Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2308.15945

The DeepZen Speech Synthesis System for Blizzard Challenge 2023

Christophe Veaux·Ranniery Maia·Spyridoula Papandreou
View original source ↗Read source document ↗Export metadata ↓

Abstract

This paper describes the DeepZen text to speech (TTS) system for Blizzard Challenge 2023. The goal of this challenge is to synthesise natural and high-quality speech in French, from a large monospeaker dataset (hub task) and from a smaller dataset by speaker adaptation (spoke task). We participated to both tasks with the same model architecture. Our approach has been to use an auto-regressive model, which retains an advantage for generating natural sounding speech but to improve prosodic control in several ways. Similarly to non-attentive Tacotron, the model uses a duration predictor and gaussian upsampling at inference, but with a simpler unsupervised training. We also model the speaking style at both sentence and word levels by extracting global and local style tokens from the reference speech. At inference, the global and local style tokens are predicted from a BERT model run on text. This BERT model is also used to predict specific pronunciation features like schwa elision and optional liaisons. Finally, a modified version of HifiGAN trained on a large public dataset and fine-tuned on the target voices is used to generate speech waveform. Our team is identified as O in the the Blizzard evaluation and MUSHRA test results show that our system performs second ex aequo in both hub task (median score of 0.75) and spoke task (median score of 0.68), over 18 and 14 participants, respectively.

Explore related subjects

eess.AScs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Christophe Veaux, Ranniery Maia, Spyridoula Papandreou. 2023-09-01. The DeepZen Speech Synthesis System for Blizzard Challenge 2023. https://arxiv.org/abs/2308.15945

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Deep Filter Estimation from Inter-Frame Correlations for Monaural Speech Dereverberation

Speech dereverberation with a distant microphone is challenging because reverberation is correlated with the target speech, and models trained on simulated data often generalize poorly to real recordings. We propose IF-CorrNet, a correlation-to-filter architecture for monaural dereverberation. Instead of feeding raw complex STFT coefficients to the network, IF-CorrNet computes inter-frame correlations among neighboring frames at each time-frequency bin and estimates multi-frame deep filters from these features with a dual-path Transformer backbone. This design makes inter-frame dependencies explicit at the network input while retaining a multi-frame filtering output, a pairing motivated by the normal equation of linear multi-frame filtering. On the REVERB Challenge corpus, IF-CorrNet achieves the best CD, LLR, SNRfw, and PESQ among the compared dereverberation baselines on SimData, and the highest SRMR among the compared systems on RealData. The ablation shows higher RealData SRMR with correlation inputs for both filtering and masking, with filtering adding a further gain.

eess.AS↗
arXiv2026

Recovering the Zipfian Distribution in Unsupervised Term Discovery

Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach -- K-means -- produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-based approaches (K-means, GMM, BIRCH) in both word- and syllable-level lexicon discovery across three languages, producing more Zipf-like distributions. Another bottom-up approach, agglomerative clustering with average linkage, also performs well, although it is computationally less efficient and allows for less control over the resulting distribution. Our work calls into question the dominance of centre-based clustering for term discovery, and promotes graph clustering as an attractive alternative.

eess.AS↗
arXiv2026

CHILDES-Aligned: A Curated Children's Speech Dataset via Multi-Model Timestamp Ensembling

CHILDES is a large-scale child speech corpus containing long-form recordings of naturalistic child-adult interactions, making it a valuable resource for studying child speech and language development. However, utterance-level timestamps provided in this corpus are often noisy, incomplete, or misaligned with the audio. As a result, utterances cannot always be reliably localized within long recordings, which limits the direct use of these data for training and evaluating speech models. In this work, we propose BEACON (Boundary Estimation via Alignment CONsensus), an ensemble timestamp-curation framework that refines utterance-level timestamps by aggregating knowledge from multiple off-the-shelf ASR models. Specifically, each model's word-level timestamp predictions are first aligned to provided human transcripts, and the final utterance time boundaries are determined by a consensus voting strategy. The framework is corpus-agnostic and applies to any long-form recording paired with a trusted transcript whose timestamps are unreliable or missing, offering a general recipe for timestamp curation. Leveraging this pipeline, we curate and release a 413-hour general-purpose child-speech dataset with corrected utterance-level timestamps, together with a 283-hour quality-controlled subset for ASR training. Fine-tuning on this subset yields up to an average 19.5% relative WER reduction on four out-of-domain child-speech benchmarks.

eess.AS↗