REVIEW 15 cited by
Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Recent advancements in speech generation models have been significantly driven by the use of large-scale training data. However, producing highly spontaneous, human-like speech remains a challenge due to the scarcity of large, diverse, and spontaneous speech datasets. In response, we introduce Emilia, the first large-scale, multilingual, and diverse speech generation dataset. Emilia starts with over 101k hours of speech across six languages, covering a wide range of speaking styles to enable more natural and spontaneous speech generation. To facilitate the scale-up of Emilia, we also present Emilia-Pipe, the first open-source preprocessing pipeline designed to efficiently transform raw, in-the-wild speech data into high-quality training data with speech annotations. Experimental results demonstrate the effectiveness of both Emilia and Emilia-Pipe. Demos are available at: https://emilia-dataset.github.io/Emilia-Demo-Page/.
Forward citations
Cited by 15 Pith papers
-
FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model
FlexiSLM is the first spoken language model supporting dynamic and controllable frame rates on speech input and output, outperforming fixed-rate 7B models at high quality and enabling faster inference at lower rates l...
-
Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness
Embedding watermarks inside a codec-like autoencoder's continuous latent space improves EnCodec-24k bit accuracy to ~95–97%, but the gain is in-distribution and does not transfer to EnCodec-16k.
-
StellarTTS: Sparse Temporal Embedding for Low-Latency and Robust Speech Synthesis
A mobile-oriented 83M-parameter masked transformer with sparse phone-anchored temporal embeddings achieves RTF 0.08 and lower WER than MaskGCT/F5-TTS on Seed-TTS test sets.
-
DLLM-TTS: Block Discrete Diffusion Language Model for Text-to-Speech Synthesis
Block discrete diffusion over X-Codec2 tokens yields competitive zero-shot TTS with 0.6B parameters, 20K training hours, and a 0.15 real-time factor.
-
Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders
Sparse autoencoders on a TTS language model yield interpretable features that causally control attributes such as laughter, gender, and speech rate via targeted interventions.
-
BareWave: Waveform-Native Flow-Matching Text-to-Speech
BareWave develops a waveform-native flow-matching framework for direct text-to-waveform TTS using representation alignment, staged noise scheduling, and velocity-aware perceptual alignment to achieve strong zero-shot ...
-
Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
Block-diffusion decoder with prior-calibrated scoring and early stopping produces streaming zero-shot TTS at quality comparable to AR and NAR baselines with lower real-time factor.
-
StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration
StreamChar decouples LLM-based orchestration from DiT denoising to achieve real-time long-horizon streaming character audio-video generation with reduced drift and misalignment.
-
Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training
Jointly training the watermark embedder/detector with the source separator enables ~1% bit-error-rate recovery of per-stem watermarks after mixing and separation, where independent training yields 15–35%.
-
UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models
A single LLM can do ASR and zero-shot TTS on continuous speech features by switching between causal and bidirectional attention, reaching competitive but not state-of-the-art results.
-
Over-the-Air Adversarial Attack Detection: from Datasets to Defenses
AdvSV 2.0 provides 629k adversarial and bona fide audio samples for automatic speaker verification, with a neural replay simulator attack and a one-class contrastive domain-aligned detector reaching 11.2% EER.
-
AudioCodecBench: A Comprehensive Benchmark for Audio Codec Evaluation
A four-part benchmark plus a semantic/acoustic token taxonomy for comparing audio codecs, with correlation analysis across ten models.
-
Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
A multitask classifier built on Whisper features flags multi-speaker, non-English, music, noisy, and synthetic speech clips in large in-the-wild corpora, and a new 21k-clip labeled dataset is released.
-
REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers
REF-VC is a zero-shot voice conversion system that random-erases redundant parts of speech-embedding features to stay robust to noise, and uses shortcut-distilled flow matching to convert speech in only four steps.
-
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching
F5-TTS generates natural speech from text via flow matching on DiT with simple text padding, ConvNeXt refinement, and sway sampling, trained on 100K hours multilingual data.
Discussion (0). Sign in to comment.