechcodes into waveforms in an incremental, streamable manner. Further, our speechcodes are built using a novel speech tokenization technique that features speaker ID disentanglement and compression with byte-pair encoding. 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. We design and share a specialized dataset to measure these emergent abilities for text-to-speech. We showcase state-of-the-art naturalness of BASE TTS by evaluating against baselines that include publicly available large-scale text-to-speech systems: YourTTS, Bark and TortoiseTTS. Audio samples generated by the model can be heard at https://amazon-ltts-paper.com/.

Marcel Granero-Moya, Penny Karanasou, Sri Karlapati et al.

State-of-the-art text-to-speech (TTS) systems have utilized pretrained language models (PLMs) to enhance prosody and create more natural-sounding speech. However, while PLMs have been extensively researched for natural language understanding (NLU), their impact on TTS has been overlooked. 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. Firstly, we trained a prosody prediction model using 15 different PLMs. Our findings revealed a logarithmic relationship between model size and quality, as well as significant performance differences between neutral and expressive prosody. Secondly, we employed PLMs for pause prediction and found that the task was less sensitive to small models. We also identified a strong correlation between our empirical results and the GLUE scores obtained for these language models. To the best of our knowledge, this is the first study of its kind to investigate the impact of different PLMs on TTS.

Mateusz Lajszczak, Animesh Prasad, Arent van Korlaar et al.

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. Our goal is to increase diversity of text conditionings available during training. This helps to reduce overfitting, especially in low-resource settings. Our method relies on substituting text and audio fragments in a way that preserves syntactical correctness. We take additional measures to ensure that synthesized speech does not contain artifacts caused by combining inconsistent audio samples. The perceptual evaluations show that our method improves speech quality over a number of datasets, speakers, and TTS architectures. We also demonstrate that it greatly improves robustness of attention-based TTS models.

Ammar Abbas, Bajibabu Bollepalli, Alexis Moinet et al.

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody. We present a generic multi-scale spectrogram prediction mechanism where the system first predicts coarser scale mel-spectrograms that capture the suprasegmental information in speech, and later uses these coarser scale mel-spectrograms to predict finer scale mel-spectrograms capturing fine-grained prosody. We present details for two specific versions of MSS called Word-level MSS and Sentence-level MSS where the scales in our system are motivated by the linguistic units. The Word-level MSS models word, phoneme, and frame-level spectrograms while Sentence-level MSS models sentence-level spectrogram in addition. Subjective evaluations show that Word-level MSS performs statistically significantly better compared to the baseline on two voices.

Penny Karanasou, Sri Karlapati, Alexis Moinet et al.

Many factors influence speech yielding different renditions of a given sentence. Generative models, such as variational autoencoders (VAEs), capture this variability and allow multiple renditions of the same sentence via sampling. The degree of prosodic variability depends heavily on the prior that is used when sampling. In this paper, we propose a novel method to compute an informative prior for the VAE latent space of a neural text-to-speech (TTS) system. By doing so, we aim to sample with more prosodic variability, while gaining controllability over the latent space's structure. By using as prior the posterior distribution of a secondary VAE, which we condition on a speaker vector, we can sample from the primary VAE taking explicitly the conditioning into account and resulting in samples from a specific region of the latent space for each condition (i.e. speaker). A formal preference test demonstrates significant preference of the proposed approach over standard Conditional VAE. We also provide visualisations of the latent space where well-separated condition-specific clusters appear, as well as ablation studies to better understand the behaviour of the system.

Jonas Rohnke, Tom Merritt, Jaime Lorenzo-Trueba et al.

Recently the state-of-the-art text-to-speech synthesis systems have shifted to a two-model approach: a sequence-to-sequence model to predict a representation of speech (typically mel-spectrograms), followed by a 'neural vocoder' model which produces the time-domain speech waveform from this intermediate speech representation. This approach is capable of synthesizing speech that is confusable with natural speech recordings. However, the inference speed of neural vocoder approaches represents a major obstacle for deploying this technology for commercial applications. Parallel WaveNet is one approach which has been developed to address this issue, trading off some synthesis quality for significantly faster inference speed. In this paper we investigate the use of a sentence-level conditioning vector to improve the signal quality of a Parallel WaveNet neural vocoder. We condition the neural vocoder with the latent vector from a pre-trained VAE component of a Tacotron 2-style sequence-to-sequence model. With this, we are able to significantly improve the quality of vocoded speech.

Sri Karlapati, Ammar Abbas, Zack Hodari et al.

In this paper, we introduce Kathaka, a model trained with a novel two-stage training process for neural speech synthesis with contextually appropriate prosody. In Stage I, we learn a prosodic distribution at the sentence level from mel-spectrograms available during training. In Stage II, we propose a novel method to sample from this learnt prosodic distribution using the contextual information available in text. To do this, we use BERT on text, and graph-attention networks on parse trees extracted from text. We show a statistically significant relative improvement of $13.2\%$ in naturalness over a strong baseline when compared to recordings. We also conduct an ablation study on variations of our sampling technique, and show a statistically significant improvement over the baseline in each case.

Thomas Drugman, Thomas Dubuisson, Alexis Moinet et al.

This paper addresses the problem of estimating the voice source directly from speech waveforms. A novel principle based on Anticausality Dominated Regions (ACDR) is used to estimate the glottal open phase. This technique is compared to two other state-of-the-art well-known methods, namely the Zeros of the Z-Transform (ZZT) and the Iterative Adaptive Inverse Filtering (IAIF) algorithms. Decomposition quality is assessed on synthetic signals through two objective measures: the spectral distortion and a glottal formant determination rate. Technique robustness is tested by analyzing the influence of noise and Glottal Closure Instant (GCI) location errors. Besides impacts of the fundamental frequency and the first formant on the performance are evaluated. Our proposed approach shows significant improvement in robustness, which could be of a great interest when decomposing real speech.

Sri Karlapati, Alexis Moinet, Arnaud Joly et al.

Prosody Transfer (PT) is a technique that aims to use the prosody from a source audio as a reference while synthesising speech. Fine-grained PT aims at capturing prosodic aspects like rhythm, emphasis, melody, duration, and loudness, from a source audio at a very granular level and transferring them when synthesising speech in a different target speaker's voice. Current approaches for fine-grained PT suffer from source speaker leakage, where the synthesised speech has the voice identity of the source speaker as opposed to the target speaker. In order to mitigate this issue, they compromise on the quality of PT. In this paper, we propose CopyCat, a novel, many-to-many PT system that is robust to source speaker leakage, without using parallel data. We achieve this through a novel reference encoder architecture capable of capturing temporal prosodic representations which are robust to source speaker leakage. We compare CopyCat against a state-of-the-art fine-grained PT model through various subjective evaluations, where we show a relative improvement of $47\%$ in the quality of prosody transfer and $14\%$ in preserving the target speaker identity, while still maintaining the same naturalness.

Thomas Drugman, Alexis Moinet, Thierry Dutoit et al.

This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as to construct a more realistic source signal. First a limited codebook of typical excitations is built from some training database. During the synthesis part, HMMs are used to generate filter and source coefficients. The latter coefficients contain both the pitch and a compact representation of target residual frames. 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. Subjective results show a relevant improvement compared to the basic technique.

Orazio Angelini, Alexis Moinet, Kayoko Yanagisawa et al.

We present UTACO, a singing synthesis model based on an attention-based sequence-to-sequence mechanism and a vocoder based on dilated causal convolutions. These two classes of models have significantly affected the field of text-to-speech, but have never been thoroughly applied to the task of singing synthesis. UTACO demonstrates that attention can be successfully applied to the singing synthesis field and improves naturalness over the state of the art. The system requires considerably less explicit modelling of voice features such as F0 patterns, vibratos, and note and phoneme durations, than previous models in the literature. Despite this, it shows a strong improvement in naturalness with respect to previous neural singing synthesis models. The model does not require any durations or pitch patterns as inputs, and learns to insert vibrato autonomously according to the musical context. However, we observe that, by completely dispensing with any explicit duration modelling it becomes harder to obtain the fine control of timing needed to exactly match the tempo of a song.

Marius Cotescu, Thomas Drugman, Goeric Huybrechts et al.

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. We investigate using Gaussian Mixture Models (GMM) and Deep Neural Networks (DNN) to model the mapping between acoustic features of normal speech and those of whispered speech. We evaluate naturalness and speaker similarity of the converted whisper on an internal corpus and on the publicly available wTIMIT corpus. We show that applying VC techniques is significantly better than using rule-based signal processing methods and it achieves results that are indistinguishable from copy-synthesis of natural whisper recordings. We investigate the ability of the DNN model to generalize on unseen speakers, when trained with data from multiple speakers. We show that excluding the target speaker from the training set has little or no impact on the perceived naturalness and speaker similarity of the converted whisper. The proposed DNN method is used in the newly released Whisper Mode of Amazon Alexa.

Thomas Drugman, Goeric Huybrechts, Viacheslav Klimkov et al.

Pitch detection is a fundamental problem in speech processing as F0 is used in a large number of applications. Recent articles have proposed deep learning for robust pitch tracking. In this paper, we consider voicing detection as a classification problem and F0 contour estimation as a regression problem. For both tasks, acoustic features from multiple domains and traditional machine learning methods are used. The discrimination power of existing and proposed features is assessed through mutual information. Multiple supervised and unsupervised approaches are compared. A significant relative reduction of voicing errors over the best baseline is obtained: 20% with the best clustering method (K-means) and 45% with a Multi-Layer Perceptron. For F0 contour estimation, the benefits of regression techniques are limited though. We investigate whether those objective gains translate in a parametric synthesis task. Clear perceptual preferences are observed for the proposed approach over two widely-used baselines (RAPT and DIO).

Thomas Merritt, Bartosz Putrycz, Adam Nadolski et al.

Statistical TTS systems that directly predict the speech waveform have recently reported improvements in synthesis quality. This investigation evaluates Amazon's statistical speech waveform synthesis (SSWS) system. An in-depth evaluation of SSWS is conducted across a number of domains to better understand the consistency in quality. The results of this evaluation are validated by repeating the procedure on a separate group of testers. Finally, an analysis of the nature of speech errors of SSWS compared to hybrid unit selection synthesis is conducted to identify the strengths and weaknesses of SSWS. Having a deeper insight into SSWS allows us to better define the focus of future work to improve this new technology.

Jaime Lorenzo-Trueba, Thomas Drugman, Javier Latorre et al.

This paper explores the potential universality of neural vocoders. We train a WaveRNN-based vocoder on 74 speakers coming from 17 languages. 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. When the recordings show significant changes in quality, or when moving towards non-speech vocalizations or singing, the vocoder still significantly outperforms speaker-dependent vocoders, but operates at a lower average relative MUSHRA of 75%. These results are shown to be consistent across languages, regardless of them being seen during training (e.g. English or Japanese) or unseen (e.g. Wolof, Swahili, Ahmaric).

Matei Mancas, Christian Frisson, Joëlle Tilmanne et al.

The 11th Summer Workshop on Multimodal Interfaces eNTERFACE 2015 was hosted by the Numediart Institute of Creative Technologies of the University of Mons from August 10th to September 2015. During the four weeks, students and researchers from all over the world came together in the Numediart Institute of the University of Mons to work on eight selected projects structured around intelligent interfaces. Eight projects were selected and their reports are shown here.